anton-abyzov/specweave
GitHubfrontend
Modern frontend development with React, Vue, and web technologies
kafka-kubernetes
Kubernetes deployment expert for Apache Kafka. Guides K8s deployments using Helm charts, operators (Strimzi, Confluent), StatefulSets, and production best practices. Activates for kubernetes, k8s, helm, kafka on kubernetes, strimzi, confluent operator, kafka operator, statefulset, kafka helm chart, k8s deployment, kubernetes kafka, deploy kafka to k8s.
kafka-architecture
Expert knowledge of Apache Kafka architecture, cluster design, capacity planning, partitioning strategies, replication, and high availability. Auto-activates on keywords kafka architecture, cluster sizing, partition strategy, replication factor, kafka ha, kafka scalability, broker count, topic design, kafka performance, kafka capacity planning.
n8n-kafka-workflows
n8n workflow automation with Kafka integration expert. Covers Kafka trigger node, producer node, event-driven workflows, error handling, retries, and no-code/low-code event processing patterns. Activates for n8n kafka, kafka trigger, kafka producer, n8n workflows, event-driven automation, no-code kafka, workflow patterns.
kafka-cli-tools
Expert knowledge of Kafka CLI tools (kcat, kcli, kaf, kafkactl). Auto-activates on keywords kcat, kafkacat, kcli, kaf, kafkactl, kafka cli, kafka command line, produce message, consume topic, list topics, kafka metadata. Provides command examples, installation guides, and tool comparisons.
expo-workflow
Expert in Expo SDK 54+ development workflows, EAS Build, EAS Update, native tabs, Expo Router v6, expo-video, expo-audio, dev clients, expo-cli commands, app configuration, and deployment strategies. Activates for expo, expo go, eas build, eas update, expo config, app.json, eas.json, expo dev client, expo prebuild, expo eject, over-the-air updates, expo doctor, expo install, managed workflow, bare workflow, expo router, native tabs, liquid glass.
spec-driven-brainstorming
Spec-driven brainstorming and product discovery expert. Helps teams ideate features, break down epics, conduct story mapping sessions, prioritize using MoSCoW/RICE/Kano, and validate ideas with lean startup methods. Activates for brainstorming, product discovery, story mapping, feature ideation, prioritization, MoSCoW, RICE, Kano model, lean startup, MVP definition, product backlog, feature breakdown.
qa-lead
QA Lead that creates test suites ONE FILE AT A TIME to prevent crashes. Handles test plans, test cases, testing strategies, quality gates. **CRITICAL CHUNKING RULE - Large test suites (15 files) done incrementally.** Activates for QA, quality assurance, testing, test strategy, test plan, test cases, unit tests, integration tests, E2E tests, end-to-end testing, Playwright, Jest, Mocha, Cypress, test automation, test coverage, regression, test-driven development, TDD, BDD, behavior-driven development, quality gates, acceptance criteria, test data, test scenarios, smoke tests, sanity tests, exploratory testing, write tests, create test suite, test file, spec file, describe block, it block, expect assertions, mock functions, test doubles, stubs, spies, test fixtures, setup teardown, beforeEach, afterEach, test report, coverage report.
kafka-observability
Kafka monitoring and observability expert. Guides Prometheus + Grafana setup, JMX metrics, alerting rules, and dashboard configuration. Activates for kafka monitoring, prometheus, grafana, kafka metrics, jmx exporter, kafka observability, monitoring setup, kafka dashboards, alerting, kafka performance monitoring, metrics collection.
plugin-development
Expert Claude Code plugin development covering plugin structure, slash commands, auto-activating skills, sub-agents, plugin.json configuration, YAML frontmatter, activation keywords, directory structure, and plugin best practices. Activates for plugin development, create plugin, claude plugin, slash command, skill activation, SKILL.md, plugin.json, claude code plugin, how to make plugin.
kafka-streams-topology
Kafka Streams topology design expert. Covers KStream vs KTable vs GlobalKTable, topology patterns, stream operations (filter, map, flatMap, branch), joins, windowing strategies, and exactly-once semantics. Activates for kafka streams topology, kstream, ktable, globalkTable, stream operations, stream joins, windowing, exactly-once, topology design.
react-native-setup
Expert in React Native 0.83+ and Expo SDK 54+ environment setup. Helps with Node.js 20+, Xcode 16.1+, Android Studio, watchman, CocoaPods, EAS Build, simulators, emulators, and troubleshooting. Activates for environment setup, installation issues, xcode setup, android studio, simulators, emulators, react-native init, expo init, development environment, SDK configuration, EAS Build, development builds.
kafka-iac-deployment
Infrastructure as Code (IaC) deployment expert for Apache Kafka. Guides Terraform deployments across Apache Kafka (KRaft mode), AWS MSK, Azure Event Hubs. Activates for terraform, iac, infrastructure as code, deploy kafka, provision kafka, aws msk, azure event hubs, kafka infrastructure, terraform modules, cloud deployment, kafka deployment automation.
test-aware-planner
Test-Aware Planning agent that generates tasks.md **ONE USER STORY AT A TIME** with embedded test plans. **CRITICAL CHUNKING RULE - Prevents crashes.** Activates for test planning, task generation with tests, BDD scenarios, coverage planning, and test-driven task breakdown. Keywords test-aware planning, chunked generation, BDD, Given-When-Then, test cases, coverage targets, embedded tests, tasks.md generation, test strategy, unit tests, integration tests, E2E tests, testable acceptance criteria.
confluent-kafka-connect
Kafka Connect integration expert. Covers source and sink connectors, JDBC, Elasticsearch, S3, Debezium CDC, SMT (Single Message Transforms), connector configuration, and data pipeline patterns. Activates for kafka connect, connectors, source connector, sink connector, jdbc connector, debezium, smt, data pipeline, cdc.
roadmap-planner
Product roadmap and feature prioritization expert. Creates product roadmaps, prioritizes features using RICE/MoSCoW/Kano frameworks, defines success metrics and KPIs, and translates technical decisions into business impact. Activates for roadmap, prioritization, RICE, MoSCoW, Kano, product planning, feature ranking, success metrics, KPIs, stakeholder communication, business impact, Q1 Q2 Q3 Q4 planning, quarterly goals, release planning, feature prioritization.
mobile-debugging
Expert in debugging React Native and Expo mobile applications. Covers React DevTools, Flipper, Chrome DevTools, network debugging, crash analysis, error boundaries, debugging native modules, remote debugging, breakpoints, console logging strategies. Activates for debugging mobile app, react native debugging, flipper, devtools, breakpoints, crash, error, remote debugging, network request debugging, console.log, debugger, react native debugger.
lsp-integration
LSP (Language Server Protocol) integration expert. Provides semantic code understanding using language servers for TypeScript, JavaScript, Python, Go, Rust, and more. Handles code navigation (go to definition, find references), symbol search, hover information, diagnostics, refactoring. 100x faster than grep for code exploration. Activates for LSP, language server, TypeScript, JavaScript, Python, Go, Rust, Java, C#, code navigation, go to definition, find references, find all references, hover type, type information, symbol search, document symbols, workspace symbols, diagnostics, code errors, type errors, refactoring, rename symbol, code actions, auto import, semantic analysis, code intelligence, intellisense, autocomplete context, type inference.
docusaurus
Docusaurus documentation expert. Specializes in creating, configuring, and deploying Docusaurus documentation sites, MDX authoring, plugin development, theming, versioning, and i18n. Activates for Docusaurus, documentation site, docs, MDX, markdown docs, static site generator, documentation framework, Docusaurus plugins, Docusaurus themes, public docs, docs site design, landing page, hero section, docs styling, spec-weave.com, documentation redesign, docs UI, docs theme, dark mode docs, sidebar navigation, algolia search, versioned docs, i18n docs, blog posts, announcement bar, footer customization, docusaurus config.
ralph-loop-guide
Ralph Loop Best Practices - Guidelines for effective autonomous iteration. Based on Anthropic's official ralph-loop plugin. Helps design prompts for iterative AI development with clear completion signals.
metro-bundler
Expert in Metro bundler configuration, optimization, troubleshooting, caching strategies, custom transformers, asset management, source maps, bundling performance. Activates for metro, metro bundler, metro.config.js, bundler, bundle, cache, transformer, asset resolver, metro cache, bundling error, unable to resolve module, port 8081.
native-modules
Expert in React Native native modules with New Architecture, Turbo Modules with Codegen, Fabric renderer, JSI (JavaScript Interface), New Architecture migration, bridging JavaScript and native code, iOS Swift modules, Android Kotlin modules, expo config plugins. IMPORTANT - Use Context7 for version-specific APIs. Activates for native module, native code, bridge, turbo module, JSI, fabric, autolinking, custom native module, ios module, android module, swift, kotlin, objective-c, java native code, codegen, new architecture.
aws-cost-expert
Deep AWS cost optimization expertise covering EC2 Reserved Instances, Savings Plans, Spot Instances, Lambda cost optimization, S3 lifecycle policies, RDS Reserved Instances, Cost Explorer, AWS Budgets, Trusted Advisor, Compute Optimizer, Cost Anomaly Detection, and AWS-specific FinOps best practices. Activates for AWS costs, AWS pricing, EC2 costs, Lambda costs, S3 costs, RDS costs, AWS savings plans, AWS reserved instances, AWS spot instances, AWS cost explorer, AWS budgets, reduce AWS bill.
github-issue-tracker
Task-level GitHub issue tracking for SpecWeave increments. Provides fine-grained progress tracking via issue comments, task checklists, and labels. Enables team collaboration on individual tasks. Activates for task tracking, GitHub comments, issue updates, task progress, team collaboration, granular tracking.
pm-closure-validation
Expert PM validation for increment closure with 3-gate quality checks (tasks, tests, documentation). Acts as final quality gate before closing increments. Validates task completion, test coverage, documentation updates, and detects scope creep. Activates for /done command, increment closure, close increment, validate increment, completion check, quality gate, PM approval, ready to close, scope creep detection, release validation, increment validation.
jira-sync
Sync SpecWeave increments with JIRA epics/stories. Content flows SpecWeave→JIRA, status flows JIRA→SpecWeave. Activates ONLY when user asks questions about JIRA integration or needs help configuring JIRA sync. Does NOT activate for slash commands. For syncing, use /sw-jira:sync command instead. Coordinates with jira-mapper agent.
mlops-dag-builder
Design DAG-based MLOps pipeline architectures with Airflow, Dagster, Kubeflow, or Prefect. Activates for DAG orchestration, workflow automation, pipeline design patterns, CI/CD for ML. Use for platform-agnostic MLOps infrastructure - NOT for SpecWeave increment-based ML (use ml-pipeline-orchestrator instead).
deploy-router
Smart deployment platform router for Vercel vs Cloudflare vs GitHub Pages. Analyzes project structure, framework, SEO needs, runtime requirements, AND repository visibility (private/public). Routes to Cloudflare for private repos (GitHub Pages requires paid plan), Vercel for dynamic SEO, GitHub Pages only for public repos. Activates for deploy, vercel vs cloudflare, where to deploy, cloudflare workers, cloudflare pages, vercel deployment, edge deployment, SSR deployment, static site deployment, which hosting, deployment recommendation, github pages, private repo deployment.
experiment-tracker
Manages ML experiment tracking with MLflow, Weights & Biases, or SpecWeave's built-in tracking. Activates for "track experiments", "MLflow", "wandb", "experiment logging", "compare experiments", "hyperparameter tracking". Automatically configures tracking tools to log to SpecWeave increment folders, ensuring all experiments are documented and reproducible. Integrates with SpecWeave's living docs for persistent experiment knowledge.
ml-pipeline-orchestrator
Orchestrates complete machine learning pipelines within SpecWeave increments. Activates when users request "ML pipeline", "train model", "build ML system", "end-to-end ML", "ML workflow", "model training pipeline", or similar. Guides users through data preprocessing, feature engineering, model training, evaluation, and deployment using SpecWeave's spec-driven approach. Integrates with increment lifecycle for reproducible ML development.
ado-sync
Bidirectional synchronization between SpecWeave increments and Azure DevOps work items (two-way sync by default). Activates ONLY when user asks questions about Azure DevOps integration or needs help configuring ADO sync. Does NOT activate for slash commands. For syncing, use /sw-ado:sync command instead.
brownfield-analyzer
Analyzes existing brownfield projects to map documentation structure to SpecWeave's PRD/HLD/Spec/Runbook pattern. Scans folders, classifies documents, detects external tools (Jira, ADO, GitHub), and creates project context map for just-in-time migration. Activates for brownfield, existing project, migrate, analyze structure, legacy documentation.
increment-quality-judge-v2
Enhanced AI-powered quality assessment with RISK SCORING (BMAD pattern) and quality gate decisions. Evaluates specifications, plans, and tests for clarity, testability, completeness, feasibility, maintainability, edge cases, and RISKS. Provides PASS/CONCERNS/FAIL decisions. Activates for validate quality, quality check, assess spec, evaluate increment, spec review, quality score, risk assessment, qa check, quality gate, /sw:qa command.
reflective-reviewer
Self-reflection specialist that analyzes completed work for quality issues, security vulnerabilities, and improvement opportunities. Performs comprehensive code review covering OWASP Top 10, best practices, testing gaps, performance, and technical debt. Activates after task completion to provide constructive feedback and catch issues early before code review. Activates for self-reflection, code review, quality assessment, security review, OWASP check, best practices review, testing gaps, performance review, technical debt, lessons learned, what went well, what could improve, post-task analysis, code quality, reflection.
detector
Detects SpecWeave context (.specweave/ directory exists) and provides workflow documentation. Explains available slash commands and workflow. Keywords slash commands, /sw:increment, /increment, /sw:do, /sw:progress, /sw:validate, /sw:done, specweave commands, workflow help, specweave folder.
code-simplifier
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.
reflect
Self-improving AI memory system that learns from sessions. Stores learnings in skill-specific MEMORY.md files. Supports cross-platform Claude Code and non-Claude environments. Smart merging preserves user learnings during marketplace updates. Activates for reflect, remember, learn from session, memory, self-improvement, AI memory, correction patterns, skill learning, persistent memory.
cv-pipeline-builder
Computer vision ML pipelines for image classification, object detection, semantic segmentation, and image generation. Activates for "computer vision", "image classification", "object detection", "CNN", "ResNet", "YOLO", "image segmentation", "image preprocessing", "data augmentation". Builds end-to-end CV pipelines with PyTorch/TensorFlow, integrated with SpecWeave increments.
archive-increments
Intelligent increment archiving expert. Analyzes increment age, status, and activity to recommend archiving strategy. Keeps workspace clean while preserving history. Activates for archive increments, clean workspace, too many increments, archive old, archive completed, preserve history, _archive folder.
infrastructure
Generates Infrastructure-as-Code ONE LAYER AT A TIME (Compute → Database → Storage → Monitoring) to prevent crashes. Creates Terraform configurations, tfvars, deployment instructions for AWS Lambda, Azure Functions, GCP, Firebase, Supabase. **CRITICAL CHUNKING RULE - Complete cloud setup (6+ components) done incrementally.** Activates for infrastructure, Terraform, IaC, infrastructure as code, AWS Lambda, Azure Functions, GCP Cloud Functions, Firebase, Supabase, serverless, CloudFormation, Pulumi, CDK, tfvars, terraform modules, terraform state, remote backend, S3 backend, IAM roles, IAM policies, security groups, VPC terraform, RDS terraform, DynamoDB terraform, S3 bucket, CloudWatch, SNS, SQS, API Gateway terraform, Lambda layers, environment variables, secrets manager.
confluent-ksqldb
ksqlDB stream processing expert. Covers SQL-like queries on Kafka topics, stream and table concepts, joins, aggregations, windowing, materialized views, and real-time data transformations. Activates for ksqldb, ksql, stream processing, kafka sql, real-time analytics, windowing, stream joins, table joins, materialized views.
automl-optimizer
Automated machine learning with hyperparameter optimization using Optuna, Hyperopt, or AutoML libraries. Activates for "automl", "hyperparameter tuning", "optimize hyperparameters", "auto tune model", "neural architecture search", "automated ml". Systematically explores model and hyperparameter spaces, tracks all experiments, and finds optimal configurations with minimal manual intervention.
progress-sync
Comprehensive progress synchronization expert. Explains when and how to use /sw:sync-progress for multi-system sync (tasks → docs → external tools). AUTO-CREATES missing external issues. Activates for sync progress, update progress, sync everything, sync all systems, sync to GitHub, sync to JIRA, how to sync, progress synchronization, multi-system sync, create github issue, no github issue linked.
framework
Expert knowledge of SpecWeave framework structure, rules, conventions, and increment lifecycle. Deep understanding of source-of-truth discipline, increment naming, living docs sync. Covers SpecWeave-specific hooks (post-task-completion), and increment discipline. Activates for specweave rules, increment lifecycle, source of truth, increment naming, tasks.md format, spec.md structure, living docs sync, specweave hooks, where do files go, how to use specweave, specweave best practices, specweave conventions.
technical-writing
Creates high-quality technical documentation including API documentation, user guides, tutorials, architecture documents, README files, release notes, and technical specifications. Produces clear, structured, and comprehensive documentation following industry best practices. Use when writing technical documentation, creating API docs, developing user guides, documenting architecture, writing tutorials, preparing release notes, or when users mention "technical writing", "documentation", "API docs", "user guide", "tutorial", "README", "technical specification", "architecture document", or "developer documentation".
diagrams-generator
Generate Mermaid diagrams following C4 conventions. Activates for create diagram, draw diagram, visualize, system diagram, architecture diagram, C4 diagram, context diagram, container diagram, component diagram, sequence diagram, ER diagram, entity relationship, data model, deployment diagram. Coordinates with diagrams-architect agent.
claude-sdk
Expert knowledge of Claude Code SDK, API, tools (Read, Write, Edit, Bash, Grep, Glob), agent tools (Task, Skill, SlashCommand), plugin hooks, MCP integration, and Claude Code extension development. Activates for claude sdk, claude api, claude tools, Read tool, Write tool, Edit tool, Task tool, Skill tool, claude hooks, MCP, claude code api.
ado-mapper
Expert in bidirectional conversion between SpecWeave increments and Azure DevOps (ADO) Epics/Features/User Stories/Tasks. Handles export (increment → ADO), import (ADO → increment), and bidirectional sync with conflict resolution. Activates for ADO sync, Azure DevOps sync, work item creation, import from ADO.
increment-work-router
Smart work continuation system that detects implementation intent and routes to active increment or creates new one. Activates for implement, complete, build, add, develop, work on, continue, resume, finish, fix, resolve, address, let's implement, let's build, start working, begin implementation, add feature, create feature.
smart-reopen-detector
Detects when user reports issues with recently completed work and suggests reopening relevant tasks, user stories, or increments. Auto-activates on keywords: not working, broken, bug, issue, problem, failing, error, crash, regression, still broken, incorrect, missing, wrong. Scans active and recently completed (7 days) work to find related items. Provides smart suggestions with relevance scoring.
kafka-mcp-integration
MCP server integration for Kafka operations. Auto-activates on keywords kafka mcp, mcp server, mcp configure, mcp setup, kanapuli, tuannvm, confluent mcp, kafka integration. Provides configuration examples and connection guidance for all 4 MCP servers.
living-docs-navigator
Navigate and load project living documentation for context. Provides a table of contents for specs, ADRs, architecture docs, and operations runbooks. Use when implementing features, making design decisions, or needing project context. Keywords - living docs, context, ADR, architecture, specs, documentation, project knowledge.
release-coordinator
Coordinates multi-repository releases with dependency management, release order orchestration, and cross-repo validation. Handles coordinated releases (lockstep versioning), independent releases, and umbrella versioning. Creates release increments spanning multiple repositories, manages release dependencies (repo A must release before B), generates comprehensive release plans, validates pre-release checks across all repos. Activates for coordinate releases, multi-repo release, release dependencies, release order, cross-repo release, synchronized release, orchestrate release, release planning, multi-service release, coordinated deployment.
model-explainer
Model interpretability and explainability using SHAP, LIME, feature importance, and partial dependence plots. Activates for "explain model", "model interpretability", "SHAP", "LIME", "feature importance", "why prediction", "model explanation". Generates human-readable explanations for model predictions, critical for trust, debugging, and regulatory compliance.
sw:validated-api
Generate a validated REST API endpoint with automatic test execution
external-sync-wizard
Expert guide for setting up bidirectional synchronization between SpecWeave and external tools (GitHub Issues, Jira Epics, Azure DevOps Work Items). Provides interactive setup wizards with sync direction options (bidirectional, export-only, import-only, manual). Activates for GitHub sync, Jira integration, Azure DevOps, ADO, external tool setup, issue tracking sync, sync configuration, bidirectional sync, import issues, export increments, sync direction, GitHub issues, Jira epics, work items, project management tools.
plugin-validator
Validates SpecWeave plugin installation when EXPLICITLY requested by user. Ensures marketplace registered, core plugin installed, and context-specific plugins available. ONLY activates for explicit validation requests - does NOT auto-activate for workflow commands to avoid false positives. Activates ONLY for plugin validation, environment setup, validate plugins, check plugins, specweave init, fresh setup, marketplace registration.
code-standards-detective
Coding standards discovery agent. Performs deep analysis of codebase to detect naming conventions, import patterns, function characteristics, type usage, error handling, and anti-patterns. Generates evidence-based coding standards documentation with statistical confidence levels and real code examples. Parses ESLint, Prettier, TypeScript configs. Detects security issues and maintainability concerns. Activates for coding standards, code conventions, naming conventions, style guide, code analysis, detect patterns, import patterns, function patterns, type patterns, error handling patterns, anti-patterns, eslint config, prettier config, typescript config, code style, code quality rules, project conventions, consistency check, coding guidelines.
tdd-orchestrator
Master TDD orchestrator specializing in red-green-refactor discipline, multi-agent workflow coordination, and comprehensive test-driven development practices. Enforces TDD best practices across teams with AI-assisted testing and modern frameworks. Activates for TDD, test-driven development, test driven, red-green-refactor, write tests first, test first, failing test, make test pass, refactor with tests, Kent Beck, TDD cycle, outside-in TDD, inside-out TDD, London style TDD, Chicago style TDD, test doubles, mocking TDD, test isolation, test pyramid, unit tests TDD, integration tests TDD, acceptance tests, ATDD, specification by example, executable specifications, tests first, with tdd, using tdd, tdd approach, tdd workflow, tdd mode.
docs-updater
Updates living documentation during implementation. Syncs task completion to docs, changes [DRAFT] to [COMPLETE], maintains bidirectional links. Activates for update docs, sync documentation, mark complete, documentation updates, living docs sync.
code-standards-analyzer
Coding standards discovery and documentation expert. Analyzes codebase to detect naming conventions, patterns, anti-patterns, and best practices. Generates or updates coding standards documentation in .specweave/docs/internal/governance/. Detects ESLint/Prettier configs, analyzes TypeScript/JavaScript patterns, finds security issues, and creates evidence-based standards with confidence levels. Activates for analyze coding standards, discover conventions, code style analysis, detect patterns, coding guidelines, what are the standards, code quality check, naming conventions, linting rules, best practices analysis, standards audit, code review standards, detect anti-patterns.
jira-resource-validator
Validates Jira projects and boards exist, creates missing resources automatically. Smart enough to prompt user to select existing or create new projects. For boards, accepts either IDs (validates existence) or names (creates boards and updates .env with IDs). NEW - Per-project configuration support - JIRA_BOARDS_{ProjectKey} for hierarchical board organization across multiple projects. Activates for jira setup, jira validation, jira configuration, missing jira project, missing jira boards, jira .env setup, per-project boards.
time-series-forecaster
Time series forecasting with ARIMA, Prophet, LSTM, and statistical methods. Activates for "time series", "forecasting", "predict future", "trend analysis", "seasonality", "ARIMA", "Prophet", "sales forecast", "demand prediction", "stock prediction". Handles trend decomposition, seasonality detection, multivariate forecasting, and confidence intervals with SpecWeave increment integration.
export-skills
Export SpecWeave skills to Agent Skills open standard format (agentskills.io). Converts Claude Code plugin skills to portable SKILL.md files compatible with GitHub Copilot, VS Code, Gemini CLI, Cursor, and other Agent Skills-compatible tools. Activates for export skills, agent skills, github skills, skills.md, agentskills, portable skills, convert skills, skill export, cross-platform skills.
github-issue-standard
Standard format for ALL GitHub issues created by SpecWeave. Ensures checkable acceptance criteria, task connections, working links, and consistent metadata. Activates for create GitHub issue, sync to GitHub, format GitHub issue, standardize issue.
github-multi-project
Expert at organizing specs and splitting tasks across multiple GitHub repositories. Handles monorepo, polyrepo, and parent repo architectures. Activates for multi-project GitHub setups, task splitting, spec organization, team allocation, cross-repo coordination.
feature-engineer
Comprehensive feature engineering for ML pipelines: data quality assessment, feature creation, selection, transformation, and encoding. Activates for "feature engineering", "create features", "feature selection", "data preprocessing", "handle missing values", "encode categorical", "scale features", "feature importance". Ensures features are production-ready with automated validation, documentation, and integration with SpecWeave increments.
diagrams-architect
Expert in creating Mermaid diagrams following C4 Model and SpecWeave conventions. Specializes in system architecture, sequence diagrams, ER diagrams, and deployment diagrams. Activates for diagram creation, architecture visualization, data modeling, sequence flows, C4 diagrams, HLD, LLD, Mermaid diagram, flowchart, class diagram, state diagram, entity relationship, database schema visualization, API flow diagram, microservices diagram, system overview, architecture diagram, draw diagram, create diagram, visualize architecture, show flow, explain visually.
cloud-pricing
Expert knowledge of cloud provider pricing models for AWS, Azure, GCP covering compute, storage, database, networking, and serverless services. Includes 2025 pricing data, regional differences, free tiers, pricing calculators, and cost comparison across providers. Activates for cloud pricing, how much does it cost, price comparison, AWS vs Azure vs GCP pricing, pricing calculator, estimate costs, regional pricing, free tier, what's cheaper.
context-optimizer
Second-pass context optimization that analyzes user prompts and removes irrelevant specs, agents, and skills from loaded context. Achieves 80%+ token reduction through smart cleanup. Activates for optimize context, reduce tokens, clean context, smart context, precision loading.
code-reviewer
程式碼審查。觸發：review、審查、檢查、看一下、有沒有問題、安全。
github-sync
Two-way synchronization between SpecWeave specs and GitHub Projects (push & pull by default). Activates ONLY when user asks questions about GitHub integration or needs help configuring GitHub sync. Does NOT activate for slash commands. For syncing, use /sw-github:sync-spec command instead.
model-registry
Centralized model versioning, staging, and lifecycle management. Activates for "model registry", "model versioning", "model staging", "deploy to production", "rollback model", "model metadata", "model lineage", "promote model", "model catalog". Manages ML model lifecycle from development through production with SpecWeave increment integration.
version-aligner
Aligns versions across multiple repositories according to release strategy (lockstep, independent, umbrella). Handles semantic versioning constraints, detects version conflicts, suggests version bumps based on conventional commits, validates cross-repo compatibility, manages version matrices for umbrella releases. Activates for version alignment, align versions, version sync, semver, version conflicts, version bump, version compatibility, cross-repo versions, umbrella version matrix, lockstep versioning.
ml-deployment-helper
Prepares ML models for production deployment with containerization, API creation, monitoring setup, and A/B testing. Activates for "deploy model", "production deployment", "model API", "containerize model", "docker ml", "serving ml model", "model monitoring", "A/B test model". Generates deployment artifacts and ensures models are production-ready with monitoring, versioning, and rollback capabilities.
hetzner-provisioner
Provisions infrastructure on Hetzner Cloud with Terraform/Pulumi. Generates IaC code for CX11/CX21/CX31 instances, managed Postgres, SSL configuration, Docker deployment. Activates for deploy on Hetzner, Hetzner Cloud, budget deployment, cheap hosting, $10/month hosting.
performance-optimization
Expert performance decisions for iOS/tvOS: when to optimize vs premature optimization, profiling tool selection, SwiftUI view identity trade-offs, and memory management strategies. Use when debugging performance issues, optimizing slow screens, or reducing memory usage. Trigger keywords: performance, Instruments, Time Profiler, Allocations, memory leak, view identity, lazy loading, @StateObject, retain cycle, image caching, faulting, batch operations
preview
Documentation view expert for Docusaurus integration. Launches interactive server for SpecWeave living documentation with hot reload, auto-generated sidebar, and Mermaid diagrams. Works in ANY SpecWeave project with auto-setup. Supports both internal (port 3015) and public (port 3016) docs. Activates for preview docs, view documentation, Docusaurus server, docs UI, documentation website, local docs server, hot reload docs, static site build.
confluent-schema-registry
Schema Registry expert for Avro, Protobuf, and JSON Schema management. Covers schema evolution strategies, compatibility modes, validation, and best practices for managing schemas in Confluent Cloud and self-hosted Schema Registry. Activates for schema registry, avro, protobuf, json schema, schema evolution, compatibility modes, schema validation.
device-testing
Expert in React Native testing strategies including unit tests with Jest, integration tests, E2E tests with Detox, component testing with React Native Testing Library, snapshot testing, mocking native modules, testing on simulators and real devices. Activates for testing, jest, detox, e2e, unit test, integration test, component test, test runner, mock, snapshot test, testing library, react native testing library, test automation.
serverless-recommender
Intelligent serverless platform recommendation expert. Detects project context (pet-project, startup, enterprise), analyzes workload suitability, ranks platforms (AWS Lambda, Azure Functions, GCP Cloud Functions, Firebase, Supabase), and provides comprehensive recommendations with cost estimates. Activates for serverless recommendations, platform selection, AWS vs Azure vs GCP, Firebase vs Supabase, serverless architecture, should I use serverless, which serverless platform, serverless cost, serverless free tier, Lambda vs Functions, cloud functions comparison.
security-patterns
Security Pattern Detector - Real-time detection of dangerous coding patterns during file edits. Based on Anthropic's official security-guidance hook. Activates proactively when writing code. Warns about command injection, XSS, unsafe deserialization, dynamic code execution.
ado-multi-project
Expert at organizing specs and splitting tasks across multiple Azure DevOps projects. Handles project-per-team, area-path-based, and team-based architectures. Intelligently maps increments and specs to correct projects based on content analysis. Activates for multi-project Azure DevOps setups, task splitting, spec organization, team allocation, cross-project coordination.
compliance-architecture
Enterprise-grade compliance architecture for SOC 2, HIPAA, GDPR, PCI-DSS. Provides compliance checklists, security controls, audit guidance, and regulatory requirements for serverless and cloud architectures. Activates for compliance, HIPAA, SOC2, SOC 2, GDPR, PCI-DSS, PCI DSS, regulatory, healthcare data, payment card, data protection, audit, security standards, regulated industry, BAA, business associate agreement, DPIA, data protection impact assessment.
grafana-dashboards
Create and manage production Grafana dashboards for real-time visualization of system and application metrics. Use when building monitoring dashboards, visualizing metrics, or creating operational observability interfaces.
billing-automation
Build automated billing systems for recurring payments, invoicing, subscription lifecycle, and dunning management. Use when implementing subscription billing, automating invoicing, or managing recurring payment systems.
slo-implementation
Define and implement Service Level Indicators (SLIs) and Service Level Objectives (SLOs) with error budgets and alerting. Use when establishing reliability targets, implementing SRE practices, or measuring service performance.
ado-resource-validator
Validates Azure DevOps projects and resources exist, creates missing resources automatically. Smart enough to prompt user to select existing or create new projects. Supports multiple projects for project-per-team strategy, area paths for area-path-based strategy, and teams for team-based strategy. NEW - Per-project configuration support - AZURE_DEVOPS_AREA_PATHS_{ProjectName} and AZURE_DEVOPS_TEAMS_{ProjectName} for hierarchical organization. Activates for ado setup, ado validation, ado configuration, missing ado project, azure devops .env setup, per-project area paths, per-project teams.
nextjs
Guidance for Next.js using the official docs at nextjs.org/docs. Use when the user needs Next.js concepts, configuration, routing, data fetching, or API reference details.
anomaly-detector
Anomaly and outlier detection using Isolation Forest, One-Class SVM, autoencoders, and statistical methods. Activates for "anomaly detection", "outlier detection", "fraud detection", "intrusion detection", "abnormal behavior", "unusual patterns", "detect anomalies", "system monitoring". Handles supervised and unsupervised anomaly detection with SpecWeave increment integration.
cost-optimization
Optimize cloud costs through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.
distributed-tracing
Implement distributed tracing with Jaeger and Zipkin for tracking requests across microservices. Use when debugging distributed systems, tracking request flows, or analyzing service performance.
data-visualizer
Automated data visualization for EDA, model performance, and business reporting. Activates for "visualize data", "create plots", "EDA", "exploratory analysis", "confusion matrix", "ROC curve", "feature distribution", "correlation heatmap", "plot results", "dashboard". Generates publication-quality visualizations integrated with SpecWeave increments.
visual-regression
Visual regression testing expert using Playwright snapshots, Percy, Chromatic, BackstopJS, and pixel-diff analysis. Covers baseline management, responsive testing, cross-browser visual testing, component visual testing, and CI integration. Activates for visual regression, screenshot testing, visual diff, Percy, Chromatic, BackstopJS, pixel comparison, snapshot testing, visual testing, CSS regression, UI looks different, layout changed, style regression, component looks wrong, responsive breakpoints, cross-browser differences, screenshot comparison, baseline update, approve changes, Storybook visual tests, design QA, pixel perfect, UI drift, visual bugs.
e2e-playwright
Comprehensive Playwright end-to-end testing expertise covering browser automation, cross-browser testing, visual regression, API testing, mobile emulation, accessibility testing, test architecture, page object models, fixtures, parallel execution, CI/CD integration, debugging strategies, and production-grade E2E test patterns. Activates for playwright, e2e testing, end-to-end testing, browser automation, cross-browser testing, visual testing, screenshot testing, API testing, mobile testing, accessibility testing, test fixtures, page object model, POM, test architecture, parallel testing, playwright config, trace viewer, codegen, test debugging, flaky tests, CI integration, playwright best practices.
gitops-workflow
Implement GitOps workflows with ArgoCD and Flux for automated, declarative Kubernetes deployments with continuous reconciliation. Use when implementing GitOps practices, automating Kubernetes deployments, or setting up declarative infrastructure management.
tdd-workflow
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
release-strategy-advisor
Expert in analyzing and recommending release strategies for software projects. Detects existing release patterns in brownfield projects (git tags, CI/CD workflows, changelogs, version files). Suggests optimal strategies based on architecture (single-repo, multi-repo, monorepo, microservices), team size, deployment frequency, and dependencies. Creates comprehensive release-strategy.md in living docs (.specweave/docs/internal/delivery/ or projects/{id}/delivery/). Activates for release strategy, versioning strategy, multi-repo releases, monorepo versioning, semantic versioning, coordinated releases, independent releases, release planning, version alignment, brownfield release analysis, deployment strategy, CI/CD release, how to version, release best practices.
performance
Angular performance optimization, change detection strategies, and bundle optimization
k8s-security-policies
Implement Kubernetes security policies including NetworkPolicy, PodSecurityPolicy, and RBAC for production-grade security. Use when securing Kubernetes clusters, implementing network isolation, or enforcing pod security standards.
architect
System Architect and technical design expert. Creates system architecture, technical specifications, Architecture Decision Records (ADRs), component designs, API contracts, data models, and deployment architectures. Handles design patterns, scalability planning, technology stack decisions, microservices architecture, event-driven systems, CQRS, domain-driven design. Activates for architect, architecture, system design, technical design, api, backend, frontend, fullstack, ADR, architecture decision record, design patterns, microservices, API design, data model, database schema, scalability, performance architecture, technology stack, tech stack selection, distributed systems, event-driven, CQRS, DDD, domain model, component architecture, integration patterns, CAP theorem, consistency, availability, partition tolerance, how should I design, how to architect, what architecture, best architecture for, system architecture for, design the system, plan the architecture, architecture review, architecture decision, which technology, which framework, which database, monolith vs microservices, when to use microservices, service boundaries, bounded context, aggregate root, repository pattern, factory pattern, singleton pattern, observer pattern, strategy pattern, adapter pattern, facade pattern, decorator pattern, dependency injection, inversion of control, clean architecture, hexagonal architecture, onion architecture, layered architecture, vertical slice, modular monolith, event sourcing, saga pattern, outbox pattern, two phase commit, eventual consistency, strong consistency, read model, write model, command query separation, API gateway, service discovery, circuit breaker, bulkhead pattern, retry pattern, timeout pattern, rate limiting architecture, caching architecture, CDN architecture, multi-tenant architecture, SaaS architecture, B2B architecture, B2C architecture, marketplace architecture, e-commerce architecture, social media architecture, real-time architecture, WebSocket architecture, pub/sub architecture, message queue architecture, Kafka architecture, RabbitMQ architecture, Redis architecture.
model-evaluator
Comprehensive ML model evaluation with multiple metrics, cross-validation, and statistical testing. Activates for "evaluate model", "model metrics", "model performance", "compare models", "validation metrics", "test accuracy", "precision recall", "ROC AUC". Generates detailed evaluation reports with visualizations and statistical significance tests, integrated with SpecWeave increment documentation.
security
Python security best practices, OWASP, and vulnerability prevention
pci-compliance
Implement PCI DSS compliance requirements for secure handling of payment card data and payment systems. Use when securing payment processing, achieving PCI compliance, or implementing payment card security measures.
ui-testing
Multi-framework UI testing expert - Cypress, Testing Library, component tests. Use for framework comparison, Cypress-specific testing, or React Testing Library. For DEEP Playwright expertise, use e2e-playwright skill instead. Activates for Cypress, Testing Library, component tests, React testing, Vue testing, framework comparison, which testing tool, Cypress vs Playwright, render component, fireEvent, userEvent, screen queries, getByRole, getByText, getByTestId, waitFor, findBy, queryBy, test component, mount component, shallow render, integration test UI, DOM testing, accessibility testing, aria queries, form testing, user interaction testing, click test, input test.
stripe-connect
Implement Stripe Connect for marketplace and platform payments. Handles Direct Charge, Destination Charge, and Separate Charges & Transfers patterns. Covers Connect webhook setup, onboarding flows, payout management, and platform fees. Activates for Stripe Connect, marketplace payments, platform payments, Direct Charge, Destination Charge, connected account, onboarding, Express account, Standard account, Custom account, platform fee, application fee, transfer, payout, account.updated, Connect webhook, multi-party payments, seller payments, vendor payments, service provider payments, two-sided marketplace, booking platform, gig economy, rental platform.
specweave-router
DEPRECATED: This skill is obsolete as of v1.0.140+. Plugin detection is now handled by `detect-intent` command via the user-prompt-submit hook. This skill remains for backward compatibility only.
design-system-architect
Expert in building scalable design systems with Atomic Design, design tokens, theming, and component libraries. Activates for design system, design tokens, atomic design, component library, design patterns, theming, brand consistency, UI library, Storybook, design system architecture, make it sleeky, premium design, modern aesthetic, beautiful UI, redesign, UI overhaul, improve design, visual refresh, sleek look, polished design, professional appearance, design refresh, modernize UI, elegant design, clean design, minimalist design, luxury aesthetic, high-end design, corporate design, brand design, visual identity.
tdd-expert
Test-Driven Development (TDD) expertise covering red-green-refactor cycle, behavior-driven development, test-first design, refactoring with confidence, TDD best practices, TDD workflow, unit testing strategies, mock-driven development, test doubles, TDD patterns, SOLID principles through testing, emergent design, incremental development, TDD anti-patterns, and production-grade TDD practices. Activates for TDD, test-driven development, red-green-refactor, test-first, behavior-driven, BDD, refactoring, test doubles, mock-driven, test design, SOLID principles, emergent design, incremental development, TDD workflow, TDD best practices, TDD patterns, Kent Beck, Robert Martin, Uncle Bob, test-first design.
unit-testing-expert
Comprehensive unit testing expertise covering Vitest, Jest, test-driven development (TDD), mocking strategies, test coverage, snapshot testing, test architecture, testing patterns, dependency injection, test doubles (mocks, stubs, spies, fakes), async testing, error handling tests, parametric testing, test organization, code coverage analysis, mutation testing, and production-grade unit testing best practices. Activates for unit testing, vitest, jest, test-driven development, TDD, red-green-refactor, mocking, stubbing, spying, test doubles, test coverage, snapshot testing, test architecture, dependency injection, async testing, test patterns, code coverage, mutation testing, test isolation, test fixtures, AAA pattern, given-when-then, test organization, testing best practices, vi.fn, vi.mock, vi.spyOn, describe, it, expect, beforeEach, afterEach.
k8s-manifest-generator
Create production-ready Kubernetes manifests for Deployments, Services, ConfigMaps, and Secrets following best practices and security standards. Use when generating Kubernetes YAML manifests, creating K8s resources, or implementing production-grade Kubernetes configurations.
helm-chart-scaffolding
Design, organize, and manage Helm charts for templating and packaging Kubernetes applications with reusable configurations. Use when creating Helm charts, packaging Kubernetes applications, or implementing templated deployments.
jira-mapper
Expert in mapping SpecWeave increments to JIRA epics/stories/subtasks. Content flows SpecWeave→JIRA, status flows JIRA→SpecWeave. Handles export (increment → JIRA), import (JIRA → increment). Activates for JIRA sync, issue creation, import from JIRA.
prometheus-configuration
Set up Prometheus for comprehensive metric collection, storage, and monitoring of infrastructure and applications. Use when implementing metrics collection, setting up monitoring infrastructure, or configuring alerting systems.
rc-manager
Manages Release Candidate (RC) workflows including pre-release tagging, RC lifecycle (alpha/beta/rc), testing validation, RC promotion to production, rollback procedures, and channel-based releases. Handles RC versioning (v1.0.0-rc.1, v1.0.0-beta.1), tracks RC testing status, coordinates RC across multiple repositories, manages canary/blue-green deployments. Activates for release candidate, RC, pre-release, beta release, alpha release, canary release, rc workflow, promote rc, rc testing, staging release, pre-production.
paypal-integration
Integrate PayPal payment processing with support for express checkout, subscriptions, and refund management. Use when implementing PayPal payments, processing online transactions, or building e-commerce checkout flows.
docs-writer
Use this skill when asked to write documentation (`/docs` directory) for Gemini CLI.
image-generation
自动为文章生成配图，支持AI生成图片、公共领域图片、免费图库图片，并上传到ImgBB图床生成Markdown链接。当用户提到"配图"、"插图"、"图片"、"生成图片"、"文章配图"时使用此技能。
tech-lead
Technical Lead that implements code ONE FILE AT A TIME to prevent crashes. Handles code review, best practices, mentorship, implementation planning. **CRITICAL CHUNKING RULE - Large implementations (auth system = auth.ts + tests + middleware) done incrementally.** Activates for tech lead, code review, best practices, refactoring, technical debt, code quality, design patterns, SOLID principles, clean code, code standards, implementation plan, technical guidance, mentorship, code optimization, complexity analysis, technical planning, estimation, implementation strategy, code architecture.
nlp-pipeline-builder
Natural language processing ML pipelines for text classification, NER, sentiment analysis, text generation, and embeddings. Activates for "nlp", "text classification", "sentiment analysis", "named entity recognition", "BERT", "transformers", "text preprocessing", "tokenization", "word embeddings". Builds NLP pipelines with transformers, integrated with SpecWeave increments.
marketplace-publishing
Expert Claude Code marketplace publishing covering npm publishing, GitHub releases, semantic versioning, plugin packaging, README documentation, CHANGELOG management, marketplace submission, and plugin distribution. Activates for publish plugin, npm publish, marketplace, release plugin, semantic versioning, semver, plugin distribution, publish to npm, github release.
browser-automation
Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understanding selectors, waiting strategies, and anti-detection patterns. This skill covers Playwright (recommended) and Puppeteer, with patterns for testing, scraping, and agentic browser control. Key insight: Playwright won the framework war. Unless you need Puppeteer's stealth ecosystem or are Chrome-only, Playwright is the better choice in 202
stakeholder-docs
Generate executive-friendly documentation views from technical living docs. Creates business summaries, progress dashboards, feature status reports, and non-technical overviews. Activates for stakeholder, executive summary, business view, non-technical, management report, progress dashboard, business impact, ROI, feature status, quarterly report, executive overview, business metrics, KPI dashboard, status report, project status, feature progress, delivery status, release summary, business documentation, non-technical summary, leadership update, board report, investor update, customer facing docs, sales documentation.
stripe-integration
Implement Stripe payment processing for robust, PCI-compliant payment flows including checkout, subscriptions, and webhooks. Use when integrating Stripe payments, building subscription systems, or implementing secure checkout flows.
mobile-architect
Elite mobile architect for React Native and Expo. Expert in New Architecture (Fabric, Turbo Modules, JSI), modern React patterns (Activity, useEffectEvent, concurrent features), state management (Zustand, TanStack Query, Jotai, Legend State), navigation (Expo Router native tabs, React Navigation), performance (Hermes, FlashList, expo-image, Intersection Observer), platform-specific UI (iOS design language, Android edge-to-edge), and offline-first patterns. IMPORTANT - Always fetch latest React Native and Expo docs via Context7 for version-specific details. Activates for mobile architecture, React Native design, app structure, state management, navigation patterns, New Architecture, Turbo Modules, Fabric, JSI, Expo SDK, mobile performance, offline-first, Hermes, React concurrent, Activity component, native tabs, mobile app, iOS app, Android app, build mobile app, create app, phone app, tablet app, mobile UI, app design, push notifications, deep linking, app store, play store, mobile authentication, biometrics, Face ID, Touch ID, mobile storage, AsyncStorage, MMKV, app permissions, camera access, location tracking, create mobile app, make an app, build an app, develop app, app for iPhone, app for Android, native app, cross-platform app, hybrid app, app development, smartphone app, make iOS app, make Android app, I want to build an app, let's create an app, need a mobile app, app idea, startup app, MVP app, app prototype, mobile MVP, app screens, app navigation, bottom tabs, tab bar, drawer navigation, stack navigation, app splash screen, app icon, app onboarding, user onboarding mobile, login screen, signup screen mobile, app forms, mobile forms, keyboard handling, gesture handling, swipe gestures, pull to refresh, infinite scroll mobile, app animations, Reanimated, Lottie animations, app theming, app dark mode, app notifications, local notifications, remote notifications, FCM, APNs, app analytics, mobile analytics, crash reporting, Sentry mobile, app testing, Detox, Maestro, app deployment, TestFlight, Google Play Console, app review, app rejection, app store optimization, ASO.
kafka-devops
Kafka DevOps and SRE specialist. Expert in infrastructure deployment, CI/CD, monitoring, incident response, capacity planning, and operational best practices for Apache Kafka.
kafka-architect
Kafka architecture and design specialist. Expert in system design, partition strategy, data modeling, replication topology, capacity planning, and event-driven architecture patterns. Activates for Kafka, Apache Kafka, Kafka architecture, topic design, partition strategy, consumer groups, producer config, Kafka Connect, Kafka Streams, event streaming, message broker, pub/sub, event-driven architecture, EDA, event sourcing, CQRS with Kafka, Kafka cluster, Zookeeper, KRaft, replication factor, ISR, broker config, retention policy, compaction, exactly-once semantics, at-least-once, offset management, lag monitoring, Kafka security, SASL, SSL Kafka.
performance-engineer
Performance optimization specialist for improving application speed and efficiency. Use when investigating performance issues or optimizing code.
ado-sync-judge
LLM Judge for verifying Azure DevOps synchronization correctness, conflict resolution, and lifecycle management. Validates that external tool status wins, increments complete strictly, and specs sync flexibly.
type-design-analyzer
Type Design Analyzer - Evaluates type quality across encapsulation, invariant expression, usefulness, and enforcement. Based on Anthropic's official type-design-analyzer. Activates for type review, type design, type quality, invariants, encapsulation review, type safety, TypeScript types, type analysis, improve types, type architecture.
kubernetes-architect
Expert Kubernetes architect that generates manifests ONE SERVICE AT A TIME (frontend → backend → database → cache) to prevent crashes. Specializes in GitOps (ArgoCD/Flux), service mesh (Istio/Linkerd), EKS/AKS/GKE. **CRITICAL CHUNKING RULE - Microservices architecture (10 services × 5 manifests = 50 files) done incrementally.** Activates for K8s, Kubernetes, pods, deployments, services, ingress, configmaps, secrets, helm charts, kustomize, argocd, flux, gitops, EKS, AKS, GKE, container orchestration, namespace, service mesh, istio, linkerd, horizontal pod autoscaler, HPA, persistent volumes, PV, PVC, statefulsets, daemonsets, jobs, cronjobs, RBAC, network policies, kubernetes troubleshooting, pod not starting, crashloopbackoff.
database-optimizer
Use when investigating slow queries, analyzing execution plans, or optimizing database performance. Invoke for index design, query rewrites, configuration tuning, partitioning strategies, lock contention resolution.
devops
Deploy and manage cloud infrastructure on Cloudflare (Workers, R2, D1, KV, Pages, Durable Objects, Browser Rendering), Docker containers, and Google Cloud Platform (Compute Engine, GKE, Cloud Run, App Engine, Cloud Storage). Use when deploying serverless functions to the edge, configuring edge computing solutions, managing Docker containers and images, setting up CI/CD pipelines, optimizing cloud infrastructure costs, implementing global caching strategies, working with cloud databases, or building cloud-native applications.
sre
Site Reliability Engineering expert for incident response, troubleshooting, and mitigation. Handles production incidents across UI, backend, database, infrastructure, and security layers. Performs root cause analysis, creates mitigation plans, writes post-mortems, and maintains runbooks. Activates for incident, outage, slow, down, performance, latency, error rate, 5xx, 500, 502, 503, 504, crash, memory leak, CPU spike, disk full, database deadlock, SRE, on-call, SEV1, SEV2, SEV3, production issue, debugging, root cause analysis, RCA, post-mortem, runbook, health check, service degradation, timeout, connection refused, high load, monitor, alert, p95, p99, response time, throughput, Prometheus, Grafana, Datadog, New Relic, PagerDuty, observability, logging, tracing, metrics.
frontend-architect
Frontend architecture expert. Use when planning component architecture, state management strategies, performance optimization, or technology selection decisions.
silent-failure-hunter
Silent Failure Hunter - Identifies hidden error handling issues, inadequate catch blocks, and inappropriate fallback behavior. Based on Anthropic's official silent-failure-hunter. Activates for error handling review, silent failures, catch block review, error swallowing, hidden errors, exception handling, try catch review, error logging, failure detection, find silent errors.
confluent-architect
Confluent Cloud architecture specialist. Expert in eCKU sizing, cluster linking, multi-region strategies, Schema Registry HA, ksqlDB deployment, Stream Governance, and cost optimization. Activates for confluent cloud architecture, ecku sizing, cluster linking, multi-region kafka, schema registry ha, stream governance, cost optimization, Confluent Cloud, Confluent Platform, Schema Registry, Avro schema, Protobuf schema, JSON Schema, schema evolution, compatibility mode, ksqlDB, stream processing, Kafka REST Proxy, Confluent Control Center, Confluent CLI, managed Kafka, serverless Kafka, dedicated cluster, basic cluster, standard cluster, private link, VPC peering, audit logs, RBAC Kafka.
payment-integration
Implement payment integrations with SePay (Vietnamese payment gateway with VietQR, bank transfers, cards) and Polar (global SaaS monetization platform with subscriptions, usage-based billing, automated benefits). Use when integrating payment processing, implementing checkout flows, managing subscriptions, handling webhooks, processing bank transfers, generating QR codes, automating benefit delivery, or building billing systems. Supports authentication (API keys, OAuth2), product management, customer portals, tax compliance (Polar as MoR), and comprehensive SDK integrations (Node.js, PHP, Python, Go, Laravel, Next.js).
release-manager
Expert release management orchestrator for single-repo, multi-repo, and monorepo architectures. Coordinates all aspects of software releases including strategy planning, version alignment, RC workflows, multi-repo coordination, and deployment validation. Integrates brownfield detection, living docs updates, and CI/CD automation. Activates for release, version, versioning, semver, semantic versioning, changelog, release notes, npm publish, package publish, tag, git tag, release candidate, RC, production release, deploy to production, rollback, hotfix, patch release, major release, minor release, monorepo release, multi-repo release, release branch, release pipeline, release automation, changesets, conventional commits, bump version, publish package, release checklist, go-live, ship it, release cycle.
observability-engineer
Production observability architect - metrics, logs, traces, SLOs. Opinionated on OpenTelemetry-first, Prometheus+Grafana stack, alert fatigue prevention. Activates for monitoring, observability, SLI/SLO, alerting, Prometheus, Grafana, tracing, logging, Datadog, New Relic, OpenTelemetry, OTEL, metrics collection, log aggregation, distributed tracing, Jaeger, Zipkin, Loki, ELK stack, Elasticsearch, Kibana, Fluentd, structured logging, alert rules, dashboards, Grafana dashboards, PromQL, LogQL, cardinality, metric labels, span context, trace ID, correlation ID, service mesh observability, APM, application performance monitoring, error tracking, Sentry, uptime monitoring, synthetic monitoring, real user monitoring, RUM.
qa-engineer
Assist QA Engineers with test planning, test case generation from acceptance criteria, coverage analysis, and regression test identification. Use when creating test plans, generating test cases, analyzing test coverage, or identifying regression risks. Triggers on keywords like "test plan", "test cases", "test spec", "test coverage", "regression", "QA", "testing strategy", "edge cases".
comment-analyzer
Comment Analyzer - Reviews code comments for accuracy, completeness, and maintainability. Guards against comment rot and misleading documentation. Based on Anthropic's official comment-analyzer. Activates for comment review, documentation accuracy, outdated comments, misleading comments, docstring review, JSDoc review, comment quality, documentation audit, fix comments, update comments.
data-scientist
Expert in statistical analysis, predictive modeling, machine learning, and data storytelling to drive business insights.
mlops-engineer
Expert in Machine Learning Operations bridging data science and DevOps. Use when building ML pipelines, model versioning, feature stores, or production ML serving. Triggers include "MLOps", "ML pipeline", "model deployment", "feature store", "model versioning", "ML monitoring", "Kubeflow", "MLflow".
jira-sync-judge
LLM Judge for verifying JIRA synchronization correctness, conflict resolution, and lifecycle management. Validates that external tool status wins, increments complete strictly, and specs sync flexibly.
ado-multi-project-mapper
Expert in mapping SpecWeave specs to multiple Azure DevOps projects with intelligent project detection and cross-project coordination. Handles project-per-team, area-path-based, and team-based strategies. Manages bidirectional sync across multiple projects.
pr-test-analyzer
PR Test Coverage Analyzer - Evaluates test completeness focusing on behavioral verification, not metrics chasing. Based on Anthropic's official pr-test-analyzer. Activates for PR test coverage, test coverage review, missing tests, test gaps, edge case coverage, regression prevention, test quality, are tests complete, check test coverage, review tests, test analysis.
jira-manager
Jira integration specialist for SpecWeave increments. Handles epic creation, bidirectional sync, task completion status updates, and cross-system consistency between SpecWeave and Jira. Activates for JIRA, Jira sync, Jira integration, create Jira issue, Jira epic, Jira story, Jira task, Jira subtask, sync to Jira, Jira API, Jira webhook, Jira workflow, Jira board, Jira sprint, Jira backlog, Jira project, JQL, Jira query, Jira automation, Jira transition, Jira status, Jira fields, custom fields Jira, Jira REST API, Atlassian, Jira Cloud, Jira Server, Jira Data Center.
network-engineer
Use when user needs network architecture design, security implementation, performance optimization, and troubleshooting for cloud and hybrid environments. Builds reliable, secure networks with zero-trust principles.
ml-engineer
Expert in building scalable ML systems, from data pipelines and model training to production deployment and monitoring.
code-explorer
Code Explorer - Deep codebase analysis by tracing feature implementation across architecture layers. Based on Anthropic's official code-explorer. Activates for how does this work, trace execution, find implementation, understand codebase, where is this defined, follow the code, code flow, execution path, find entry point.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
user-story-updater
Updates GitHub issues for user stories with proper ACs and tasks. Activates for update user story issue, fix GitHub issue format, add checkable ACs, refresh user story issue, sync user story to GitHub.
jira-multi-project-mapper
Expert in mapping SpecWeave specs to multiple JIRA projects with intelligent project detection and cross-project coordination. Handles project-per-team, component-based, and epic-based strategies. Manages bidirectional sync across multiple projects.
github-task-splitter
Expert agent for splitting SpecWeave tasks across multiple GitHub repositories based on architecture patterns. Analyzes task dependencies across services and creates tracking issues in multiple repositories for multi-repo architectures.