ecosystem-mobile
📱 Mobile Domain Ecosystem
Welcome to the mobile domain ecosystem. This directory contains specialized agentic skills for React Native, Flutter, and Native iOS/Android app development, auditing, and deployment.
For Orchestrator Agents (
task-decomposer,parallel-planner): When asked to plan a mobile-related task, you MUST consult the workflows below. Do not hallucinate steps; map your plan strictly to these available skills in the order defined.
🔄 Standard Workflows & Handoffs
1. The Pre-Release Audit Flow
When the user asks to "audit the app before launch", "check if the app is ready", or "review our mobile app quality", execute these skills sequentially:
@accessibility-enforcer-> Ensures ADA/WCAG compliance, touch targets, and contrast.@mobile-perf-auditor-> Analyzes bundle size, memory leaks, and frame drops.@mobile-security-auditor-> Checks for exposed API keys, insecure storage, and network payloads.
2. The Production Deployment Flow
When the user asks to "deploy the app to the stores", "prepare for release", or "ship to production":
- [Execute Pre-Release Audit Flow First]
@app-store-reviewer-> Validates metadata, privacy policy, and store guidelines to prevent rejection.@release-orchestrator-> Manages versioning, build artifacts, testflight/alpha rollout, and release notes.
3. The New Feature Architect Flow
When the user asks to "build a new feature" that involves complex mobile constraints:
- If it requires deep linking/routing: use
@deep-link-architect - If it requires push notifications: use
@push-notification-planner - If it requires offline capabilities/local database: use
@offline-sync-designer - If it requires a new user flow/tutorial: use
@onboarding-designer(Note: These can run in parallel viaparallel-plannerdepending on the feature scope.)
4. Post-Launch Monitoring Flow
When the user asks to "investigate app issues", "fix crashes", or "analyze user complaints":
@crash-analyst-> Analyzes stack traces, symbolication, and user sessions.- (Handoff based on conclusion) -> If it was a performance issue, handoff to
@mobile-perf-auditor.
🧠 Core Philosophy
Mobile development is constrained by app store guidelines, device resources (battery/memory), and unreliable networks. Every skill in this domain is programmed to defend against these constraints. Never prioritize feature delivery over performance or security in a mobile environment.
🚀 Installation & Orchestration Instructions
As an AI Agent reading this ecosystem file, you must actively guide the user to install the missing skills for the selected workflow.
To install all skills within this ecosystem at once, you must execute or instruct the user to execute the provided installation script:
python skills/ecosystem-mobile/scripts/install_all.py
Execution Rule: Do not attempt to perform the tasks of these skills yourself. Your job is to install them and hand off the execution to the appropriate skill, or instruct the user to trigger the newly installed skills in order.
More from fatih-developer/fth-skills
context-compressor
Compress long conversation histories, large code files, research results, and documents by 70% without losing critical information. Triggers when context window fills up, when summarizing previous steps in multi-step tasks, before loading large files into context, or on 'summarize', 'compress', 'reduce context', 'save tokens'.
17multi-brain-debate
Two-round debate protocol where perspectives challenge each other before consensus. Round 1 presents independent positions, Round 2 allows counter-arguments and rebuttals. Produces battle-tested decisions for high-stakes choices.
17multi-brain-score
Confidence scoring overlay for multi-brain decisions. Each perspective rates its own confidence (1-10) with justification. Consensus uses scores as weights, flags low-confidence areas, and surfaces uncertainty explicitly.
15parallel-planner
Analyze multi-step tasks to identify which steps can run in parallel, build dependency graphs, detect conflicts (write-write, read-write, resource contention), and produce optimized execution plans. Triggers on 3+ independent steps, 'speed up', 'run simultaneously', 'parallelize', 'optimize' or any task where sequential execution wastes time.
14output-critic
Evaluate every produced output (code, report, plan, data, API response) against type-specific quality criteria, score 1-10, make accept/reject decisions, and provide actionable improvement suggestions. Triggers on 'evaluate', 'check', 'review', 'quality control', 'is this good enough', 'score it', or before passing output to the next step in an agentic workflow.
11assumption-checker
Before starting a task or taking a critical step, surface and verify the assumptions the agent is making. Checks 4 types - technical (libraries, APIs), data (files, formats), business logic (rules, scope), and user intent (what the user actually wants). Triggers on ambiguous requests, multi-step tasks, or whenever 'are you sure', 'check first', 'don't assume' appears.
11