tech-planner
Technical Planning
Create technical overviews and Architecture Decision Records (ADRs) that document HOW a feature is built — architecture, integration, and decisions.
Workflow
- Read the spec — Load the spec from the argument path. If no path is provided, ask the user for the spec location.
- Analyze architecture — Evaluate the analysis questions below against the spec.
- Create technical overview — Write
specs/feature-name/tech.mdusingassets/tech.md. - Determine if ADR(s) are needed — Apply the decision criteria below. Skip if no ADR is warranted.
- Create ADR(s) — Write
docs/adr/NNN-title.mdusingassets/adr-template.md. Scan existing ADRs for the highest number, increment by one, and pad to 3 digits.
Architectural Analysis
Evaluate these questions for every technical plan:
- What existing systems does this touch?
- Where does this feature start and end?
- How does it connect to existing components?
- How does data flow through the system?
- What are we gaining and giving up?
When to Create an ADR
Create an ADR when the decision:
- Chooses between competing technologies or frameworks
- Sets a project-wide pattern or convention
- Selects an authentication or authorization approach
- Introduces a trade-off with long-term implications
- Is difficult or expensive to reverse
When NOT to Create an ADR
Skip the ADR when the decision:
- Affects only a single feature (document in the feature spec instead)
- Covers implementation details within one component
- Describes a temporary workaround or experiment
See references/adr-guide.md for extended ADR guidance, status lifecycle, and content guidelines.
Constraints
- Never include specific file paths, implementation order, code snippets, line-by-line details, time estimates, or timeline references in technical overviews or ADRs.
- Keep technical overviews focused on architecture boundaries, data flow, and integration — not implementation steps.
Assets
assets/tech-template.md— Technical overview templateassets/adr-template.md— ADR templatereferences/adr-guide.md— Extended ADR guidance
More from jkappers/agent-skills
dotnet-dockerfile
Create optimized, secure multi-stage Dockerfiles for .NET Core and ASP.NET Core applications. Use when (1) creating a new Dockerfile for a .NET project, (2) containerizing a .NET application, (3) optimizing an existing .NET Dockerfile, (4) setting up Docker for .NET 6/7/8+ apps, or (5) user mentions .NET and Docker/container together.
38enhance-prompt
Analyzes and improves LLM prompts and agent instructions for token efficiency, determinism, and clarity. Use when (1) writing a new system prompt, skill, or CLAUDE.md file, (2) reviewing or improving an existing prompt for clarity and efficiency, (3) diagnosing why a prompt produces inconsistent or unexpected results, (4) converting natural language instructions into imperative LLM directives, or (5) evaluating prompt anti-patterns and suggesting fixes. Applies to all LLM platforms (Claude, GPT, Gemini, Llama).
32conventional-commit
Conventional Commits v1.0.0 standards for git messages. Use when (1) creating git commits, (2) writing or drafting commit messages, (3) reviewing commit message format, (4) explaining commit conventions, or (5) validating commit message compliance.
24react-dockerfile
Create optimized, secure multi-stage Dockerfiles for React applications (Vite, CRA, Next.js static). Use when (1) creating a new Dockerfile for a React project, (2) containerizing a React/Vite application, (3) optimizing an existing React Dockerfile, (4) setting up Docker for React with Nginx, or (5) user mentions React and Docker/container together.
23gap-analysis
Product and feature evaluation. Use when (1) Evaluating product/feature feasibility and market viability (2) Assessing product-market fit before investment (3) Comparing opportunities for roadmap prioritization (4) Competitive analysis to identify gaps (5) User asks "should we build X?" or "is this viable?" (6) Risk assessment for product decisions
16skill-creator
Guide for creating effective agent skills following the Agent Skills open standard. This skill should be used when users want to create a new skill (or update an existing skill) that extends agent capabilities with specialized knowledge, workflows, or tool integrations.
16