codethread
- 11 skills
- 0 followers
- 10 hours ago last updated
- ▌ How · codethread bundleDecompose a feature PRD into an ordered task list. Mechanical phase — pure agent. Triggers on: "dev/how", "decompose", "break this down", "create tasks"
- ▌ What · codethread bundleDefine what to build through structured research and experimentation. Produces or revises `.dev/<feature>/prd.md`. Triggers on: "what should we build", "let's plan", "new feature", "I want to build", "dev/what"
- ▌ Specs · codethread bundleWrite or update persistent domain specs from existing code. Updates `specs/<domain>.md` and `specs/README.md`. Triggers on: "dev/specs", "write spec", "update specs", "spec this"
- ▌ Systems · codethread bundleSurvey a codebase and produce a reverse-spec backlog in `specs/systems.yml`. Use when you want a queue of stable system domains to reverse-engineer over time. Triggers on: "dev/systems", "what systems should we spec", "plan reverse specs"
- ▌ Introspection · codethread bundleTest and verify Claude Code behaviour — hooks, instructions, CLAUDE.md rules, tool usage patterns — using a headless subprocess harness. Use when building integration tests, verifying hook execution, or validating Claude Code configuration end-to-end.
- ▌ Claude Code Knowledge · codethread bundleMandatory when configuring any Claude Code specifics - hooks, skills, plugins, MCP servers, slash commands, settings, agents, or any Claude Code feature. Provides opinionated best practices
- ▌
- ▌
- ▌ Lang React · codethreadBuild React SPAs where components are declarative UI consuming external state (Zustand/XState/TanStack Query). Logic lives in stores, not components.
- ▌ Lang Typescript · codethread bundleWrite clean, type-safe TypeScript code using modern patterns, strict configuration, and best practices. Use when writing TypeScript code, configuring projects, or solving type-related challenges.
- ▌ Writing Documentation · codethread bundleWrite clear, effective technical documentation following industry-proven patterns from exemplary projects and authoritative style guides, with built-in countermeasures for common LLM documentation issues