Skill Claude CodeCodex
Discovers and injects project-specific coding guidelines from .cstl/spec/ before implementation begins. Reads spec indexes, pre-development checklists, and shared thinking guides for the target package. Use when starting a new coding task, before writing any code, switching to a different package, or needing to…
Skill Claude CodeCodex
Guides collaborative requirements discovery before implementation. Two-phase Cursor planning: Discovery Before Questions, PRD draft, then PRD Grill (document pass + micro-grill for blocking business questions). Use when requirements are unclear, multiple valid approaches exist, or the user describes a new feature or…
Skill Claude CodeCodex
Deep bug analysis to break the fix-forget-repeat cycle. Analyzes root cause category, why fixes failed, prevention mechanisms, and captures knowledge into specs. Use after fixing a bug to prevent the same class of bugs.
Skill Claude CodeCodex
Comprehensive quality verification: spec compliance, lint, type-check, tests, cross-layer data flow, code reuse, and consistency checks. Use when code is written and needs quality verification, before committing changes, or to catch context drift during long sessions.
Skill Claude CodeCodex
Resume work on the current task. Loads the workflow Phase Index, figures out which phase/step to pick up at, then pulls the step-level detail via getcontext.py --mode phase. Use when coming back to an in-progress task and you need to know what to do next.
Skill Claude CodeCodex
Wrap up the current session: verify quality gate passed, remind user to commit, archive completed tasks, and record session progress to the developer journal. Use when done coding and ready to end the session.
Skill Claude CodeCodex
Understand and customize the local Trellis architecture inside a user project. Use when modifying .cstl plus platform hooks, settings, agents, skills, commands, prompts, or workflows generated by cstl init.
Skill Claude CodeCodex
Clarifies small underspecified Trellis requests with one high-value question at a time before direct execution. Use when a request is likely small, missing details would materially change the result, and creating a Trellis task would be premature.
Skill Claude CodeCodex
Initializes an AI development session by reading workflow guides, developer identity, git status, active tasks, and project guidelines from .cstl/. Classifies incoming tasks and routes to brainstorm, direct edit, or task workflow. Use when beginning a new coding session, resuming work, starting a new task, or…
Skill Claude CodeCodex
Captures executable contracts and coding conventions into .cstl/spec/ documents. Use when learning something valuable from debugging, implementing, or discussion that should be preserved for future sessions.
Skill Claude CodeCodex
Systematic first principles thinking for any problem domain. Use when the user says "analyze from first principles", "第一性原理", "从根本分析", "从零开始思考", "think from scratch", "question this design", "is this the right approach", "challenge assumptions", "挑战假设", "为什么要这样做", "有没有更好的方案", "why are we doing it this way", or needs…
Skill Claude CodeCodex
Python design patterns for CLI scripts and utilities — type-first development, deep modules, complexity management, and red flags. Use when reading, writing, reviewing, or refactoring Python files, especially in .cstl/scripts/ or any CLI/scripting context. Also activate when planning module structure, deciding where…
Skill Claude CodeCodex
CLI-first web research and source retrieval through the local smart-search command. Use when Codex needs current web search, source-backed fact checking, URL fetching, site mapping, official/API/documentation search, or reproducible search evidence via Skill + CLI instead of MCP tools.
Skill Claude CodeCodex
Design, build, verify, and publish production-grade TypeScript SDKs as npm packages inside a pnpm monorepo. Covers workspace layout, public API and module boundaries, plugin extension points, branded types and library-tuned tsconfig, tsdown bundling (vs tsup/tsc-only/unbuild), package.json exports with dual ESM+CJS…
MCP server Claude CodeCodexCursor +2
AI-driven semantic code search MCP server (Node.js). Runs locally from the fast-context-mcp npm package.
MCP server Claude CodeCodexCursor +2
Local-first code intelligence for AI agents (MCP). Self-contained — bundles its own runtime. Runs locally from the @colbymchenry/codegraph npm package.
MCP server Claude CodeCodexCursor +2
Lets the agent work with GitHub: search code, read and create issues and pull requests, and manage repositories through the GitHub API. Runs locally from the @modelcontextprotocol/server-github npm package.
MCP server Claude CodeCodexCursor +2
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
Instructions file CodexOpenCode
AGENTS.md instructions for blxzer77/cursor-trellis, covering cursor-trellis (cstl) instructions, command surface (what is user-invocable vs internal), skill authoring (mandatory), invocation map (short) and internal skill reachability (on-demand).
Skill Claude CodeCodex
Condense the current session into a portable handoff document so a new agent / harness / directory can continue the work. User-invoked when the work needs to 'travel' (switch harness, switch directory or repo, hand to a colleague, or fork a side branch); writes to the OS temp directory and reports the full path.
Skill Claude CodeCodex
Create or improve Trellis-compatible agent skills. Use when the user asks to author a project-local skill, shared .agents skill, platform-specific skill, or upstream Trellis bundled skill.
Skill Claude CodeCodex
Bootstrap project-specific Trellis coding specs with a platform-neutral single-agent workflow. Use when creating or refreshing .cstl/spec guidelines, analyzing a codebase with GitNexus, ABCoder, or source inspection, decomposing package/layer spec work, and writing real codebase-backed spec docs without placeholder…
Command
Resume work only when this live session already has a selectedtask. If no task is selected, show the Task Dashboard and ask for an explicit route.
Command
Wrap up the current session: archive the selected task (and any other completed-but-unarchived tasks the user wants to clean up) and record the session journal. Code commits are NOT done here — those happen in workflow Phase 3.4 before you invoke this command.