Loading...
Loading...
Found 10 Skills
Route broad documentation-governance requests to existing ECC skills and run an opt-in, read-only audit of mapped documentation roles, links, ADR indexes, and evidence references. Use when a user asks for documentation governance, project-knowledge organization, documentation integrity, or a deterministic docs audit without naming a narrower skill.
Audit documentation authority, reconcile conflicting specifications, and maintain canonical Single Source of Truth records across repository documentation.
Govern stable domain context with a narrowly scoped CONTEXT.md when needed, and route hard-to-reverse decisions to ECC's existing architecture-decision-records skill. Use when domain terms require repeated explanation, one term has multiple meanings, unclear language causes module-boundary mistakes, or domain semantics must remain separate from architecture decisions.
Governance-focused README with fixed structure and output contract. Use for asset governance, audit, or standardized first-impression docs. For process-driven creation (templates by project type) use crafting-effective-readmes.
Define team interfaces, contracts, and communication boundaries
Ask which skill or flow fits your situation. A router over the docs/Agent-Note maintenance flow, the documentation governance run, the prose-and-docs tool layer, and the standalone git and game skills in this pack.
Use when writing, restructuring, auditing, or reviewing Cherry Studio repository documentation, READMEs, JSDoc, comments, Agent instructions, or paired English/Chinese docs, including source-linked documentation impact checks.
Keep a repository's README for the person deciding whether and how to use it, its AGENTS.md (or a CLAUDE.md read through it) for the agent working inside it, and the manifests hosts read first (package.json, plugin and marketplace files, agents/openai.yaml) on the repository's one name: audit them with the bundled script, then move each line to the file whose reader needs it and fix each disagreeing manifest. Use when writing, rewriting or reviewing a README or an AGENTS.md, when an agent-only command shows up in a README or marketing copy in an agent guide, when deciding which file a section belongs in, or after a rename. Not for contracts, ledgers, changelogs or release notes.
Keep a repository's docs the product authority, with one dated owner-decision register, lasting docs in `docs/` grouped by kind, and scratch in an ignored `.scratch/`. Use when you record or rely on an owner decision, add, move, or remove a doc, write a temporary note, plan, or spec, edit agent instructions, or set this method up in a new repository.
Perform documentation and AGENTS.md governance for long-running, continuously iterated projects (reduce routing overhead by task, synchronize a single source through @AGENTS.md, eliminate duplicated copying between topic-specific specifications and project-local Skills, and clean up outdated descriptions and process snapshots); testing governance (separate fast and heavyweight tests to prevent AI from repeatedly running expensive tests in vain, identify orphan tests and slow unit tests, remove ineffective tests, and ensure side-effect-free isolation); parallel Git Worktree hygiene audits; use a board to clarify where each branch is, what it changed, and how it should be handled; and turn hard project rules into deterministic static checks inside the repository. Use this when users request a health check or cleanup of project documentation and AGENTS.md, fast/heavy test stratification, removal of redundant tests or idle Worktrees, visibility into repository branch and working-tree status, or conversion of specifications into automated checks. Do not use it for solution design for a single feature (use oil-plan), Code Review of a single change (use oil-code-review), or diagnosis and damage containment for a single defect (use oil-bug-fix).