skill-distiller
Fetches top-rated skills from skills.sh, analyzes them, and synthesizes one token-efficient skill combining the best elements. Use when the user asks to…
Manages project documentation: CLAUDE.md, AGENTS.md, README.md, CONTRIBUTING.md, DOCS.md. Use when asked to update, create, or init these context files. Not for general markdown editing.
$ npx -y skills add iliaal/whetstone --skill ia-md-docs --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/ia-md-docsContext preview
The summary Claude sees to decide when to auto-load this skill.
Manages project documentation: CLAUDE.md, AGENTS.md, README.md, CONTRIBUTING.md, DOCS.md. Use when asked to update, create, or init these context files. Not for general markdown editing.
name: ia-md-docs class: workflow description: >- Manages project documentation: CLAUDE.md, AGENTS.md, README.md, CONTRIBUTING.md, DOCS.md. Use when asked to update, create, or init these context files. Not for general markdown editing. paths: "**/*.md"
Manage project documentation by verifying against actual codebase state -- analyze structure, files, and patterns before writing; never generate blind.
AGENTS.md is the universal context file (works with Claude Code, Codex, Kilocode). During Initialize Context or Update Context Files workflows only: if CLAUDE.md exists without AGENTS.md, confirm with the user first (Ask via AskUserQuestion (Claude Code; load with ToolSearch `select:AskUserQuestion` if not loaded) or request_user_input (Codex); fall back to numbered options in chat), then `mv CLAUDE.md AGENTS.md && ln -sf AGENTS.md CLAUDE.md`. Never migrate as a side effect of another task.
When this skill references "context files", it means AGENTS.md (and CLAUDE.md if present as symlink).
Multi-package repo? Read [monorepo.md](./references/monorepo.md) before any `update-*`/`init-*` sweep (discovery commands, per-file scoping, context-loading rules). Enumerate targets; if the sweep would create or rewrite more than 3 files, stop: list planned targets and confirm before writing (same ask mechanism as in Portability above).
Treat these as user-request modifiers: apply when the request contains the flag or equivalent phrasing. All workflows support:
Before overwriting: `cp FILE FILE.backup`; never auto-delete backups.
After every operation, display a summary:
[OK] Updated AGENTS.md - Fixed build command - Added new directory to structure [OK] Updated README.md - Added installation section - Updated badges [--] CONTRIBUTING.md not found (skipped)
Read the relevant reference before implementing or reviewing the matching behavior:
Existing specialized references, when the corresponding topic applies:
A Claude Code plugin that makes AI coding agents follow engineering discipline. Plan before coding. Verify before claiming done. Find root cause before patching. Review before merge. Skills activate based on file type and task signals, not manual toggling.
Repo: iliaal/whetstone
Fetches top-rated skills from skills.sh, analyzes them, and synthesizes one token-efficient skill combining the best elements. Use when the user asks to…
Design agent-native applications where agents replace UI users as the primary actor. Use when designing MCP tools, agent-loop architectures, system prompt…
Pre-implementation exploration: deep interview, approach comparison, design doc. Use when exploring a vague feature idea, clarifying ambiguous requirements, or…
C patterns for systems code, libraries, and native extensions: module layout, function decomposition, status-enum errors, memory safety, undefined behavior,…
Structured code reviews with severity-ranked findings and deep multi-agent mode. Use when performing a code review, auditing code quality, or critiquing PRs,…
Document solved problems for team reuse. Provides process knowledge for /ia-compound. Use when documenting a resolved issue, writing up lessons learned,…