agent-docs-audit
Auditing and maintaining AGENTS.md documentation. Triggers include "audit AGENTS.md", "check agent docs", "verify documentation accuracy", "maintain agent instructions", or "check for drift".
Discover Documentation skills, compare source repositories and read the instructions for each workflow.
Auditing and maintaining AGENTS.md documentation. Triggers include "audit AGENTS.md", "check agent docs", "verify documentation accuracy", "maintain agent instructions", or "check for drift".
Interactive clarification with smart HIL question flows. Triggers include "ask me questions", "help me think through", "what should we consider", session start ("what are we working on"), scope definition ("wha...
External AI collaboration with output contracts. Triggers include "pair with codex", "get a second opinion", "delegate this", "consult on", "review this work". Returns lean, structured JSON responses.
Test generation and verification workflow. Triggers include "generate tests", "increase coverage", "flaky test", and "verify tests". Optimized for vitest, playwright, and convex-test.
Generate structured metaprompts for repeatable AI tasks. Triggers include "create a metaprompt for X", "generate a review prompt", "make a prompt template", or when building prompts for AI tools.
Generate Excalidraw diagrams from text content for Obsidian. Use when user asks to create diagrams, flowcharts, mind maps, or visual representations in Excalidraw format. Triggers on "Excalidraw", "순서도", "마...
GitHub Pull Request를 분석하여 Obsidian PKM 시스템에 work 노트를 자동 생성하고 daily journal에 백링크를 추가합니다. PR URL 또는 PR 번호를 전달하면 자동으로 처리됩니다.
Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas fil...
Detect and resolve incoherence in documentation, code, specs vs implementation. Includes reconciliation phase for applying user-provided resolutions.
Invoke IMMEDIATELY via python script when user requests codebase analysis, architecture review, security assessment, or quality evaluation. Do NOT explore first - the script orchestrates exploration.
Interactive planning and execution for complex tasks. Use when breaking down multi-step projects (planning) or executing approved plans through delegation (execution). Planning creates milestones with specifica...
Optimize system prompts for Claude Code agents using proven prompt engineering patterns. Use when users request prompt improvement, optimization, or refinement for agent workflows, tool instructions, or system...
Invoke IMMEDIATELY via python script for structured problem analysis and decision reasoning. Do NOT explore first - the script orchestrates the workflow.
Start a managed Chrome CDP session with a prewarmed profile dir and reuse login cookies for browser automations.
Prepare a clean local checkout for a GitHub PR (worktree-first via `wf`/`wt`), fetch the PR base ref, and emit PR context (CI checks + PR comments/reviews) as JSON for downstream review.
Generate `llms.txt` and `llms-full.txt` for a docs/product website from just a URL. Detect and reuse an existing `/llms.txt`, discover the docs source repo via “Edit this page”/GitHub links, fall back to `sitem...
Use git-repo-manager (GRM) on this machine via the `grmrepo` wrappers: refresh config from canonical clones, view status, and bootstrap a new machine by syncing repos.
Use when working with stacked branches, managing dependent PRs/CRs, or uncertain about git-spice commands (stack vs upstack vs downstack) - provides command reference, workflow patterns, and common pitfalls for...
Run PAL MCP tools (precommit, codereview, secaudit, debug, apilookup, listmodels, etc.) via the `mcporter` CLI against the PAL stdio MCP server (`uvx … pal-mcp-server`) instead of configuring PAL as a Codex MCP...
Create a new experiment workspace directory: initialize git, write an AGENTS.md goal doc, and create references/ with index.md + notes/links markdown plus GitHub repos cloned under references/repos (gitignored)...
Convert documents and files to Markdown using markitdown. Use when converting PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx, .xls), HTML, CSV, JSON, XML, images (with EXIF/OCR), audio (with transcription)...
Run `codex review` plus PAL `codereview` (via the `pal-mcporter` skill) against a git base ref, then merge both outputs into one prioritized, actionable review.
Simplify and refine code for clarity, consistency, and maintainability while preserving behavior. Use for refactor/simplify requests, polishing PR diffs, or cleaning up recently modified code without changing o...
End-to-end CI fixer loop for the current git branch/PR (GitHub Actions + Buildkite). Use when asked to “fix CI”, “make checks green”, or “address failing checks”, and the workflow should: (1) discover failing c...
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.