AI Agent Workflow Collection

Internal skill invoked by repo-standards polish phase 6 to audit Claude Code plugin projects. Fetches live docs and runs scripts/validate-plugin-json.sh + scripts/validate-skill-frontmatter.py (via scripts/check-skill-frontmatter.sh) to detect misuse, broken hook paths, stale patterns, and missed capabilities. Returns structured P1 findings before PR. Never invoke directly — use repo-standards. Also callable by other skills needing live-doc-grounded answers about Claude Code hooks, skills, plugin.json, or MCP config.

Use when the user wants a polished, shareable single-file HTML technical document with a dark developer / terminal aesthetic — including comparison tables (A vs B), reference sheets, cheatsheets, changelogs, release notes, feature breakdowns, and API docs. Trigger phrases: "make a comparison table", "write a reference doc", "create a feature breakdown", "styled HTML doc", "dark terminal doc", "developer-facing HTML", "comparison cheatsheet", "technical reference page", "release notes HTML", "offline HTML doc", "single-file HTML page", "API cheatsheet", "git cheatsheet", "vs comparison".

Use when the user asks to build a UI, interactive explainer, dashboard, visualizer, diagram, reference tool, or any artifact that needs a consistent visual design system in the "engineer's field-notebook" aesthetic. Trigger on: "build a UI for", "create an interactive", "make a visualizer", "generate an artifact", "design a component", "create a dashboard", "make an explainer", or any request to produce a React/HTML artifact with content to display. Also trigger when the user says "make it look like the field-notebook style" or references the warm stone-paper aesthetic.

Internal guardrail invoked by mcp-builder only. Audits MCP tool definitions that contain list, search, find, getall, or SQL-executing operations for missing pagination/limit parameters. NOT triggered by general MCP questions, single-item getters, or mutation tools. mcp-builder calls this at Phase 1.4 (after cataloging endpoints), Phase 3.0 (before writing each list/search tool schema), Phase 4.1 (post-Inspector checklist), and Phase 5 (eval design). Skip invocation when all tools are single-item getters or mutations only.

Use when auditing or setting up a repository for multi-agent development across Claude Code, Cursor, and Codex — or making a repo compatible with those assistants. Triggers: multi-agent repo, audit agent setup, AGENTS.md gaps, make compatible with Claude and Cursor, add Codex support, add cursor rules, generate AGENTS.md, agent drift, canonical AGENTS.md, multi-agent-repo review/plan/dev, multi-platform AI support.

Use when the user wants to convert an informal task, feature request, spec, or review doc into a structured implementation plan before any code is written. User''s intent is organization and sequencing — phases, dependency ordering, and GitHub issues that make work trackable and reviewable. Invoke for: ''plan this'', ''break into phases'', ''create issues for'', ''decompose this spec'', ''turn into tickets'', ''what order should I tackle these'', ''help me organize this work'', ''structure this feature'', ''plan-dev''. This is distinct from architecture analysis of existing code, how-to questions, or direct coding requests — the output is a roadmap, not code.

Use when auditing any repo that uses Claude Code, OpenAI Codex CLI, or Cursor — plugin repos, app repos, or hybrids. Detects target usage via manifests, CLAUDE.md, AGENTS.md, .cursor/rules/, skills/, hooks/, and related signals; fetches live docs per target; identifies unused new features; synthesizes a numbered improvement plan. Synonyms: "sync my plugin", "check against latest docs", "what features am I missing", "audit all platforms", "/platform-sync".

Internal companion to platform-sync. Fetches live Claude Code docs, reads the local .claude-plugin config (plugin.json, skills/, hooks/hooks.json), identifies features in the latest docs NOT yet used, and returns structured improvement steps. Not user-invocable — called by the platform-sync umbrella skill.

Internal companion to platform-sync. Fetches live OpenAI Codex CLI docs (github.com/openai/codex), reads the local .codex-plugin/plugin.json, identifies features not yet leveraged, and returns structured improvement steps. Not user-invocable — called by the platform-sync umbrella skill.

Internal companion to platform-sync. Fetches live Cursor docs (docs.cursor.com), reads the local .cursor-plugin/plugin.json, identifies new Cursor features not yet used, and returns structured improvement steps. Not user-invocable — called by the platform-sync umbrella skill.

Use when the user wants to actively drive a PR to completion — ''finish this PR'', ''address review comments'', ''ship/land/close the PR'', ''drive PR N to merge'', ''fix CI and merge'', ''clean up this PR''. Persistently loops: addresses all review threads, fixes branch-related CI, retries flakes (max 3×), always enables auto-merge, and stops when merged or blocked (asks for help).

Use when the user wants to create a new GitHub repository from scratch with production-ready infrastructure. Triggers: ''scaffold a repo'', ''create a new repo'', ''set up a new project'', ''new github repo'', ''bootstrap a project'', ''forge a repo'', ''/repo-scaffold'', ''start a new repo'', ''initialize a project'', ''make me a repo'', ''agent-kit'', ''plugin marketplace''. Use --type plugin for agent-kit distribution repos. Does NOT trigger for repo-standards (existing repo polish) or when the user only wants docs.

Use when auditing or polishing a repository to Tamir Cohen standards — README badges (author, version, AI targets), Makefile install/update/uninstall, docs tree, CI/CD, changelog + versioning policy, branch protection, employer IP scan, repo hygiene, and multi-agent setup. Triggers: repo standards, polish this repo, prepare for GitHub, world-class repo, publish-ready, scan employer IP, fix repo hygiene, repo-standards review/plan/polish, standards audit.

Use when running, validating, or testing the tamirs-superpowers Claude Code plugin — checks JSON validity, shellcheck hooks, SKILL.md frontmatter, statusline output, hook wiring, and absence of hardcoded paths or internal references. Trigger phrases: ''run the plugin health check'', ''validate the plugin'', ''test tamirs-superpowers'', ''smoke test the plugin'', ''check the plugin'', ''is the plugin clean''.

Use when switching between Claude Code, Cursor, and Codex mid-task without losing context — hand off work via GitHub issue Resume blocks, resume on another platform, or list active agent-owned issues and worktrees. Triggers: switch agent, hand off issue, resume issue, rate limited switch platform, continue on Cursor, pick up where I left off, cross-platform handoff, switch-dev, agent handoff.

Use when the user pastes a stack trace, traceback, panic, crash log, or error message WITH a file:line reference and wants to know the root cause. Triggers on: ''debug this error'', ''look at this stack trace'', ''why does X crash'', ''what causes this exception'', ''why is this panicking'', ''look at this file:line'', error types (NullPointerException, AttributeError, TypeError, nil pointer dereference, unwrap on None, index out of bounds, segfault, unbound variable, cannot read properties of undefined). Does NOT trigger on vague ''something is broken'' or ''why is it slow'' without a concrete error signal.