with one click
init
Initialize AGENTS.md with hierarchical structure and .agents.yml config
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Menu
Initialize AGENTS.md with hierarchical structure and .agents.yml config
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | init |
| description | Initialize AGENTS.md with hierarchical structure and .agents.yml config |
| allowed-tools | Bash Write Read Grep Glob AskUserQuestion Skill |
Set up AI agent documentation and machine-readable config for this project.
Architecture: AGENTS.md (human guidance) + .agents.yml (machine config) + CLAUDE.md (symlink)
Check existing state first: !${CLAUDE_PLUGIN_ROOT}/skills/init/scripts/check-existing.sh
If AGENTS.md exists, ask: Regenerate | Enhance | Skip
Then invoke the hierarchical agents skill:
Skill(skill: "hierarchical-agents")
Complete all 4 phases: Repository Analysis → Root AGENTS.md → Sub-folder files → Special Considerations
For AGENTS.md best practices, see resources/agents-md-template.md in the init-agents-config skill.
Use AskUserQuestion to gather config. Ask in batches of max 4 questions.
| Question | Options |
|---|---|
| Tech Stack | Rails, Python, Node, Generic |
| App Status | Development, Production |
| Task Management | GitHub Issues, Linear, Beads, File-based |
| Workflow | Worktrees, Branches |
| Experience Level | Expert (Recommended), Senior, Intermediate, Beginner |
Experience level definitions:
Multi-stack projects (e.g., Rails + React detected): Ask per-stack experience level instead of single level.
Rails (auto-detect ruby/rails versions first):
| Question | Options |
|---|---|
| Database | SQLite, PostgreSQL, MySQL |
| Frontend | Hotwire, Inertia, API-only |
| CSS | Tailwind, Bootstrap, None |
| JavaScript | Importmap, esbuild, Vite |
| Deployment (multi) | Kamal, Fly.io, Heroku, Render |
| Solid Gems (multi) | Solid Cache, Solid Queue, Solid Cable |
Python (auto-detect python version, framework):
| Question | Options |
|---|---|
| Framework | FastAPI, Django, Flask, None |
| Package Manager | uv, Poetry, pip |
| Database | PostgreSQL, SQLite, None |
Node (auto-detect node version, typescript, framework):
| Question | Options |
|---|---|
| Framework | Next.js, React, Vue/Nuxt, Express/Fastify |
| Package Manager | pnpm, npm, yarn, bun |
| TypeScript | Yes, No |
| Styling | Tailwind, CSS Modules, Styled Components, Sass |
| Testing | Vitest, Jest, Playwright, Cypress |
| Deployment | Vercel, Cloudflare, Netlify, Railway |
| Question | Options |
|---|---|
| Branch Naming | feature/desc, issue-desc, type/issue-desc, user/desc |
| Track in Git | Yes (shared), No (local-only) |
| Local Overrides | Yes (if tracked), No |
| Browser | Chrome, Brave, Edge, Skip |
Run these operations in parallel:
${CLAUDE_PLUGIN_ROOT}/skills/init/scripts/detect-branch.sh${CLAUDE_PLUGIN_ROOT}/skills/init/scripts/detect-tech-stack.sh stackGlob: "**/design-system.md"If design system found, record path in toolbox config.
Load the init-agents-config skill:
Skill(skill: "init-agents-config")
Select template by tech_stack from resources/:
rails.yaml | python.yaml | node.yaml | generic.yamlReplace placeholders with collected values. Handle conditionals:
extras if user selected Solid gemstoolbox.build_task.design_system_path if detectedbrowser.type if Brave or Edge selectedIf not tracking in git: !${CLAUDE_PLUGIN_ROOT}/skills/init/scripts/gitignore-add.sh .agents.yml
If local overrides requested: !${CLAUDE_PLUGIN_ROOT}/skills/init/scripts/gitignore-add.sh .agents.local.yml
If local overrides requested, write .agents.local.yml using template from resources/local-config-template.yaml.
ln -s AGENTS.md CLAUDE.md (backup if exists)${CLAUDE_PLUGIN_ROOT}/skills/init/scripts/verify-setup.shReport what was created:
Create distinctive, production-grade frontend interfaces with high design quality. Use when building web components, pages, or applications. Includes framework-specific guidance for Tailwind, React, Vue, and Rails/Hotwire ecosystems.
Skill file structure, naming conventions, directory layout, frontmatter requirements, and invocation control. Use when creating skill files or slash commands to ensure correct format and validation.
Forces adversarial reasoning before committing to decisions. Triggers on architectural choices, approach selection, and planning phases to prevent premature commitment bias.
Verify LLM reasoning using Reverse Chain-of-Thought (RCoT) to detect overlooked conditions.
Autonomous task implementation - research, plan, build, review, fix, ship
Generate a complete favicon set (ICO, PNG variants, apple-touch-icon, web manifest) from a source image and integrate into the project's HTML layout. Use when user asks to generate favicons, set up PWA icons, or add an apple-touch-icon.