init
Initialize AGENTS.md with hierarchical structure and .agents.yml config
What this skill does
# Initialize AGENTS.md
Set up AI agent documentation and machine-readable config for this project.
**Architecture:** AGENTS.md (human guidance) + .agents.yml (machine config) + CLAUDE.md (symlink)
## Step 1: Generate AGENTS.md
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.
## Step 2: Gather Configuration
Use `AskUserQuestion` to gather config. Ask in batches of max 4 questions.
### Core Questions (All Users)
| 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:**
- **Beginner**: New to the technology, needs detailed explanations
- **Intermediate**: Comfortable with basics, learning advanced patterns
- **Senior**: Deep knowledge, focus on edge cases and best practices
- **Expert**: Authoritative, skip explanations, just show the code
**Multi-stack projects** (e.g., Rails + React detected): Ask per-stack experience level instead of single level.
### Stack-Specific Questions
**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 |
### Final Questions (All Users)
| 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 |
## Step 3: Auto-Detect Values
**Run these operations in parallel:**
- Default branch: !`${CLAUDE_PLUGIN_ROOT}/skills/init/scripts/detect-branch.sh`
- Tech stack: !`${CLAUDE_PLUGIN_ROOT}/skills/init/scripts/detect-tech-stack.sh stack`
- Design system: `Glob: "**/design-system.md"`
If design system found, record path in toolbox config.
## Step 4: Write .agents.yml
Load the init-agents-config skill:
```
Skill(skill: "init-agents-config")
```
Select template by tech_stack from `resources/`:
- `rails.yaml` | `python.yaml` | `node.yaml` | `generic.yaml`
Replace placeholders with collected values. Handle conditionals:
- Only include `extras` if user selected Solid gems
- Only include `toolbox.build_task.design_system_path` if detected
- Only uncomment `browser.type` if Brave or Edge selected
### Gitignore + Local Config
If not tracking in git: !`${CLAUDE_PLUGIN_ROOT}/skills/init/scripts/gitignore-add.sh .agents.yml`
If local overrides requested: !`${CLAUDE_PLUGIN_ROOT}/skills/init/scripts/gitignore-add.sh .agents.local.yml`
If local overrides requested, write `.agents.local.yml` using template from `resources/local-config-template.yaml`.
## Step 5: Finalize Setup
1. **Create symlink** - `ln -s AGENTS.md CLAUDE.md` (backup if exists)
2. **Verify** - Run verification: !`${CLAUDE_PLUGIN_ROOT}/skills/init/scripts/verify-setup.sh`
## Output Summary
Report what was created:
- AGENTS.md structure (line count, sub-folders)
- .agents.yml (key settings)
- Design system status (detected path or suggest Skill("ux-brief"))
- Symlink and local config status
Related in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.