Create and maintain a multi-tool context setup using `AGENTS.md` as canonical source and synced adapter files for other tools.
Scanned 6/2/2026
Install via CLI
openskills install Zidong-IA/BIBLIOTECA# Skill: context-files-bootstrap
## Purpose
Create and maintain a multi-tool context setup using `AGENTS.md` as canonical source and synced adapter files for other tools.
## When to use
Use this skill when the user asks to:
- Create `AGENTS.md` from scratch
- Translate existing context files to a unified format
- Add `CLAUDE.md`, `GEMINI.md`, `COPILOT.md`, `CURSOR.md`, `CODEX.md`, `AGENT.md` adapters
- Keep all context files synchronized after process changes
## Output files
Mandatory:
- `AGENTS.md` (canonical)
Optional adapters (create only requested ones):
- `CLAUDE.md`
- `GEMINI.md`
- `COPILOT.md`
- `CURSOR.md`
- `CODEX.md`
- `AGENT.md`
## Workflow
1. Inspect existing docs (`README.md`, CI workflows, lint/test scripts, architecture docs).
2. Draft `AGENTS.md` with executable commands and explicit conventions.
3. Create adapter files as thin wrappers that point to `AGENTS.md`.
4. Verify consistency across files.
5. Return a short changelog with touched paths and any assumptions.
## AGENTS.md minimum sections
- Project overview
- Setup commands
- Development/test/lint/typecheck/build commands
- Code style and architecture rules
- Security and secret handling
- Contribution flow (commit/PR)
## Quality rules
- Prefer precise commands over generic text.
- Avoid duplicated policy text across adapters.
- Keep adapters short and stable.
- If something is unknown, mark as `TODO:` instead of inventing details.
## Adapter template
Use this exact structure for adapters:
```markdown
# <TOOL_FILE_NAME>
This repository uses `AGENTS.md` as the canonical agent context.
Read and apply first: `./AGENTS.md`
If this file conflicts with `AGENTS.md`, `AGENTS.md` wins.
If user instructions in chat conflict, user instructions win.
```
## Maintenance mode
When updating an existing project:
1. Update `AGENTS.md` first.
2. Refresh adapter files only if precedence text is missing or stale.
3. Do not add tool-specific behavior unless explicitly requested.
## Deliverable style
- Keep final response concise.
- Include list of created/updated files.
- Include 1-2 practical next steps.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.