{
  "markdown": "# Rust Agentic Skills\n\n[![Rust Guild](https://img.shields.io/badge/Agent-Rust%20Guild-orange)](https://github.com/rust-lang/rust)\n[![Research-Plan-Implement Methodology](https://img.shields.io/badge/Methodology-RPI-blue)](AGENTS.md)\n[![Claude Ready](https://img.shields.io/badge/Claude-Plugin-purple)](.Claude-plugin/marketplace.json)\n[![Gemini Extension](https://img.shields.io/badge/Gemini-Extension-blue)](gemini-extension.json)\n[![Antigravity Compatible](https://img.shields.io/badge/Antigravity-Engine-green)](AGENTS.md)\n[![Install with Skills.sh](https://img.shields.io/badge/Install_with-skills.sh-000000?style=for-the-badge)](https://skills.sh)\n\n**A modular, constraint-based skill set for Autonomous AI coding agents.**\n\nThis repository transforms any general-purpose LLM (Claude, Gemini) into a **disciplined Rust engineering team**. It adheres to the **Agent Context Protocol (ACP)** to provide self-describing skills that explicitly define their triggers, capabilities, and execution phases.\n\n---\n\n## // Architecture Overview\n\n![Architecture Diagram](assets/rust-agentic-skill-architecture.png)\n\nWe do not use monolithic instruction files. Instead, every skill in `skills/` follows the **Brain-Tool-Context** architecture to maximize token efficiency:\n\n1.  **Driver (`SKILL.md`)**:\n    - **The Brain**. Contains minimal YAML metadata (`trigger`, `rpi_phase`) and high-level role benchmarks.\n    - _Usage_: The agent reads this first to decide if it is relevant.\n2.  **Tools (`scripts/`)**:\n    - **The Hands**. Executable code (Shell scripts, Rust binaries) for reliable, deterministic task execution.\n    - _Usage_: The agent executes these to perform work (e.g., `init_project.sh`, `explain_error.sh`).\n3.  **Context (`references/`)**:\n    - **The Knowledge**. Deep-dive documentation and \"Dictionaries of Pain\".\n    - _Usage_: \"Lazy loaded\" by the agent only when specifically needed to solve a complex problem.\n\n---\n\n## // Integration Guide\n\n### 1. Claude Code (Plugin)\n\nThis repository is a compliant Claude Plugin.\n\n1.  Clone this repository locally.\n2.  Allow Claude to discover the `.Claude-plugin/marketplace.json` manifest.\n3.  **Result**: Claude will automatically see \"Rust Kernel\" and \"Lint Hunter\" as available tools.\n\n### 2. Gemini CLI (Extension)\n\nCompatible with the Gemini CLI tool via the **Model Context Protocol (MCP)**. This repo provides a dynamic server that auto-discovers skills.\n\n1.  **Link Extension**:\n    ```bash\n    gemini extensions link .\n    ```\n2.  **Activate**:\n    ```bash\n    gemini context set rust-agentic-skills\n    ```\n3.  **Result**: The `rust-agentic-skills` server starts up, reads your `skills/` directory, and dynamically routes your requests to the appropriate skill (e.g., \"Lint Hunter\").\n\n### 3. Manual / Custom Agents\n\n**Running the MCP Server Manually:**\nYou can run the server directly to verify standard JSON-RPC communication:\n\n```bash\n./bootstrap.sh\n```\n\n_(Or `cargo run --release` if you prefer manual builds)_\n\n_(Expects JSON-RPC messages on stdin)_\n\nFor generic agents (ChatGPT, heavily customized setups):\n\n1.  **System Prompt**: Load [AGENTS.md](AGENTS.md) as your system instruction. It defines the **RPI (Research → Plan → Implement)** loop.\n2.  **Context Loading**: When the agent enters a specific phase (e.g., \"Verification\"), manually load the relevant `SKILL.md` (e.g., `skills/lint-hunter/SKILL.md`).\n\n---\n\n## // See it in Action\n\nWant to see what a full session looks like?\n\n- **[See Example Trace](examples/gemini_session_trace.md)**: A real-world interaction log showing the agent initializing a project, running commands, and validating outputs.\n\n---\n\n## // How to Contribute 🤝\n\nWe welcome new skills! Follow the **Triad Pattern**:\n\n1.  **Create Directory**: `skills/<your-skill-name>/`.\n2.  **Create Driver**: Add `SKILL.md` with YAML frontmatter:\n    ```yaml\n    ---\n    name: My Skill\n    description: What it does.\n    rpi_phase: Implementation\n    trigger:\n      - \"keyword1\"\n      - \"keyword2\"\n    capabilities:\n      - capability 1\n    ---\n    ```\n3.  **Add Tools**: Put executable scripts in `skills/<your-skill-name>/scripts/`.\n4.  **Add Context**: Put documentation in `skills/<your-skill-name>/references/`.\n5.  **Generate Docs**: Run `make doc` to update `AGENTS.md`.\n\n---\n\n## // Roadmap (In Progress / TBD)\n\n- [ ] **Multi-Agent Beast Mode**: Chaining multiple skills in a single \"Beast Mode\" loop without human intervention.\n- [ ] **New Skill**: `Test Architect` (Refactoring & property-based testing).\n- [ ] **New Skill**: `Crates.io Scout` (Dependency analysis).\n- [ ] **Automated CI**: GitHub Action to run `make verify` on PRs.\n\n---\n\n## 📜 License\n\nMIT\n",
  "bytes": 4656,
  "sha": "d6e65dd9c0460dc7249d1cc2bad5fa49f62182d476c733ef03d69e9885a1960a",
  "repo_slug": "udapy/rust-agentic-skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_udapy_rust_agentic_skills_10fae0ef/readme"
}