{
  "markdown": "# Fastly Agent Toolkit\n\nA collection of skills for AI coding agents to work with the Fastly platform and edge computing tools.\n\n- [Fastly Agent Toolkit](#fastly-agent-toolkit)\n  - [Agent Plugins](#agent-plugins)\n  - [Available skills](#available-skills)\n  - [Usage](#usage)\n    - [Using the `skills` CLI](#using-the-skills-cli)\n    - [Manual copy](#manual-copy)\n    - [Claude Code](#claude-code)\n      - [Plugin Marketplace](#plugin-marketplace)\n      - [Manual](#manual)\n    - [Codex](#codex)\n    - [Swival](#swival)\n    - [Qwen Code](#qwen-code)\n    - [Gemini CLI](#gemini-cli)\n  - [Skill format](#skill-format)\n  - [Contributing new skills](#contributing-new-skills)\n\n## Agent Plugins\n\nThis repository is a portable [Agent Plugin](https://agent-plugins.org/specification).\nClients load the root [`plugin.json`](plugin.json) manifest and discover the skills in `skills/`.\n\n## Available skills\n\n- `fastly`: Working with the Fastly platform, including services, caching, VCL, WAF, TLS, DDoS protection, purging, and API usage.\n- `fastly-cli`: Using the [Fastly CLI](https://www.fastly.com/documentation/reference/cli/) to manage services, compute apps, logging, WAF, TLS, key-value stores, and stats.\n- `fastly-fiddle`: Testing VCL against real Fastly edge infrastructure with [Fastly Fiddle](https://fiddle.fastly.dev/), covering assertion-based tests, the Fiddle HTTP API, shareable bug reproductions, and CI integration.\n- `fastly-stats`: Fastly traffic numbers via the CLI or raw HTTP, covering the Historical Stats, Real-Time analytics, and Origin/Domain Inspector APIs, and owning the unit, window, and aggregation conventions that decide whether a reported figure is right.\n- `fastly-reference-architectures`: Curated GitHub repositories demonstrating working reference architectures on Fastly, from single Compute applications to systems combining multiple Fastly products.\n- `falco`: VCL development with [Falco](https://github.com/ysugimoto/falco), covering linting, testing, simulation, formatting, REPL, and Terraform integration.\n- `fastlike`: Running Fastly Compute locally with [Fastlike](https://github.com/avidal/fastlike), covering backend configuration, builds, and testing.\n- `viceroy`: Running Fastly Compute locally with [Viceroy](https://github.com/fastly/Viceroy), covering serving, configuration, testing, and SDK adaptation.\n- `xvcl`: The [XVCL](https://dip-proto.github.io/xvcl/) VCL transpiler, covering syntax extensions, subroutines, header manipulation, and caching logic.\n\nEach skill lives under `skills/` with a `SKILL.md` entrypoint and a `references/` directory containing detailed topic files.\n\n**Important:** SKILL.md files reference companion files in their `references/` directory. Make sure your agent is allowed to read from these directories, otherwise it won't be able to follow the references and will miss important context.\n\n## Usage\n\nPick the skills relevant to your project. You probably don't need all of them.\n\n### Using the `skills` CLI\n\nThe [`skills`](https://github.com/vercel-labs/skills) CLI installs skills into the standard `.agents/skills/` directory and automatically symlinks them into agent-specific directories. It supports most agents out of the box.\n\nInstall into the current project:\n\n```bash\nbunx skills add github:fastly/fastly-agent-toolkit --skill falco --skill viceroy\n# or with node:\nnpx skills add github:fastly/fastly-agent-toolkit --skill falco --skill viceroy\n```\n\nInstall globally (available across all projects via `~/.agents/skills/`):\n\n```bash\nbunx skills add -g github:fastly/fastly-agent-toolkit --skill falco --skill viceroy\n```\n\n### Manual copy\n\nIf your agent supports the `.agents/skills/` convention, this is the most portable option. Agents that use this location include Amp, Cline, Codex, Cursor, Gemini CLI, GitHub Copilot, Kimi Code, OpenCode, Replit Agent, Swival, and Warp.\n\nInstall into the current project:\n\n```bash\nmkdir -p .agents/skills\ncp -R ./skills/{falco,viceroy} .agents/skills/\n```\n\nInstall globally (for agents that support `~/.agents/skills/`):\n\n```bash\nmkdir -p ~/.agents/skills\ncp -R ./skills/{falco,viceroy} ~/.agents/skills/\n```\n\nIf your agent doesn't support `.agents/skills/`, use its agent-specific location below.\n\n### [Claude Code](https://code.claude.com/docs/en/overview)\n\n#### Plugin Marketplace\n\n```bash\nclaude plugin install fastly-agent-toolkit@claude-plugins-official\nclaude plugin list\n\n# If this fails, add skills manually in the next section.\n```\n\n#### Manual\n\n```bash\nmkdir -p .claude/skills\ncp -R ./skills/{falco,viceroy} .claude/skills/\n```\n\nFor a quick local setup, the manual copy is more reliable since it doesn't depend on the marketplace.\n\n### [Codex](https://github.com/openai/codex)\n\n```bash\nmkdir -p ~/.codex/skills\ncp -R ./skills/{falco,viceroy} ~/.codex/skills/\n```\n\n### [Swival](https://swival.dev/)\n\nStage the collection in your library first, then add the skills you want:\n\n```bash\nswival skills add --global https://github.com/fastly/fastly-agent-toolkit  # stage into ~/.config/swival/library\nswival skills add fastly-agent-toolkit                                     # install the collection into this project\nswival skills add --global fastly-agent-toolkit                            # or activate it in every project\n```\n\nPrefer only a couple of skills? Activate them by name instead of the whole collection: `swival skills add falco`, `swival skills add viceroy`.\n\n### [Qwen Code](https://qwenlm.github.io/qwen-code-docs/en/users/overview/)\n\nQwen Code requires the experimental skills feature. Enable it by adding to `.qwen/settings.json`:\n\n```json\n{\n  \"tools\": {\n    \"experimental\": {\n      \"skills\": true\n    }\n  }\n}\n```\n\nThen copy skills to the project directory:\n\n```bash\nmkdir -p .qwen/skills\ncp -R ./skills/{falco,viceroy} .qwen/skills/\n```\n\n### [Gemini CLI](https://geminicli.com/)\n\nGemini CLI supports `.agents/skills/` as shown above. You can also link the whole repository using Gemini's extension workflow:\n\n```bash\ngemini extensions link .\n```\n\nSwap `{falco,viceroy}` for whatever combination you need. For VCL work, `falco` and `xvcl` are the most useful. For Fastly Compute, grab `fastly-cli` and either `viceroy` or `fastlike`.\n\n## Skill format\n\nEach skill lives in its own directory as a `SKILL.md` file with YAML frontmatter following the [Agent Skills spec](https://agentskills.io/specification).\nThe skills are validated with [`skillscheck`](https://github.com/Swival/skillscheck).\n\n## Contributing new skills\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md).",
  "bytes": 6515,
  "sha": "04b69df7af9eb72afa9a39eb35f582fae5df74aabfb835e5e2c472437cf658a9",
  "repo_slug": "fastly/fastly-agent-toolkit",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_fastly_fastly_agent_toolkit_fastly_agent_89fa29d3/readme"
}