{
  "markdown": "# AgenticFlow AI Toolkit\n\n> Connect your AI tools to the AgenticFlow platform.\n\nThe toolkit gives your agent (Claude Code, OpenAI Codex, Cursor, Gemini CLI, …) access to AgenticFlow: build AI agents, deploy multi-agent workforces, inspect and attach MCP tool providers, and automate operations via the `af` CLI.\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](./LICENSE)\n\n## Install\n\n- **Claude Code** — run these in a chat:\n\n  ```\n  /plugin marketplace add PixelML/agenticflow-skill\n  /plugin install agenticflow-plugin@agenticflow-ai-toolkit\n  ```\n\n- **Cursor** — install from the Cursor Marketplace (search \"AgenticFlow\").\n\n- **Gemini CLI** — run:\n\n  ```bash\n  gemini extensions install https://github.com/PixelML/agenticflow-skill\n  ```\n\n- **OpenAI Codex CLI** — in Codex, run `/plugins`, search **AgenticFlow**, and select **Add to Codex**.\n\n- **VS Code / other** — open the Command Palette and run **Chat: Install Plugin From Source**, then paste:\n\n  ```\n  https://github.com/PixelML/agenticflow-skill\n  ```\n\n## Prerequisites\n\nThe skills assume the `af` CLI is installed:\n\n```bash\n# Quick try (no install)\nnpx @pixelml/agenticflow-cli bootstrap --json\n\n# Global install (recommended for daily use)\nnpm install -g @pixelml/agenticflow-cli\n```\n\nRequires Node.js 18+.\n\n### Get authenticated\n\n1. **Get an API key.** Sign in at [app.agenticflow.ai](https://app.agenticflow.ai) → **Settings → API Keys** → **Create key**. Copy the `a9w_...` token.\n2. **Link the CLI.** Either run `af login` (interactive — prompts for API key, workspace ID, and project ID; saves to `~/.agenticflow/auth.json`) OR export env vars in your shell:\n   ```bash\n   export AGENTICFLOW_API_KEY=a9w_xxxxx\n   export AGENTICFLOW_WORKSPACE_ID=<your-workspace-uuid>\n   export AGENTICFLOW_PROJECT_ID=<your-project-ulid>\n   ```\n   Use env vars for CI/CD; `af login` for a dev machine.\n3. **Verify.** Run `af doctor --json --strict` — should exit 0 with `health: true`. If it fails, the `hint` in the error envelope will tell you exactly what to fix.\n4. **Orient.** Run `af bootstrap --json` — this is always the first command of every session. It returns auth, agents, workforces, blueprints, playbooks, and a commands cheat-sheet in one call.\n\n## What you get\n\nThree flagship skills auto-route based on your prompt:\n\n| Skill | When it fires | What it covers |\n| --- | --- | --- |\n| **agenticflow-workforce** | \"team\", \"multi-agent\", \"pipeline\", blueprint names (`dev-shop`, `marketing-agency`, `amazon-seller`, …) | `af workforce *`, blueprint decisions, graph wiring, publish + public URL |\n| **agenticflow-agent** | \"create/build an agent\", \"support bot\", \"customer assistant\", \"system prompt\" | `af agent *`, `--patch` iteration pattern, schema drilldown |\n| **agenticflow-mcp** | \"mcp\", \"attach tools\", provider names (google sheets/docs, notion, slack, gmail, etc.) | `af mcp-clients inspect/list/get`, Pipedream vs Composio write-safety, attach shape |\n\nLong-form reference material stays in [`reference/`](./reference/) — CLI setup, business packs, troubleshooting, glossary.\n\n## Auto-updates\n\nPlugins update automatically as new capabilities land in the CLI. Major surface changes (e.g. the workforce deploy in v1.6) propagate to the skills once the plugin is refreshed.\n\n## Other install methods\n\nIf your platform doesn't support plugins, install the skills directly from this repo or use the `af` CLI standalone:\n\n- [Skills (monolithic legacy copy)](./SKILL.md) — single file, still works\n- [CLI Reference Library](./reference/) — markdown pages usable by any LLM\n\nThe **standalone MCP server** (`agenticflow-mcp` repo) significantly lags the CLI and is **not recommended**. Use the `af` CLI (via `npm install -g @pixelml/agenticflow-cli`) instead.\n\n## Contributing\n\nWe don't accept external pull requests. Any pull requests will be automatically closed.\n\nPixelML employees: open pull requests against the upstream source repository rather than this mirror.\n\n## License\n\nMIT\n",
  "bytes": 3976,
  "sha": "d8d61d75746e8fe9301f6c04f1cc2eb8c397fde65abd1e95fb14ca1195648cf6",
  "repo_slug": "pixelml/agenticflow-skill",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_pixelml_agenticflow_skill_5cefa227/readme"
}