{ "markdown": "

\n \"Revelica\"\n

\n\n

Revelica Skills

\n\nOfficial Revelica plugin for AI agents. Connects an agent to a Revelica product\nworkspace — customer research, competitive analysis, user story maps, goals, bets,\nand the specs that come out of them — and bundles Revelica's own product skills.\nFollows the [Agent Skills open standard](https://agentskills.io/specification),\ncompatible with Claude Code, Cowork, Cursor, Gemini CLI, OpenAI Codex, and more.\n\n## Repository Structure\n\n```\nrevelica/skills\n├── .claude-plugin/\n│ ├── marketplace.json # Claude Code marketplace catalog\n│ ├── plugin.json # Claude Code plugin manifest\n│ └── mcp.json # MCP config for Claude Code plugin\n├── .cursor-plugin/\n│ └── plugin.json # Cursor plugin manifest\n├── skills/ # Skill definitions (Agent Skills open standard)\n│ ├── product-for-coding-agents/ # Product layer for coding agents (orientation)\n│ └── write-spec/ # Author a feature spec attached to an idea\n├── assets/ # Brand icons (README, directory submissions)\n├── server.json # MCP registry manifest (registry.modelcontextprotocol.io)\n├── .mcp.json # MCP config for Cursor/Gemini\n├── gemini-extension.json # Gemini CLI extension manifest\n└── LICENSE # Apache-2.0\n```\n\n## Installation by Platform\n\n### Claude Code\n\n```\n/plugin marketplace add revelica/skills\n/plugin install revelica@revelica\n```\n\nSkills are **model-invoked** — Claude automatically uses them based on context. The MCP\nserver is registered automatically.\n\n### Cowork\n\nAdd `https://api.revelica.com/mcp` as a custom connector in your organization's\nsettings. Skills come with the plugin once it is listed in the plugin directory.\n\n### Cursor\n\nInstall via the `.cursor-plugin/plugin.json` manifest. Cursor will discover skills from\nthe `skills/` directory and connect to the MCP server via `.mcp.json` automatically.\n\n### Gemini CLI\n\n```\ngemini extensions install revelica/skills\n```\n\nThe `gemini-extension.json` manifest registers both skills and the MCP server.\n\n## Available MCP Tools\n\nThese tools are provided by the Revelica MCP server and callable from any skill:\n\n| Tool | Description |\n|------|-------------|\n| `query` | Search or filter the workspace by criteria. Returns ranked matches, plus the schema template when `artifact_type` is set. |\n| `read` | Read a single artifact or entity in full by id, or navigate to a subtree with a dotted field `path`. |\n| `create` | Create new artifacts or entities. Content validated against registered schemas. |\n| `update` | Apply partial field-level updates via dot-path notation. |\n| `load_skill` | Load a skill's instructions and prefetched workspace data. |\n| `list_skills` | List the skills this workspace exposes to MCP clients. |\n\nAll tools require OAuth authentication and enforce Supabase RLS — users only see their\nown workspace's data.\n\n## Available Skills\n\n| Skill | Description |\n|-------|-------------|\n| `product-for-coding-agents` | Orientation for a coding agent: read the idea/spec/UX behind the code, write high-level results (impl docs, PRs, tested feasibility assumptions, ideas, sources) back. |\n| `write-spec` | Author a feature spec attached to an idea, following the Revelica spec template — incremental section-by-section writes that fit coding-agent tool-call budgets. |\n\n## Adding a New Skill\n\n1. Create a folder under `skills/`:\n ```bash\n mkdir skills/my-skill\n touch skills/my-skill/SKILL.md\n ```\n\n2. Write `SKILL.md` following the [Agent Skills spec](https://agentskills.io/specification):\n ```markdown\n ---\n name: my-skill\n description: What this skill does and when to use it.\n compatibility: Requires Revelica MCP server (query, read, create, update tools)\n ---\n\n Instructions for the agent...\n ```\n\n3. Commit and push. Users get the update by running:\n ```\n /plugin update revelica@revelica\n ```\n\nNo backend changes needed unless the skill requires a new MCP tool.\n\n## Connecting the MCP Server Directly\n\nIf you'd rather connect the server without the plugin, add it as a remote MCP\nserver / custom connector:\n\n| | |\n|---|---|\n| **Server URL** | `https://api.revelica.com/mcp` |\n| **Transport** | Streamable HTTP |\n| **Authentication** | OAuth 2.0 with dynamic client registration — no API key to manage |\n| **Prerequisite** | A Revelica workspace ([sign up](https://app.revelica.com)) |\n\nServer metadata is published at\n[`/.well-known/mcp/server-card.json`](https://api.revelica.com/.well-known/mcp/server-card.json).\n\n## Privacy Policy\n\nRevelica's privacy policy — covering what data is collected, how it is used and\nstored, third-party sharing, retention, and how to contact us — is published at\n[revelica.com/privacy](https://revelica.com/privacy). Terms of service are at\n[revelica.com/terms](https://revelica.com/terms).\n\nThe MCP server reads and writes only the product data in your own Revelica\nworkspace. Every request is authenticated with OAuth and enforced by Supabase\nrow-level security, so a connected agent can never see another workspace's data.\nThe server does not query your chat history, conversation summaries, or files.\n\n## Support\n\n- **Issues with the plugin or skills:** [open a GitHub issue](https://github.com/revelica/skills/issues)\n- **Account, workspace, or MCP server issues:** ask@revelica.com\n\n## License\n\n[Apache-2.0](LICENSE) © Revelica\n\n# About Revelica\n\nRevelica is an AI-native product discovery platform. It helps product teams gather customer insights, perform competitive analysis, and experimentally validate ideas that feed into their AI development workflow.\n\n🔗 Homepage with free Pro trial: https://revelica.com\n\n🔗 Template library with playbooks, skills, and insight templates: https://revelica.com/templates\n\n🔗 Free AI tools with no signup required: https://revelica.com/tools\n", "bytes": 6025, "sha": "9d94eee6644c7bd9e9b80f499744fe47fb807f76c77ffddab36f22185fb05c97", "repo_slug": "revelica/skills", "fonte": "repo", "truncated": false, "api": "https://agentalog.com/api/listings/mcp_com_revelica_revelica_7da33b51/readme" }