[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BK7BYAEX43RPH679XZX1FK":3,"skill-same:01M7BK7BYAEX43RPH679XZX1FK":47},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7BK7BYAEX43RPH679XZX1FK","setup-mcp",null,"Configure Model Context Protocol (MCP) servers in .agents\u002Fmcp_config.json (project-level) or ~\u002F.gemini\u002Fconfig\u002Fmcp_config.json (global). User-invoked skill.","fderuiter\u002Fagy-skills","fderuiter","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F127706008?v=4","01M6C40AWP9EPQBS3EG0RF5DRD","Frederick de Ruiter","01M7BK63K60DTR50H82SAHMYHK",1,"MIT","https:\u002F\u002Fgithub.com\u002Ffderuiter\u002Fagy-skills\u002Fblob\u002Fmain\u002Fskills\u002Fengineering\u002Fsetup-mcp\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: setup-mcp\ndescription: \"Configure Model Context Protocol (MCP) servers in .agents\u002Fmcp_config.json (project-level) or ~\u002F.gemini\u002Fconfig\u002Fmcp_config.json (global). User-invoked skill.\"\n---\n\n# Setup MCP\n\nConfigure Model Context Protocol (MCP) servers for Antigravity, connecting the agent to external tools, databases, APIs, and local services.\n\nThis is a user-invoked skill (`\u002Fsetup-mcp`). It walks developers through selecting transport types, configuring server definitions, injecting environment variables safely, and verifying server connectivity.\n\n## Target Configuration Files\n\nAntigravity discovers MCP servers from two primary configuration files:\n\n1. **Project-level**: `.agents\u002Fmcp_config.json` (or `.agent\u002Fmcp_config.json`)\n   - Located at the repository root.\n   - Ideal for project-specific tools: local development databases, repository-scoped filesystem servers, repo git tools, and project mock servers.\n   - Can be committed to version control to share tool configurations across the team (without committing secrets).\n\n2. **Global**: `~\u002F.gemini\u002Fconfig\u002Fmcp_config.json`\n   - Located in the user's home directory.\n   - Ideal for personal credentials, global developer utilities, cross-project integrations, and machine-wide services.\n\nBoth files use the standard `mcpServers` object format:\n\n```json\n{\n  \"mcpServers\": {\n    \"\u003Cserver-name>\": {\n      ...\n    }\n  }\n}\n```\n\n## Supported Transports & Schemas\n\n### 1. Stdio Transport (Local Process)\n\nUsed for local command-line tools, scripts, or package runners (`npx`, `uvx`, `node`, `python`). The language server spawns the child process and communicates via standard input and standard output.\n\n**JSON Schema:**\n\n```json\n{\n  \"command\": \"executable-name-or-path\",\n  \"args\": [\"arg1\", \"arg2\"],\n  \"env\": {\n    \"ENV_VAR_NAME\": \"value\"\n  },\n  \"cwd\": \"\u002Foptional\u002Fworking\u002Fdirectory\"\n}\n```\n\n- `command` (string, required): Executable name on `PATH` (for example `npx`, `uvx`, `node`, `python`) or an absolute path to a binary.\n- `args` (array of strings, optional): Command-line arguments passed to the executable.\n- `env` (object, optional): Environment variables injected into the child process.\n- `cwd` (string, optional): Working directory for process execution.\n\n### 2. SSE Transport (Server-Sent Events)\n\nUsed for remote MCP services accessible over HTTP via Server-Sent Events.\n\n**JSON Schema:**\n\n```json\n{\n  \"serverUrl\": \"https:\u002F\u002Fmcp.example.com\u002Fsse\",\n  \"headers\": {\n    \"Authorization\": \"Bearer YOUR_TOKEN\"\n  }\n}\n```\n\n- `serverUrl` (string, required): Full HTTP(S) URL of the remote SSE endpoint.\n- `headers` (object, optional): Custom HTTP headers for authentication and routing.\n\n### 3. HTTP Transport (Streamable HTTP Endpoint)\n\nUsed for remote MCP servers using streamable HTTP or REST endpoints.\n\n**JSON Schema:**\n\n```json\n{\n  \"url\": \"https:\u002F\u002Fmcp.example.com\u002Fapi\",\n  \"headers\": {\n    \"Authorization\": \"Bearer YOUR_TOKEN\",\n    \"X-Custom-Header\": \"value\"\n  }\n}\n```\n\n- `url` (string, required): Full HTTP(S) URL of the MCP endpoint.\n- `headers` (object, optional): Custom HTTP headers such as bearer tokens or API keys.\n\n## Common Server Recipes\n\n### PostgreSQL Server (`@modelcontextprotocol\u002Fserver-postgres`)\n\nExposes PostgreSQL database inspection and query tools.\n\n```json\n{\n  \"mcpServers\": {\n    \"postgres\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@modelcontextprotocol\u002Fserver-postgres\",\n        \"postgresql:\u002F\u002Fuser:password@localhost:5432\u002Fmydb\"\n      ]\n    }\n  }\n}\n```\n\nOr using an environment variable for credentials:\n\n```json\n{\n  \"mcpServers\": {\n    \"postgres\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@modelcontextprotocol\u002Fserver-postgres\"],\n      \"env\": {\n        \"POSTGRES_URL\": \"postgresql:\u002F\u002Fuser:password@localhost:5432\u002Fmydb\"\n      }\n    }\n  }\n}\n```\n\n### Filesystem Server (`@modelcontextprotocol\u002Fserver-filesystem`)\n\nGrants scoped file read, write, and directory inspection capabilities. Always provide explicit allowed directory paths as arguments.\n\n```json\n{\n  \"mcpServers\": {\n    \"filesystem\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@modelcontextprotocol\u002Fserver-filesystem\",\n        \"\u002Fpath\u002Fto\u002Fallowed\u002Fdirectory\",\n        \"\u002Fsecond\u002Fallowed\u002Fdirectory\"\n      ]\n    }\n  }\n}\n```\n\n### GitHub Server (`@modelcontextprotocol\u002Fserver-github`)\n\nEnables searching repositories, reading issues, managing pull requests, and inspecting file contents across GitHub.\n\n```json\n{\n  \"mcpServers\": {\n    \"github\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@modelcontextprotocol\u002Fserver-github\"\n      ],\n      \"env\": {\n        \"GITHUB_PERSONAL_ACCESS_TOKEN\": \"ghp_yourPersonalAccessToken\"\n      }\n    }\n  }\n}\n```\n\n### Git Server (`@modelcontextprotocol\u002Fserver-git`)\n\nEnables reading commit history, diffs, branches, and status from a local git repository.\n\nNode \u002F npx version:\n```json\n{\n  \"mcpServers\": {\n    \"git\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@modelcontextprotocol\u002Fserver-git\",\n        \"--repository\",\n        \"\u002Fpath\u002Fto\u002Flocal\u002Fgit\u002Frepo\"\n      ]\n    }\n  }\n}\n```\n\nPython \u002F uvx version:\n```json\n{\n  \"mcpServers\": {\n    \"git\": {\n      \"command\": \"uvx\",\n      \"args\": [\n        \"mcp-server-git\",\n        \"--repository\",\n        \"\u002Fpath\u002Fto\u002Flocal\u002Fgit\u002Frepo\"\n      ]\n    }\n  }\n}\n```\n\n### Custom Local Node.js Server\n\nUsed for proprietary or internal MCP servers written in TypeScript or JavaScript.\n\n```json\n{\n  \"mcpServers\": {\n    \"my-node-tools\": {\n      \"command\": \"node\",\n      \"args\": [\".\u002Fscripts\u002Fmcp-server.js\"],\n      \"cwd\": \"\u002Fpath\u002Fto\u002Fproject\",\n      \"env\": {\n        \"NODE_ENV\": \"development\",\n        \"API_KEY\": \"secret-key\"\n      }\n    }\n  }\n}\n```\n\n### Custom Local Python Server\n\nUsed for custom Python MCP servers built with the FastMCP or MCP Python SDK.\n\n```json\n{\n  \"mcpServers\": {\n    \"my-python-tools\": {\n      \"command\": \"python\",\n      \"args\": [\"-m\", \"my_mcp_package.server\"],\n      \"env\": {\n        \"PYTHONPATH\": \".\u002Fsrc\",\n        \"SERVICE_ENDPOINT\": \"http:\u002F\u002Flocalhost:8080\"\n      }\n    }\n  }\n}\n```\n\nOr using `uv run`:\n\n```json\n{\n  \"mcpServers\": {\n    \"my-python-tools\": {\n      \"command\": \"uv\",\n      \"args\": [\"run\", \"--with\", \"mcp\", \"python\", \".\u002Fscripts\u002Fserver.py\"]\n    }\n  }\n}\n```\n\n## Workflow and Execution Steps\n\nWhen `\u002Fsetup-mcp` is invoked, follow this structured process:\n\n### 1. Scope and Needs Assessment\n\nAsk the developer what service, database, or tool they want to connect:\n- Identify if this is a standard recipe (PostgreSQL, Filesystem, GitHub, Git) or a custom server.\n- Determine configuration scope:\n  - **Project-level (`.agents\u002Fmcp_config.json`)**: Default for repo-specific tools.\n  - **Global (`~\u002F.gemini\u002Fconfig\u002Fmcp_config.json`)**: For personal tools and machine-wide access.\n- Check if the target config file already exists and parse its existing `mcpServers`.\n- **Upstream verification**: If configuring an unfamiliar or external MCP package, use `search_web` and `read_url_content` to fetch the authoritative npm\u002FPyPI documentation, required environment variables, and CLI argument schema from primary sources before drafting the JSON.\n\n### 2. Configure Server Entry\n\nDraft the server configuration object according to the selected transport:\n- Verify executable paths and command availability (`npx`, `uvx`, `node`, `python`).\n- Map all necessary arguments and environment variables.\n- Keep secrets safe: remind the developer to use local environment variables or private global configs if the project config is committed to public source control.\n\n### 3. Write and Merge\n\n- Read the target configuration file if it exists.\n- Preserve all existing server definitions under `mcpServers`.\n- Add or update the target server definition under its designated key name.\n- Format the JSON file cleanly with 2-space indentation.\n- Ensure the parent directory (`.agents\u002F` or `~\u002F.gemini\u002Fconfig\u002F`) exists before writing.\n\n### 4. Verification Step\n\nRun proactive diagnostics to ensure the configured MCP server will start cleanly:\n\n1. **Syntax and JSON check**: Ensure the output file is valid JSON with top-level `mcpServers` mapping.\n2. **Command \u002F Binary check**: Test if the command exists and is executable in the current environment (for example running `npx --version`, `python --version`, or verifying local script file paths).\n3. **Environment variable check**: Verify all required keys in the `env` block are populated with non-empty values.\n4. **Path & Permission check**:\n   - For filesystem servers: verify target paths exist and have appropriate read\u002Fwrite permissions.\n   - For database servers: verify database port and host are reachable.\n   - For git servers: verify the directory is a valid git repository.\n   - For remote SSE\u002FHTTP servers: verify the URL endpoint is reachable.\n\n### 5. Final Confirmation\n\nReport the setup outcome to the user:\n- Show the exact JSON configuration block that was written.\n- Specify the configuration path (`.agents\u002Fmcp_config.json` or `~\u002F.gemini\u002Fconfig\u002Fmcp_config.json`).\n- Mention how Antigravity will discover the new tools on next prompt or agent reload.\n","# Setup MCP\n\nConfigure Model Context Protocol (MCP) servers for Antigravity, connecting the agent to external tools, databases, APIs, and local services.\n\nThis is a user-invoked skill (`\u002Fsetup-mcp`). It walks developers through selecting transport types, configuring server definitions, injecting environment variables safely, and verifying server connectivity.\n\n## Target Configuration Files\n\nAntigravity discovers MCP servers from two primary configuration files:\n\n1. **Project-level**: `.agents\u002Fmcp_config.json` (or `.agent\u002Fmcp_config.json`)\n   - Located at the repository root.\n   - Ideal for project-specific tools: local development databases, repository-scoped filesystem servers, repo git tools, and project mock servers.\n   - Can be committed to version control to share tool configurations across the team (without committing secrets).\n\n2. **Global**: `~\u002F.gemini\u002Fconfig\u002Fmcp_config.json`\n   - Located in the user's home directory.\n   - Ideal for personal credentials, global developer utilities, cross-project integrations, and machine-wide services.\n\nBoth files use the standard `mcpServers` object format:\n\n```json\n{\n  \"mcpServers\": {\n    \"\u003Cserver-name>\": {\n      ...\n    }\n  }\n}\n```\n\n## Supported Transports & Schemas\n\n### 1. Stdio Transport (Local Process)\n\nUsed for local command-line tools, scripts, or package runners (`npx`, `uvx`, `node`, `python`). The language server spawns the child process and communicates via standard input and standard output.\n\n**JSON Schema:**\n\n```json\n{\n  \"command\": \"executable-name-or-path\",\n  \"args\": [\"arg1\", \"arg2\"],\n  \"env\": {\n    \"ENV_VAR_NAME\": \"value\"\n  },\n  \"cwd\": \"\u002Foptional\u002Fworking\u002Fdirectory\"\n}\n```\n\n- `command` (string, required): Executable name on `PATH` (for example `npx`, `uvx`, `node`, `python`) or an absolute path to a binary.\n- `args` (array of strings, optional): Command-line arguments passed to the executable.\n- `env` (object, optional): Environment variables injected into the child process.\n- `cwd` (string, optional): Working directory for process execution.\n\n### 2. SSE Transport (Server-Sent Events)\n\nUsed for remote MCP services accessible over HTTP via Server-Sent Events.\n\n**JSON Schema:**\n\n```json\n{\n  \"serverUrl\": \"https:\u002F\u002Fmcp.example.com\u002Fsse\",\n  \"headers\": {\n    \"Authorization\": \"Bearer YOUR_TOKEN\"\n  }\n}\n```\n\n- `serverUrl` (string, required): Full HTTP(S) URL of the remote SSE endpoint.\n- `headers` (object, optional): Custom HTTP headers for authentication and routing.\n\n### 3. HTTP Transport (Streamable HTTP Endpoint)\n\nUsed for remote MCP servers using streamable HTTP or REST endpoints.\n\n**JSON Schema:**\n\n```json\n{\n  \"url\": \"https:\u002F\u002Fmcp.example.com\u002Fapi\",\n  \"headers\": {\n    \"Authorization\": \"Bearer YOUR_TOKEN\",\n    \"X-Custom-Header\": \"value\"\n  }\n}\n```\n\n- `url` (string, required): Full HTTP(S) URL of the MCP endpoint.\n- `headers` (object, optional): Custom HTTP headers such as bearer tokens or API keys.\n\n## Common Server Recipes\n\n### PostgreSQL Server (`@modelcontextprotocol\u002Fserver-postgres`)\n\nExposes PostgreSQL database inspection and query tools.\n\n```json\n{\n  \"mcpServers\": {\n    \"postgres\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@modelcontextprotocol\u002Fserver-postgres\",\n        \"postgresql:\u002F\u002Fuser:password@localhost:5432\u002Fmydb\"\n      ]\n    }\n  }\n}\n```\n\nOr using an environment variable for credentials:\n\n```json\n{\n  \"mcpServers\": {\n    \"postgres\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@modelcontextprotocol\u002Fserver-postgres\"],\n      \"env\": {\n        \"POSTGRES_URL\": \"postgresql:\u002F\u002Fuser:password@localhost:5432\u002Fmydb\"\n      }\n    }\n  }\n}\n```\n\n### Filesystem Server (`@modelcontextprotocol\u002Fserver-filesystem`)\n\nGrants scoped file read, write, and directory inspection capabilities. Always provide explicit allowed directory paths as arguments.\n\n```json\n{\n  \"mcpServers\": {\n    \"filesystem\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@modelcontextprotocol\u002Fserver-filesystem\",\n        \"\u002Fpath\u002Fto\u002Fallowed\u002Fdirectory\",\n        \"\u002Fsecond\u002Fallowed\u002Fdirectory\"\n      ]\n    }\n  }\n}\n```\n\n### GitHub Server (`@modelcontextprotocol\u002Fserver-github`)\n\nEnables searching repositories, reading issues, managing pull requests, and inspecting file contents across GitHub.\n\n```json\n{\n  \"mcpServers\": {\n    \"github\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@modelcontextprotocol\u002Fserver-github\"\n      ],\n      \"env\": {\n        \"GITHUB_PERSONAL_ACCESS_TOKEN\": \"ghp_yourPersonalAccessToken\"\n      }\n    }\n  }\n}\n```\n\n### Git Server (`@modelcontextprotocol\u002Fserver-git`)\n\nEnables reading commit history, diffs, branches, and status from a local git repository.\n\nNode \u002F npx version:\n```json\n{\n  \"mcpServers\": {\n    \"git\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@modelcontextprotocol\u002Fserver-git\",\n        \"--repository\",\n        \"\u002Fpath\u002Fto\u002Flocal\u002Fgit\u002Frepo\"\n      ]\n    }\n  }\n}\n```\n\nPython \u002F uvx version:\n```json\n{\n  \"mcpServers\": {\n    \"git\": {\n      \"command\": \"uvx\",\n      \"args\": [\n        \"mcp-server-git\",\n        \"--repository\",\n        \"\u002Fpath\u002Fto\u002Flocal\u002Fgit\u002Frepo\"\n      ]\n    }\n  }\n}\n```\n\n### Custom Local Node.js Server\n\nUsed for proprietary or internal MCP servers written in TypeScript or JavaScript.\n\n```json\n{\n  \"mcpServers\": {\n    \"my-node-tools\": {\n      \"command\": \"node\",\n      \"args\": [\".\u002Fscripts\u002Fmcp-server.js\"],\n      \"cwd\": \"\u002Fpath\u002Fto\u002Fproject\",\n      \"env\": {\n        \"NODE_ENV\": \"development\",\n        \"API_KEY\": \"secret-key\"\n      }\n    }\n  }\n}\n```\n\n### Custom Local Python Server\n\nUsed for custom Python MCP servers built with the FastMCP or MCP Python SDK.\n\n```json\n{\n  \"mcpServers\": {\n    \"my-python-tools\": {\n      \"command\": \"python\",\n      \"args\": [\"-m\", \"my_mcp_package.server\"],\n      \"env\": {\n        \"PYTHONPATH\": \".\u002Fsrc\",\n        \"SERVICE_ENDPOINT\": \"http:\u002F\u002Flocalhost:8080\"\n      }\n    }\n  }\n}\n```\n\nOr using `uv run`:\n\n```json\n{\n  \"mcpServers\": {\n    \"my-python-tools\": {\n      \"command\": \"uv\",\n      \"args\": [\"run\", \"--with\", \"mcp\", \"python\", \".\u002Fscripts\u002Fserver.py\"]\n    }\n  }\n}\n```\n\n## Workflow and Execution Steps\n\nWhen `\u002Fsetup-mcp` is invoked, follow this structured process:\n\n### 1. Scope and Needs Assessment\n\nAsk the developer what service, database, or tool they want to connect:\n- Identify if this is a standard recipe (PostgreSQL, Filesystem, GitHub, Git) or a custom server.\n- Determine configuration scope:\n  - **Project-level (`.agents\u002Fmcp_config.json`)**: Default for repo-specific tools.\n  - **Global (`~\u002F.gemini\u002Fconfig\u002Fmcp_config.json`)**: For personal tools and machine-wide access.\n- Check if the target config file already exists and parse its existing `mcpServers`.\n- **Upstream verification**: If configuring an unfamiliar or external MCP package, use `search_web` and `read_url_content` to fetch the authoritative npm\u002FPyPI documentation, required environment variables, and CLI argument schema from primary sources before drafting the JSON.\n\n### 2. Configure Server Entry\n\nDraft the server configuration object according to the selected transport:\n- Verify executable paths and command availability (`npx`, `uvx`, `node`, `python`).\n- Map all necessary arguments and environment variables.\n- Keep secrets safe: remind the developer to use local environment variables or private global configs if the project config is committed to public source control.\n\n### 3. Write and Merge\n\n- Read the target configuration file if it exists.\n- Preserve all existing server definitions under `mcpServers`.\n- Add or update the target server definition under its designated key name.\n- Format the JSON file cleanly with 2-space indentation.\n- Ensure the parent directory (`.agents\u002F` or `~\u002F.gemini\u002Fconfig\u002F`) exists before writing.\n\n### 4. Verification Step\n\nRun proactive diagnostics to ensure the configured MCP server will start cleanly:\n\n1. **Syntax and JSON check**: Ensure the output file is valid JSON with top-level `mcpServers` mapping.\n2. **Command \u002F Binary check**: Test if the command exists and is executable in the current environment (for example running `npx --version`, `python --version`, or verifying local script file paths).\n3. **Environment variable check**: Verify all required keys in the `env` block are populated with non-empty values.\n4. **Path & Permission check**:\n   - For filesystem servers: verify target paths exist and have appropriate read\u002Fwrite permissions.\n   - For database servers: verify database port and host are reachable.\n   - For git servers: verify the directory is a valid git repository.\n   - For remote SSE\u002FHTTP servers: verify the URL endpoint is reachable.\n\n### 5. Final Confirmation\n\nReport the setup outcome to the user:\n- Show the exact JSON configuration block that was written.\n- Specify the configuration path (`.agents\u002Fmcp_config.json` or `~\u002F.gemini\u002Fconfig\u002Fmcp_config.json`).\n- Mention how Antigravity will discover the new tools on next prompt or agent reload.\n",{"name":5,"description":7},"main","97b7a56459bd17362bf4f075d60d92c1ae6cce33","skills\u002Fengineering\u002Fsetup-mcp",0,"https:\u002F\u002Fgithub.com\u002Ffderuiter\u002Fagy-skills","https:\u002F\u002Ffderuiter.github.io\u002Fagy-skills\u002F","https:\u002F\u002Fgithub.com\u002Ffderuiter","Clinical Data Specialist at @Bright-Research \r\n\r\nInterests in Photogrammetry, Data Analytics + Pipelines, Mathematics, and AI\u002FML.\r\n\r\nPython, Rust, TS.","2026-08-29 02:26:25",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add fderuiter\u002Fagy-skills --skill setup-mcp",{"tool":39,"command":40},"bunx","bunx skills add fderuiter\u002Fagy-skills --skill setup-mcp",{"tool":42,"command":43},"pnpm","pnpm dlx skills add fderuiter\u002Fagy-skills --skill setup-mcp","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ffderuiter\u002Fagy-skills\u002Fblob\u002Fmain\u002Fskills\u002Fengineering\u002Fsetup-mcp\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7BK91P025C72NSC9NZTS4JF","writing-shape","Shape raw material into an article paragraph by paragraph, arguing format choices along the way.","https:\u002F\u002Fgithub.com\u002Ffderuiter\u002Fagy-skills\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fwriting-shape\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7BK908F7QPQST3FKHAAVE87","writing-fragments","Mine raw writing fragments with no structure yet, capturing ideas into a single quarry file.","https:\u002F\u002Fgithub.com\u002Ffderuiter\u002Fagy-skills\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fwriting-fragments\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7BK8YJEBD31HR3GTYATQ6ZA","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Ffderuiter\u002Fagy-skills\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7BK8WWERTYDTVVE95VMKZ2J","writing-beats","Assemble raw material into a narrative journey of beats, grounding concepts before leaning on them.","https:\u002F\u002Fgithub.com\u002Ffderuiter\u002Fagy-skills\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fwriting-beats\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7BK8VT41ZSQVB6TFM2KZRBZ","wait-what","Stop. That last message did not land: re-pitch it.","https:\u002F\u002Fgithub.com\u002Ffderuiter\u002Fagy-skills\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fwait-what\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7BK8T2V1J99DXH22Q304T4S","to-questionnaire","Turn a decision you can't fully answer into a questionnaire for someone else to fill in.","https:\u002F\u002Fgithub.com\u002Ffderuiter\u002Fagy-skills\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fto-questionnaire\u002FSKILL.md",[],[]]