菜单
Creates and improves MCP server definitions (a portable .mcp.json) for a plugin to the Advanced Skill Library Standard. Use when you need to add an MCP server to a plugin, author or extend .mcp.json, or wire the per-target mcpServers manifest pointer.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Creates and improves agentskills.io skills to the Advanced Skill Library Standard. Use when you need to author a new SKILL.md, scaffold a skill directory, or raise an existing skill's conformance and description quality.
Evaluates a skill or plugin against the Advanced Skill Library Standard across three modes, producing deterministic conformance findings and a tier, an opt-in behavioral pass, and a qualitative review. Use when you want to audit conformance, judge whether a skill behaves and triggers correctly, get a qualitative review, or see what blocks the next tier.
Converts a meeting transcript into a decision log. Use when the user asks to extract decisions, action items, or owners from a transcript.
Assesses an existing skills repository against the Advanced Skill Library Standard, produces a staged bring-to-conformance plan, and writes the minimal canonical manifest so the repo becomes gradeable. Use when adopting a foreign or ad-hoc skills repo, migrating a Claude-only plugin toward cross-agent conformance, or planning a Bronze-to-Silver upgrade path.
Builds and validates a plugin's release by computing the version, promoting the changelog, curating the release notes, and running the readiness gate, to the Advanced Skill Library Standard. Use when cutting a release, bumping the plugin version, updating the changelog or release notes, or checking release readiness.
Creates, triages, and prunes a plugin's two backlogs (new-component proposals and enhancements) to the Advanced Skill Library Standard. Use when capturing a new-component proposal through the why-gate, prioritizing backlog items, or removing stale or completed entries.
| name | askit-build-mcp |
| description | Creates and improves MCP server definitions (a portable .mcp.json) for a plugin to the Advanced Skill Library Standard. Use when you need to add an MCP server to a plugin, author or extend .mcp.json, or wire the per-target mcpServers manifest pointer. |
| metadata | {"version":"0.1.0","tier":"universal","audience":"advanced"} |
Author the plugin's MCP servers as one portable .mcp.json at the plugin root (the standard { "mcpServers": { ... } } format) and wire the per-target mcpServers manifest pointer. Two modes: create adds a server; improve fixes findings. MCP is Universal-tier: the server definition is portable and both Claude and Codex ingest a bundled .mcp.json referenced by the native manifest's mcpServers pointer (Standard sec 3.9). Authoring depth is in references/authoring-mcp.md. Follows the shared builder contract (../../docs/reference/builder-pattern.md).
When the user asks to add, scaffold, author, or improve an MCP server (tools, resources, or prompts via the Model Context Protocol) for a plugin.
stdio or http), the command plus args (stdio) or the url (http), and any secrets as an env-var NAME (never an inline value). Skip the interview if these are already in context..mcp.json: add the server under mcpServers. Copy templates/mcp.json if the file does not exist yet.library.json components.mcpServers as { name, version, tier, status }.node scripts/generators/gen-manifest.mjs <plugin-root> --write --target=all. Each native manifest gains "mcpServers": "./.mcp.json".node scripts/evaluate.mjs . --json and iterate to 0 errors (mcp-valid, the S3 components index, and the S6 per-target pointer).node scripts/evaluate.mjs . --json and read the report.command or url; a committed secret (mcp-valid) -> replace the inline value with an env-var reference or bearer_token_env_var; a missing pointer (S6) -> regenerate the manifests; an undeclared server (S3) -> add it to components.mcpServers. For any other finding, read its message and apply the fix it states.The root .mcp.json is the single authored source; the manifest pointers are generated, so never hand-edit a generated manifest. Secrets MUST be referenced from the environment, never committed (Standard sec 9). MCP is the one plugin-distributable component both agents ingest, and emission is just the manifest-pointer wiring (no per-type render engine, per the builder pattern).