📚AI 知识库 MCP（Context7 / 文档检索）

Use when researching React APIs or concepts for documentation. Use when you need authoritative usage examples, caveats, warnings, or errors for a React feature.

Python code style, linting, formatting, naming conventions, and documentation standards. Use when writing new code, reviewing style, configuring linters, writing docstrings, or establishing project standards.

Help users write effective specs and design documents. Use when someone is creating technical specs, feature specs, design docs, or trying to communicate product requirements to engineering and design teams.

Use when writing prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Applies Strunk's timeless rules for clearer, stronger, more professional writing.

Expert knowledge for Next.js 13+ App Router architectureUse when "next.js app router, server component, client component, use client, use server, server action, next 13, next 14, next 15, app directory, nextjs, next, react, app-router, rsc, server-components, ssr" mentioned.

TypeScript development best practices, code quality tools, and documentation templates. Activated when working with .ts, .tsx files or TypeScript projects.

Documentation for the FastAPI backend, endpoints, and dependency injection.

Design and implement RESTful API endpoints following REST principles, HTTP standards, and resource-based URL conventions. Use this skill when creating or modifying API endpoints, routes, controllers, request handlers, or API documentation. Apply when working with REST API design, API versioning, HTTP methods (GET, POST, PUT, PATCH, DELETE), URL structure, query parameters, response formatting, status codes, rate limiting, or API middleware. Use when building web services, microservices, or any backend code that exposes HTTP endpoints for client consumption.

Write effective JSDoc comments for TypeScript code. Provides guidance on documentation format, strategic placement, best practices, and when to document versus when to keep code self-documenting. Helps maintain code clarity and IDE support.

Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.

Create API handoff documentation for frontend developers. Use when backend work is complete and needs to be documented for frontend integration, or user says 'create handoff', 'document API', 'frontend handoff', or 'API documentation'.

Create and evolve design systems with design tokens, component architecture, accessibility guidelines, and documentation templates. Ensures consistent, scalable, and accessible UI across products.

Upload markdown (including docmgr ticket docs) to a reMarkable device as PDF via a local uploader script, with a safe dry-run and optional mirroring of ticket structure. Use when the user asks to send docs to reMarkable, export markdown to PDF for reMarkable, or troubleshoot rmapi/pandoc/xelatex.

Use the docmgr CLI to manage ticketed docs (create tickets, add docs, relate code files with file-note, update changelog, and search). Use when the user asks how to use docmgr, wants a docmgr command sequence, or needs docmgr best practices (file-note, quoting, doctor).

Review documentation changes for compliance with the Metabase writing style guide. Use when reviewing pull requests, files, or diffs containing documentation markdown files.

Generate comprehensive, accurate API documentation from source code. Use when creating or updating API documentation, generating OpenAPI specs, or when users mention API docs, endpoints, or documentation.

Offloading tasks with a well-defined scope to sub-agents, for instance to use a sub-agent to implement a set of specs. Use this skill whenever a task should not need a broad knowledge of the whole project

Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; use OpenAI docs MCP tools for non-Codex docs questions, use the Codex manual helper first for broad Codex self-knowledge, and restrict fallback browsing to official OpenAI domains.

Turn Notion specs into implementation plans, tasks, and progress tracking; use when implementing PRDs/feature specs and creating Notion plans + tasks from them.

Research across Notion and synthesize into structured documentation; use when gathering info from multiple Notion sources to produce briefs, comparisons, or reports with citations.

Prepare meeting materials with Notion context and Codex research; use when gathering context, drafting agendas/pre-reads, and tailoring materials to attendees.

Capture conversations and decisions into structured Notion pages; use when turning chats/notes into wiki entries, how-tos, decisions, or FAQs with proper linking.

Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a companion skill.

Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply Apps SDK metadata or CSP or domain settings, or produce a docs-aligned project scaffold. Prefer a docs-first workflow by invoking the openai-docs skill or OpenAI developer docs MCP tools before generating code.

Review docs/prose for Writing Guidelines compliance. Use when asked to "review my docs", "check writing style", "audit prose", "review docs voice and tone", or "check this page against the writing handbook".

Use for Vercel cost and performance optimization on deployed projects, especially Next.js, SvelteKit, Nuxt, and limited Astro apps. Collect Vercel metrics, usage, project config, and code scan results first; investigate only metric-backed candidates; produce ranked recommendations grounded in verified files and version-aware Vercel/framework docs. Trigger for Vercel bill reduction, slow or expensive routes, caching opportunities, Function Invocations, Build Minutes, Fast Data Transfer, Core Web Vitals, Bot Management, Fluid compute, or cost breakdown requests.