Dianel555/DSkills / skills/context7
context7
VerifiedFetch current library and API documentation from Context7 when a coding answer needs authoritative, up-to-date examples or version-specific behavior.
Context7
Use the co-located Node CLI to search Context7 documentation through the v3 Search API. The v3 endpoint accepts a question and returns relevant snippets in one request. A library ID is optional.
Run the CLI
Resolve the actual directory containing this skill first. The CLI needs Node.js 18+ and no npm dependencies. Run it from that directory:
node ./context7-api.cjs search "How do I clean up a React effect?"
node ./context7-api.cjs search "How do I configure route handlers?" --library Next.js --version 15.4.0
node ./context7-api.cjs search "How do I stream a response?" --library Next.js --library OpenAI --language TypeScript
--library accepts a name or Context7 ID and may appear up to four times. --version requires at least one --library; with one library it is a strict filter, and with several it is a preference. --language is a preference. Pass the user's specific question as the query. Do not use a repo-relative path when this skill is installed elsewhere.
The old context <libraryId> <query> command remains an alias for search <query> --library <libraryId> so existing callers can migrate. It also uses v3.
Read the response
The CLI requests type=json and prints the raw codeSnippets[] and infoSnippets[], plus a normalized results[] array. Each normalized result has title, content, source, and libraryId. Use the snippet's source link when citing documentation. When a query has no matching documentation, all three arrays are empty.
The v3 REST endpoint returns plain text by default. Keep type=json when calling it directly if structured snippets are needed.
Authentication and errors
Set CONTEXT7_API_KEY in the environment or in a .env file next to the CLI. An environment variable takes precedence. Use .env.example as the template and get a key from context7.com/dashboard. Requests without a key are for testing and have low IP-based limits.
The CLI exits nonzero and writes errors to stderr for invalid arguments, network failures, invalid JSON, and API errors other than 404 no_documentation_found. For 429, wait for the rate limit before retrying. For other transient failures, retry once and report that current documentation could not be verified if it still fails.
The optional context7-fetcher can run the same command in an isolated worker when the runtime supports one. Direct CLI execution is the default.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 468k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 197k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |