eddmann/agent-toolkit/context7

Claude Code and agent skill by eddmann/agent-toolkit

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Use when looking up library or framework documentation and version-specific API examples.

Install

npx vskill@latest install eddmann/agent-toolkit/context7

SKILL.md

Context7

Resolve the library and retrieve documentation relevant to the user's question. Check the project's installed version when API compatibility matters; do not silently substitute latest.

Lookup

Set library and question to the requested package and topic. Use a configured key without printing it; public access may be limited or rejected. These examples use Bash arrays.

bash
auth=()
if [ -n "${CONTEXT7_API_KEY:-}" ]; then
auth=(-H "Authorization: Bearer $CONTEXT7_API_KEY")
fi
curl --silent --show-error --fail-with-body --max-time 30 --get \
"${auth[@]}" 'https://context7.com/api/v2/libs/search' \
--data-urlencode "libraryName=$library" --data-urlencode "query=$question"

Inspect the results and select the matching library/source, not merely the first result. Set library_id to its returned ID. When available, append a listed version as /<version> to match the project; otherwise state that exact-version coverage is unavailable.

bash
curl --silent --show-error --fail-with-body --max-time 30 --get \
"${auth[@]}" 'https://context7.com/api/v2/context' \
--data-urlencode "libraryId=$library_id" --data-urlencode "query=$question" \
--data-urlencode 'type=txt'

Inspect exit status and response before using the result. Report authentication, access, missing-library or unavailable-version errors accurately. For rate limits, honor Retry-After with a bounded retry; do not repeatedly retry unchanged authentication failures. A pending or empty result is not documentation. If unavailable, use the library's official docs and state that fallback. See the API guide for response details.

Answer

Summarize the relevant guidance and cite source URLs returned with the snippets. Identify the version covered and any mismatch. Adapt examples to the project's stack; documentation examples do not prove that code runs in the project. Distinguish retrieved guidance from your own inference.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/eddmann/agent-toolkit/context7/badge)](https://verified-skill.com/skills/eddmann/agent-toolkit/context7)

Something wrong with this skill or its page? Tell us.