Skip to content
Back to search

context7

SkillWorks with Claude CodeGitHub

Fetch up-to-date library documentation via Context7 REST API

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/netresearch/context7-skill with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/netresearch/context7-skill'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/netresearch-context7-skill/badge.svg)](/listings/netresearch-context7-skill)

HTML

<a href="/listings/netresearch-context7-skill"><img src="/api/listings/netresearch-context7-skill/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Marketplace (Recommended)

Add the [Netresearch marketplace](https://github.com/netresearch/claude-code-marketplace) once, then browse and install skills:

# Claude Code
/plugin marketplace add netresearch/claude-code-marketplace
/plugin install context7@netresearch-claude-code-marketplace

Without a marketplace

Since Claude Code 2.1.157 a plugin directory under your personal skills directory loads on its own:

mkdir -p ~/.claude/skills
git clone https://github.com/netresearch/context7-skill.git \
  ~/.claude/skills/context7

It loads as `context7@skills-dir` on the next session. Update with `git -C ~/.claude/skills/context7 pull` and start a new session; remove it by deleting the directory. This route has no `claude plugin update`.

npx ([skills.sh](https://skills.sh))

Install with any [Agent Skills](https://agentskills.io)-compatible agent:

npx skills add https://github.com/netresearch/context7-skill --skill context7

Download Release

Download the [latest release](https://github.com/netresearch/context7-skill/releases/latest) and extract to your agent's skills directory.

Git Clone

git clone https://github.com/netresearch/context7-skill.git

Composer (PHP Projects)

composer require netresearch/context7-skill

Requires [netresearch/composer-agent-skill-plugin](https://github.com/netresearch/composer-agent-skill-plugin).

npm (Node Projects)

npm install --save-dev \
  @netresearch/agent-skill-coordinator \
  github:netresearch/context7-skill

Requires [@netresearch/agent-skill-coordinator](https://github.com/netresearch/node-agent-skill-coordinator), which discovers the skill in `node_modules` and registers it in `AGENTS.md` via a `postinstall` hook. For pnpm, also allowlist the coordinator's postinstall:

{
  "pnpm": {
    "onlyBuiltDependencies": ["@netresearch/agent-skill-coordinator"]
  }
}

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/plugin.json · Manifest · 18 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "context7",
  3. "version": "1.7.3",
  4. "description": "Fetch up-to-date library documentation via Context7 REST API",
  5. "author": {
  6. "name": "Netresearch DTT GmbH",
  7. "url": "https://www.netresearch.de"
  8. },
  9. "repository": "https://github.com/netresearch/context7-skill",
  10. "license": "(MIT AND CC-BY-SA-4.0)",
  11. "support": {
  12. "issues": "https://github.com/netresearch/context7-skill/issues",
  13. "source": "https://github.com/netresearch/context7-skill"
  14. },
  15. "skills": [
  16. "./skills/context7"
  17. ]
  18. }
README.md · README · 197 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <!-- SPDX-License-Identifier: CC-BY-SA-4.0 -->
  2. <!-- SPDX-FileCopyrightText: Netresearch DTT GmbH -->
  3. # Context7 Documentation Lookup Skill
  4. Fetch up-to-date library documentation via Context7 REST API. Lightweight alternative to Context7 MCP with no persistent context overhead.
  5. ## Features
  6. - **No MCP Overhead** - Uses REST API directly, no tool schemas consuming context
  7. - **Current Documentation** - Fetches live docs from Context7's curated database
  8. - **Topic Filtering** - Focus on specific areas (hooks, routing, middleware, etc.)
  9. - **50+ Libraries** - React, Next.js, Vue, Express, Prisma, and more
  10. ## Installation
  11. ### Marketplace (Recommended)
  12. Add the [Netresearch marketplace](https://github.com/netresearch/claude-code-marketplace) once, then browse and install skills:
  13. ```bash
  14. # Claude Code
  15. /plugin marketplace add netresearch/claude-code-marketplace
  16. /plugin install context7@netresearch-claude-code-marketplace
  17. ```
  18. ### Without a marketplace
  19. Since Claude Code 2.1.157 a plugin directory under your personal skills directory loads on its own:
  20. ```bash
  21. mkdir -p ~/.claude/skills
  22. git clone https://github.com/netresearch/context7-skill.git \
  23. ~/.claude/skills/context7
  24. ```
  25. It loads as `context7@skills-dir` on the next session. Update with `git -C ~/.claude/skills/context7 pull` and start a new session; remove it by deleting the directory. This route has no `claude plugin update`.
  26. ### npx ([skills.sh](https://skills.sh))
  27. Install with any [Agent Skills](https://agentskills.io)-compatible agent:
  28. ```bash
  29. npx skills add https://github.com/netresearch/context7-skill --skill context7
  30. ```
  31. ### Download Release
  32. Download the [latest release](https://github.com/netresearch/context7-skill/releases/latest) and extract to your agent's skills directory.
  33. ### Git Clone
  34. ```bash
  35. git clone https://github.com/netresearch/context7-skill.git
  36. ```
  37. ### Composer (PHP Projects)
  38. ```bash
  39. composer require netresearch/context7-skill
  40. ```
  41. Requires [netresearch/composer-agent-skill-plugin](https://github.com/netresearch/composer-agent-skill-plugin).
  42. ### npm (Node Projects)
  43. ```bash
  44. npm install --save-dev \
  45. @netresearch/agent-skill-coordinator \
  46. github:netresearch/context7-skill
  47. ```
  48. Requires [@netresearch/agent-skill-coordinator](https://github.com/netresearch/node-agent-skill-coordinator), which discovers the skill in `node_modules` and registers it in `AGENTS.md` via a `postinstall` hook. For pnpm, also allowlist the coordinator's postinstall:
  49. ```json
  50. {
  51. "pnpm": {
  52. "onlyBuiltDependencies": ["@netresearch/agent-skill-coordinator"]
  53. }
  54. }
  55. ```
  56. ## Usage
  57. The skill triggers on keywords like:
  58. - "how do I use [library]"
  59. - "what's the API for [library]"
  60. - "[library] documentation"
  61. - "show me [library] patterns"
  62. ### Example Prompts
  63. ```
  64. "How do I use React hooks?"
  65. "What's the Next.js App Router API?"
  66. "Show me Prisma query patterns"
  67. "Express middleware documentation"
  68. ```
  69. ### Manual Script Usage
  70. ```bash
  71. # Search for a library ID
  72. scripts/context7.sh search "prisma"
  73. # Fetch documentation with topic
  74. scripts/context7.sh docs "/prisma/prisma" "queries"
  75. ```
  76. ## Structure
  77. ```
  78. context7/
  79. ├── SKILL.md # AI instructions
  80. ├── README.md # This file
  81. ├── LICENSE-MIT # Code license (MIT)
  82. ├── LICENSE-CC-BY-SA-4.0 # Content license (CC-BY-SA-4.0)
  83. ├── scripts/ # Automation scripts
  84. │ └── context7.sh # REST API wrapper
  85. └── .github/
  86. └── workflows/
  87. └── release.yml # Release packaging
  88. ```
  89. ## Why Use This Over Context7 MCP?
  90. | Aspect | MCP Server | This Skill |
  91. |--------|------------|------------|
  92. | Context cost | ~500-2000 tokens always | ~100 tokens on-demand |
  93. | Tool schemas | Always in context | None |
  94. | Invocation | Model decides | Model decides |
  95. | API access | Via MCP protocol | Direct REST API |
  96. Best for: Users who occasionally need library docs but don't want persistent context overhead.
  97. ## Environment Variables
  98. | Variable | Required | Description |
  99. |----------|----------|-------------|
  100. | `CONTEXT7_API_KEY` | No | API key for higher rate limits |
  101. ## Contributing
  102. Contributions welcome! Please submit PRs for:
  103. - Adding common library IDs
  104. - Improving script error handling
  105. - Documentation updates
  106. ### Tests
  107. The behavioural tests live in `tests/` and need only bash, jq, git and python3 (`check-plugin-version.sh` reads `plugin.json` with it):
  108. ```bash
  109. bash tests/context7.sh # skills/context7/scripts/context7.sh
  110. bash tests/check-plugin-version.sh # Build/Scripts/check-plugin-version.sh
  111. ```
  112. - `tests/context7.sh` puts a fake `curl` first on `PATH`, so no request reaches the Context7 API. It checks the usage and argument errors, the request URL each command builds (leading slash stripped, mode in the path, query and topic percent-encoded), that the `Authorization` header is sent only when `CONTEXT7_API_KEY` is set and reaches `curl` on standard input rather than as an argument, and how search results and API errors are printed.
  113. - `tests/check-plugin-version.sh` builds throwaway git repositories and checks that a semver tag at `HEAD` must match the version in `.claude-plugin/plugin.json`.
  114. Each check prints `ok` or `FAIL`; a `FAIL` line is followed by the exit code, the output and, for `context7.sh`, the arguments the fake `curl` received. A script exits 1 when any check failed. In CI, the Skill Tests workflow (`.github/workflows/tests.yml`) runs every `tests/**/*.sh` on each pull request and on pushes to `main`.
  115. A pull request that adds or changes behaviour in a shipped script adds or updates a check in `tests/` that fails without the change.
  116. ## Governance and policies
  117. This repository follows the Netresearch organisation policies:
  118. - [Governance](https://github.com/netresearch/.github/blob/main/GOVERNANCE.md): ownership, roles, how decisions are made and disputes resolved, and continuity.
  119. - [Roadmap](https://github.com/netresearch/.github/blob/main/ROADMAP.md): planned and explicitly excluded work for the coming year.
  120. - [Handling of dependency and code analysis findings](https://github.com/netresearch/.github/blob/main/SECURITY.md#handling-of-dependency-and-code-analysis-findings): thresholds, deadlines and the exception process for dependency (SCA) and static analysis (SAST) findings.
  121. - [Secret management](https://github.com/netresearch/.github/blob/main/SECURITY.md#secret-management): how CI and release credentials are stored, accessed and rotated.
  122. - [Access roster](https://github.com/netresearch/.github/blob/main/docs/access-roster.md): who holds administrative access to this repository and the organisation.
  123. The security assurance case for this skill (threat model, trust boundaries, countermeasures and limits) is in [docs/SECURITY-ASSURANCE.md](docs/SECURITY-ASSURANCE.md).
  124. Checks that run on pull requests in this repository:
  125. - Every pull request: Skill Validation (`lint.yml`: skill structure, markdownlint, yamllint, actionlint, JSON syntax, ShellCheck, ruff), Eval Validation (`eval-validate.yml`) and Skill Tests (`tests.yml`).
  126. - Pull requests to `main`: `security.yml` with Betterleaks (secret scanning), zizmor (workflow static analysis), dependency review (fails on vulnerabilities of severity high or above), Composer Audit and Opengrep SAST (failure threshold: [organisation SAST rule](https://github.com/netresearch/.github/blob/main/SECURITY.md#static-analysis-sast)); Harness Verification (`harness-verify.yml`) and Template Drift (`check-template-drift.yml`).
  127. ## License
  128. This project uses split licensing:
  129. - **Code** (scripts, workflows, configs): [MIT](LICENSE-MIT)
  130. - **Content** (skill definitions, documentation, references): [CC-BY-SA-4.0](LICENSE-CC-BY-SA-4.0)
  131. See the individual license files for full terms.
  132. ## Credits
  133. - Context7 API by [Upstash](https://upstash.com/)
  134. - Skill developed by [Netresearch DTT GmbH](https://www.netresearch.de/)
  135. ---
  136. **Made with love for Open Source by [Netresearch](https://www.netresearch.de/)**

Version history

  • v1.7.310/18/2026

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.