CtrlK
BlogDocsLog inGet started
Tessl Logo

context7-mcp

Fetches current, version-specific library documentation and code examples through the Context7 MCP server. Use whenever the user asks about a library, framework, SDK, API, CLI tool, or cloud service, including API syntax, configuration, setup instructions, version migration, CLI usage, and library-specific debugging. Use when generating code that calls a third-party library, and when the user names a version such as Next.js 15 or React 19. Use even for well-known libraries like React, Vue, Next.js, Prisma, Supabase, Express, Tailwind, Django, and Spring Boot, because training data may not reflect recent changes. Prefer this over web search for library documentation. Do not use it for refactoring, writing scripts from scratch, debugging business logic, code review, or general programming concepts, or when the user has already supplied the relevant documentation.

69

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a clear, actionable, well-structured workflow for fetching library documentation via Context7, with concrete tool names and parameters and a sensible four-step sequence. Minor redundancy with the frontmatter and the lack of a full call-syntax example or error-recovery guidance prevent the actionability and conciseness dimensions from reaching the top anchor.

Suggestions

Remove the opening line that restates the frontmatter description, and consolidate the "one topic per query" guidance so it appears in only one place to tighten conciseness.

Add a concrete example showing the full tool-call syntax (e.g., a resolve-library-id followed by a query-docs call with sample arguments) to make the guidance copy-paste ready.

Add a brief validation/error-recovery note (e.g., what to do if resolution returns no good match or query-docs returns shallow results) to push workflow clarity toward the top anchor.

DimensionReasoningScore

Conciseness

The body is mostly lean and assumes Claude's competence, but the opening line ("use Context7 to fetch current documentation instead of relying on training data") restates the frontmatter and the "one topic per query" guidance is repeated across Step 3 and Guidelines, keeping it just below the fully lean score-5 anchor.

4 / 5

Actionability

It names the exact MCP tools (resolve-library-id, query-docs) with their parameters (libraryName, query, libraryId) and a concrete example ID ("/vercel/next.js"), giving mostly executable guidance; the minor gap is that no full call-syntax example is shown, so it does not reach the copy-paste-ready score-5 anchor.

4 / 5

Workflow Clarity

A clear four-step sequence (resolve → select → fetch → use) with selection criteria as a soft checkpoint; because the operation is read-only doc fetching, the destructive/batch validation cap does not apply, but the absence of explicit validation or error-recovery feedback loops keeps it below the score-5 anchor.

4 / 5

Progressive Disclosure

No bundle files exist and none are needed; the body is a single well-organized file with clear section headers (When to Use, How to Fetch with numbered subsections, Guidelines), satisfying the simple-skill exception for well-structured content without external references.

5 / 5

Total

17

/

20

Passed

Description

90%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-targeted description that clearly states what the skill does and when to use it, with rich natural trigger terms and explicit negative boundaries. The only weaker dimension is specificity, since the skill is fundamentally a single fetch action rather than a portfolio of distinct capabilities.

DimensionReasoningScore

Specificity

The description names the domain and one to two concrete actions ("Fetches current, version-specific library documentation and code examples"), but the core capability is a single fetch action rather than a comprehensive list of distinct actions, matching the score-3 anchor rather than the multi-action score-4/5 anchors.

3 / 5

Completeness

It explicitly answers both "what" (fetches version-specific library documentation and code examples via Context7 MCP) and "when" ("Use whenever the user asks about a library, framework, SDK, API, CLI tool, or cloud service...") with concrete trigger phrases, plus negative-trigger guidance.

5 / 5

Trigger Term Quality

It offers comprehensive natural-term coverage—"library, framework, SDK, API, CLI tool, cloud service" plus many named examples (React, Vue, Next.js, Prisma, Supabase, Express, Tailwind, Django, Spring Boot) and version phrases like "Next.js 15 or React 19"—matching the comprehensive-synonyms anchor.

5 / 5

Distinctiveness Conflict Risk

It carves a clear niche (library documentation via the Context7 MCP server) with distinct triggers and an explicit "Do not use it for..." boundary list, minimizing overlap with general coding or web-search skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
upstash/context7
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.