CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

context7-mcp

This skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/context7-mcp/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 body provides a clear, executable four-step workflow with concrete MCP tool names and parameters. Its main weakness is redundancy: the Guidelines and When-to-Use sections repeat content already covered in the steps and the description.

Suggestions

Merge the "Version awareness" and "One topic per query" guideline bullets into their corresponding steps (Step 2 and Step 3) so each rule appears exactly once.

Trim the "When to Use This Skill" section to a single line or remove it, since it duplicates the frontmatter description.

Add a brief fallback to Step 2 for when resolution returns no good match (e.g., retry with a more specific libraryName, or answer from training data with a caveat).

DimensionReasoningScore

Conciseness

"Version awareness" and "One topic per query" in the Guidelines section restate the version and multi-concept guidance already given in Steps 2 and 3, and "When to Use This Skill" duplicates the frontmatter description. Mostly efficient with no concept padding, but the duplicated rules mean it could be noticeably tightened.

3 / 5

Actionability

Gives concrete tool names (`resolve-library-id`, `query-docs`) with explicit parameters (`libraryName`, `query`, `libraryId`) and an example ID (`/vercel/next.js`). Minor gaps: no example call payload and no description of the resolution result fields needed for Step 2's selection criteria.

4 / 5

Workflow Clarity

A clear four-step sequence (resolve → select → fetch → use) with concrete selection criteria (exact match, benchmark scores, version-specific IDs). This is a read-only lookup so no validation cap applies, but there is no fallback guidance for when resolution returns no good match.

4 / 5

Progressive Disclosure

A compact (~50 line) single-file skill with no bundle files and no need for external references, organized into clear sections (When to Use, How to Fetch Documentation, Guidelines). Per the simple-skill note, well-organized sections alone merit full credit here.

5 / 5

Total

16

/

20

Passed

Description

48%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.

The description has strong, explicit trigger guidance with concrete framework names, but it omits any statement of what the skill actually does, leaving the 'what' half of completeness unanswered. Trigger terms are good though missing the most natural synonyms like "docs" or "documentation".

Suggestions

Open with a 'what' clause stating the skill's function, e.g. "Fetches up-to-date documentation for libraries and frameworks via Context7 instead of relying on training data", before the 'when' clause.

Add natural trigger synonyms users actually say, such as "docs", "documentation", or "SDK", to the keyword coverage.

Narrow the "code generation involving libraries" trigger to cases where current documentation is genuinely needed, reducing overlap with general coding assistance.

DimensionReasoningScore

Specificity

"asks about libraries, frameworks, API references, or needs code examples" names the domain and trigger scenarios with named frameworks (React, Vue, Next.js, Prisma, Supabase), but the skill's own actions (fetching current documentation, resolving library IDs) are never stated — matching "names domain and 1-2 concrete actions, but not comprehensive" rather than anchor 4's several specific actions.

3 / 5

Completeness

The 'when' is explicit and detailed ("Activates for setup questions, code generation involving libraries, or mentions of specific frameworks"), but the description never states what the skill does — only 'when' is present without 'what', matching anchor 2 exactly. The actual capability (fetch current documentation via Context7) appears only in the body, and scoring only what is explicitly stated forbids inferring it.

2 / 5

Trigger Term Quality

Good natural keyword coverage: "setup questions", "code generation", "API references", and concrete framework names (React, Vue, Next.js, Prisma, Supabase). Not anchor 5 because the most natural synonyms for this skill — "docs" / "documentation" / "SDK" — are missing.

4 / 5

Distinctiveness Conflict Risk

The named frameworks give it a recognizable niche, but "code generation involving libraries" is broad — most code generation involves a library — so it could fire on ordinary coding requests that need no documentation lookup, leaving overlap with general coding skills as anchor 3 describes.

3 / 5

Total

12

/

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

Path

skills/context7-mcp/SKILL.md

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.