CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

context7-auto-research

Automatically fetch latest library/framework documentation for Claude Code via Context7 API

45

Quality

56%

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 ./cli-tool/components/skills/ai-research/context7-auto-research/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

43%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 is token-efficient and cleanly sectioned, but it functions as a README for an external repository rather than a skill: it provides almost no executable guidance for the skill's core capability, and it delegates examples and troubleshooting to an external URL instead of carrying them in bundle files.

Suggestions

Replace the vague steps with concrete, executable instructions for the skill's core workflow — how Context7 is invoked, an example query/response, and the API-key environment variable names.

Move examples and troubleshooting guidance into local bundle files (e.g. references/examples.md, references/troubleshooting.md) with clearly signaled one-level-deep links, instead of pointing to the external GitHub repo.

Cut the duplicated Overview line and the filler bullets ("seamless integration", "Use naturally") so every remaining token carries actionable content.

DimensionReasoningScore

Conciseness

The body is lean — no padding, no explanations of concepts Claude already knows — but the "Overview" section repeats the frontmatter description verbatim and "Use the skill's auto-trigger feature for seamless integration" is marketing filler that earns no tokens, so it falls just short of anchor 5's 'every token earns its place'.

4 / 5

Actionability

Only the install command ("npx skills add -g BenedictKing/context7-auto-research") is copy-paste executable; the rest are high-level hints — "Configure API key (optional, see GitHub repo for details)" and "Use naturally in Claude Code conversations" give no concrete steps or examples of the skill's actual operation, matching anchor 2's 'minimal concrete guidance; missing the specific steps to execute'.

2 / 5

Workflow Clarity

The Step-by-Step Guide is a rough three-step sequence (install → configure key → use naturally) but the steps are poorly defined — 'see GitHub repo for details' and 'use naturally' leave the user with no concrete actions or checkpoints — matching anchor 2 rather than anchor 3's adequately listed steps.

2 / 5

Progressive Disclosure

Sections are well-organized for a short skill, but there is no bundle at all (references/, scripts/, assets/ are absent) and essential content — examples and troubleshooting — is deferred to an external GitHub URL ("See [GitHub Repository](...) for examples", "See the GitHub repository for troubleshooting guides") instead of one-level-deep bundle files, matching anchor 3's 'references present but not clearly signaled / could be better organized'.

3 / 5

Total

11

/

20

Passed

Description

50%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 communicates a single clear capability with a named mechanism, but is not a complete skill description: it lacks any 'when to use' trigger clause, natural-language synonyms users would actually say, and distinctive triggers that would separate it from similar documentation-fetching/search skills.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks about a library/framework's current API, or mentions outdated docs, Context7, or needing up-to-date documentation for React, Next.js, Prisma, etc."

Include natural trigger synonyms users actually say — "docs", "API reference", "up-to-date", "latest version" — and concrete library examples.

State one or two more concrete actions (e.g. resolves a library name to its Context7 ID, retrieves targeted doc pages) to distinguish the capability from generic web-search skills.

DimensionReasoningScore

Specificity

"Automatically fetch latest library/framework documentation ... via Context7 API" names the domain (library/framework docs), one concrete action ("fetch latest documentation"), and the mechanism (Context7 API), but coverage stops at a single action — not the multiple specific actions of anchor 4, yet well above the domain-only vagueness of anchor 2.

3 / 5

Completeness

The 'what' is clear (fetch latest library/framework documentation via Context7 API) but the 'when' is entirely absent — no 'Use when...' or equivalent trigger clause — which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

"library/framework documentation" are relevant keywords a user might say, but common variations are missing ("docs", "API reference", "up-to-date", specific library names), and there is no natural trigger phrasing — matching anchor 3's 'some relevant keywords but missing common variations or synonyms' rather than anchor 4's good coverage.

3 / 5

Distinctiveness Conflict Risk

"Context7 API" carves out a specific niche, but the generic "library/framework documentation" trigger space overlaps with the related web-search skills the body itself lists (tavily-web, exa-search), so it could still trigger for the wrong skill — anchor 3 rather than anchor 4's 'minor overlap risk'.

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

davila7/claude-code-templates

Path

cli-tool/components/skills/ai-research/context7-auto-research/SKILL.md

Revision

e7d17f9

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill