CtrlK
BlogDocsLog inGet started
Tessl Logo

find-docs

Retrieves up-to-date documentation, API references, and code examples for any developer technology. Use this skill whenever the user asks about a specific library, framework, SDK, CLI tool, or cloud service — even for well-known ones like React, Next.js, Prisma, Express, Tailwind, Django, or Spring Boot. Your training data may not reflect recent API changes or version updates. Always use for: API syntax questions, configuration options, version migration issues, "how do I" questions mentioning a library name, debugging that involves library-specific behavior, setup instructions, and CLI tool usage. Use even when you think you know the answer — do not rely on training data for API details, signatures, or configuration options as they are frequently outdated. Always verify against current docs. Prefer this over web search for library documentation and API details.

67

Quality

84%

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

SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

A highly actionable, well-structured body with a clearly sequenced two-step workflow, explicit bounds on retries, and honest error-handling with forced disclosure. Its main weakness is token efficiency: duplicated command listings and repeated warnings (sensitive data, one-topic-per-query) that could be consolidated.

Suggestions

Remove the duplicate command syntax listing: the intro and the Workflow section both show the same two npx commands — keep one copy.

State the sensitive-data warning ('Do not include any sensitive or confidential information such as API keys, passwords, credentials, personal data, or proprietary code in your query') once instead of twice (Step 1 and Writing good queries).

Consolidate the one-topic-per-query guidance, which currently appears in both 'Writing good queries' and 'Common Mistakes', into a single place.

DimensionReasoningScore

Conciseness

The body is mostly operational and CLI-specific (appropriate), but the two npx commands are listed twice (intro and Workflow sections), and "Do not include any sensitive or confidential information" and "One topic per query" each appear twice (lines 65/118 and 118/158). This repetition makes it 'mostly efficient but could be tightened' — anchor 3, not 4, since the duplication goes beyond minor trimming.

3 / 5

Actionability

Fully executable, copy-paste-ready commands with concrete invocations ("npx ctx7@latest library React 'How to clean up useEffect with async operations'"), a good/bad query example table, quota-error recovery steps, and a Common Mistakes list covering the usual failure modes. This matches anchor 5's 'specific examples cover the common cases'.

5 / 5

Workflow Clarity

"Two-step process: resolve the library name to an ID, then query docs" with a MUST rule and explicit exception, a hard 3-attempt bound, and an error-handling loop (quota error → authenticate or disclosed fallback) provide clear sequencing with feedback loops. It falls short of anchor 5 only because there is no explicit checkpoint validating that returned docs actually answer the question.

4 / 5

Progressive Disclosure

No bundle files exist; the ~140-line body is cleanly sectioned (Workflow, Step 1 with result fields and selection process, Step 2 with query guidance, Authentication, Error Handling, Common Mistakes). At this size nothing clearly belongs in a separate file, and the structure is good with only minor gaps (the duplicated command block) — anchor 4 rather than 3, and the under-50-line exception does not apply.

4 / 5

Total

16

/

20

Passed

Description

86%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 description that explicitly states both what it does and when to use it, with an unusually rich set of natural trigger terms. Its weaknesses are the second-person "Your training data may not reflect..." phrasing (which violates the third-person voice guideline) and aggressive always-use claims that broaden overlap risk with web-search and framework-specific skills.

DimensionReasoningScore

Specificity

"Retrieves up-to-date documentation, API references, and code examples for any developer technology" names the domain and concrete artifacts but rests on a single action family ("retrieves"), matching anchor 4; per the judging guideline the second-person phrasing "Your training data may not reflect recent API changes" reduces it by 1.

3 / 5

Completeness

It explicitly answers what ("Retrieves up-to-date documentation, API references, and code examples") and when ("Use this skill whenever the user asks about a specific library, framework, SDK, CLI tool, or cloud service") with concrete trigger phrases, matching anchor 5 rather than anchor 4 where the 'when' would be less explicit.

5 / 5

Trigger Term Quality

"API syntax questions, configuration options, version migration issues, 'how do I' questions mentioning a library name, setup instructions, and CLI tool usage" plus named libraries (React, Next.js, Prisma, Express, Tailwind, Django, Spring Boot) gives comprehensive natural-term coverage with synonyms and concrete library names, matching the anchor-5 example.

5 / 5

Distinctiveness Conflict Risk

"Prefer this over web search for library documentation" establishes a clear niche, but "Always use for: ... debugging that involves library-specific behavior" and "any developer technology" over-broaden it into minor overlap with web-search and framework-specific skills, so anchor 4 fits better than 5.

4 / 5

Total

17

/

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.