documentation-lookup

Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React, Next.js, Prisma).

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.cursor/skills/documentation-lookup/SKILL.md

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-sequenced MCP workflow with concrete tool parameters, a hard ordering constraint, and a call-budget fallback. The main drag is token redundancy — instructions repeated across Core Concepts, steps, Best Practices, and three near-duplicate examples — plus a missing error path for failed library resolution.

Suggestions

Consolidate the 'always resolve the library ID first' rule and the selection criteria so each is stated once; drop the Best Practices bullets that restate Step 2/3 guidance and keep only the unique ones (e.g., the secrets-redaction note).

Reduce the three near-identical Examples to one fully worked example and one-line variations for the others, saving the token budget.

Add a brief error-recovery step: what to do when resolve-library-id returns no good match or query-docs returns irrelevant snippets (e.g., refine the query once, then fall back to training data with a stated caveat).

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but has real duplication: "always call resolve-library-id first" is stated in Core Concepts and again in Step 1, the Best Practices bullets ("Be specific", "Version awareness", "Prefer official sources") restate Step 2/3 guidance, and three near-identical worked examples repeat the same flow. This fits anchor 3 (could be tightened) rather than anchor 4's 'minor instances' of over-explanation.	3 / 5
Actionability	Guidance is fully executable: exact MCP tool names, parameter names (libraryName, query, libraryId), the library ID format (/org/project), and worked example calls with concrete values for the common cases. No gaps between the instruction and what to actually invoke, matching anchor 5.	5 / 5
Workflow Clarity	The 4-step sequence is clearly ordered with an explicit ordering constraint (resolve before query) and a budget checkpoint ("do not call... more than 3 times per question. If the answer is unclear... state the uncertainty"), which fits anchor 4. It falls short of anchor 5 because there is no error-recovery guidance for a failed or empty resolution result.	4 / 5
Progressive Disclosure	The body is well organized into clear sections (Core Concepts, When to use, How it works, Examples, Best Practices) with no external references needed, fitting anchor 4's good structure. The under-50-line simple-skill exception does not apply at roughly 85 body lines, and the redundant Examples section could be condensed.	4 / 5
	Total	16 / 20 Passed

Description

78%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 clearly and explicitly covers both what the skill does and when it activates, with good natural trigger phrases and named frameworks. Its main weaknesses are a thin action list (one generic "use docs" action) and slightly broad triggers that could overlap with general library-help skills.

Dimension	Reasoning	Score
Specificity	The description names the domain and mechanism ("Use up-to-date library and framework docs via Context7 MCP instead of training data") but states only one generic action; it does not list concrete operations like resolving library IDs or querying docs. It matches anchor 3 (domain plus 1-2 concrete actions, not comprehensive) rather than anchor 4, which requires several specific actions.	3 / 5
Completeness	It explicitly answers both what ("Use up-to-date library and framework docs via Context7 MCP instead of training data") and when ("Activates for setup questions, API references, code examples, or when the user names a framework") with concrete trigger phrases, matching anchor 5. It is not anchor 4 because the 'when' clause is specific and enumerated rather than merely adequate.	5 / 5
Trigger Term Quality	Triggers include natural phrases users would say — "setup questions, API references, code examples" — plus concrete framework names (React, Next.js, Prisma). Coverage is good but misses common variations such as "documentation" or "how do I use X", so it fits anchor 4 rather than the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	The Context7 docs-lookup niche is distinct, but the broad triggers "setup questions" and "code examples" create minor overlap risk with general library/coding skills. This fits anchor 4 (mostly distinct, minor overlap) rather than anchor 5's minimal-conflict profile.	4 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: .cursor/skills/documentation-lookup/SKILL.md
Commit: c70874f

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.