Name: documentation-lookup
Rating: 62.4 (1 reviews)
Author: affaan-m

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

73%

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 ./.agents/skills/documentation-lookup/SKILL.md

The canonical home for this skill is documentation-lookup in affaan-m/ECC

Quality

Content

67%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 clearly sequenced, actionable workflow with concrete MCP tool parameters and an explicit call-limit checkpoint. Its main weakness is conciseness: the Core Concepts and Examples sections repeat content already conveyed in the intro and steps.

Suggestions

Condense the three Examples into one fully worked example plus a short table of libraryName/libraryId pairs, since each example currently restates the identical 4-step flow.

Trim the Core Concepts section to avoid re-explaining Context7 and the two tools already described in the intro and Step 1-3 headings.

Add a brief error-recovery branch for Step 1 (e.g. what to do when resolve-library-id returns no strong match) to strengthen the workflow's feedback loop.

Dimension	Reasoning	Score
Conciseness	The Core Concepts section re-explains Context7/resolve-library-id/query-docs already covered in the intro, and the three Examples restate the same 4-step flow verbatim with only library names swapped — noticeable redundancy that could be tightened, fitting anchor 3.	3 / 5
Actionability	Quotes concrete MCP tool names with parameters ('libraryName', 'query', 'libraryId') and example values like '/vercel/next.js', giving mostly executable guidance with minor gaps (prose-numbered rather than literal tool-call syntax), matching anchor 4.	4 / 5
Workflow Clarity	Steps 1-4 are clearly sequenced (resolve → select → fetch → use) with an explicit 3-call checkpoint ('If the answer is unclear after 3 calls, state the uncertainty'), but error-recovery guidance for failed resolutions is thin, fitting anchor 4.	4 / 5
Progressive Disclosure	No bundle files exist and the body is self-contained with clear section headers (Core Concepts, When to use, How it works, Examples, Best Practices) and no nested references; minor redundancy between sections keeps it at anchor 4 rather than 5.	4 / 5
	Total	15 / 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.

The description clearly and explicitly states both what the skill does and when to activate it, with concrete trigger phrases and named frameworks. It is slightly limited on action specificity (one main mechanism) and has minor overlap risk from broad triggers.

Dimension	Reasoning	Score
Specificity	Quotes 'Use up-to-date library and framework docs via Context7 MCP' — names the domain and one concrete mechanism (fetch docs via Context7 MCP) but does not enumerate multiple distinct concrete actions, matching anchor 3 rather than 4.	3 / 5
Completeness	Explicitly answers 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'), matching anchor 5 for concrete trigger phrases on both.	5 / 5
Trigger Term Quality	Quotes 'setup questions, API references, code examples' and 'names a framework (e.g. React, Next.js, Prisma)' — good coverage of natural trigger phrases users would say, with only minor synonyms missing, fitting anchor 4.	4 / 5
Distinctiveness Conflict Risk	The Context7-MCP-specific framing carves a clear niche, though broad triggers like 'code examples' risk minor overlap with general coding skills, placing it at anchor 4 rather than 5.	4 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: affaan-m/ECC
Path: .agents/skills/documentation-lookup/SKILL.md
Commit: d8409a4

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.