docs-discovery

Technical documentation discovery via context7 and web search. Capabilities: library/framework docs lookup, topic-specific search. Keywords: llms.txt, context7, documentation, library docs, API docs. Use when: searching library documentation, finding framework guides, looking up API references.

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 ./skills/docs-discovery/SKILL.md

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 is a lean, actionable, well-sequenced guide with concrete tool invocations and a clear failover path. Its main weakness is redundancy between the Strategy and Workflow Summary sections, which slightly hurts conciseness and organization.

Suggestions

Collapse the '## Strategy' and '## Workflow Summary' sections into a single sequenced flow to remove the duplicated representation and tighten token usage.

Add a brief verification cue in Step 3 (e.g., confirm the fetched page is official/current documentation before presenting) to strengthen the workflow's validation checkpoint.

Specify the WebFetch step more concretely, such as what to extract or how to parse llms.txt content, to close the actionability gap.

Dimension	Reasoning	Score
Conciseness	The workflow is presented twice (## Strategy steps and ## Workflow Summary) and ## Key Rules reiterates 'context7 first' and 'parallel search', adding redundancy that could be trimmed; otherwise it avoids explaining concepts Claude already knows.	3 / 5
Actionability	Concrete tool calls with parameters are provided (mcp__context7__resolve-library-id, WebSearch queries), but the WebFetch step stays vague ('fetch and extract content') without parsing specifics.	4 / 5
Workflow Clarity	A clear three-step sequence with an explicit failover branch (context7 fail -> Step 2) and parallel search; minor gap is the absence of any verification that fetched content is actually useful documentation.	4 / 5
Progressive Disclosure	Self-contained with well-organized sections and no external bundle files needed, but the duplicated flow representation (Strategy + Workflow Summary) is a minor organization gap and the body is slightly over 50 lines.	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 is strong: it clearly answers both what the skill does and when to use it, with good keyword coverage and a distinct context7-oriented niche. Minor gaps in action specificity and a slight overlap risk with general research skills keep trigger_term_quality and distinctiveness just below the top anchor.

Dimension	Reasoning	Score
Specificity	Names the documentation domain and two concrete actions ('library/framework docs lookup, topic-specific search'), but does not enumerate a broader set of specific capabilities to reach comprehensive coverage.	3 / 5
Completeness	Explicitly states both what the skill does ('Technical documentation discovery via context7 and web search') and when to use it ('Use when: searching library documentation, finding framework guides, looking up API references') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good keyword coverage with synonyms ('library docs'/'library documentation', 'API docs'/'API references', 'framework guides'), though 'context7' and 'llms.txt' lean technical and a few natural user phrases are absent.	4 / 5
Distinctiveness Conflict Risk	The context7/llms.txt framing carves a clear niche, but 'documentation discovery' still has minor overlap risk with general web-research skills.	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: samhvw8/dot-claude
Path: skills/docs-discovery/SKILL.md
Commit: 28c7616

Reviewed: 3 days 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.