docs-seeker

Searching internet for technical documentation using llms.txt standard, GitHub repositories via Repomix, and parallel exploration. Use when user needs: (1) Latest documentation for libraries/frameworks, (2) Documentation in llms.txt format, (3) GitHub repository analysis, (4) Documentation without direct llms.txt support, (5) Multiple documentation sources in parallel

Quality

92%

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

Quality

Content

85%

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 documentation-discovery workflow with strong progressive disclosure into real reference files. Its main weakness is token redundancy from repeated context7 URL listings and a restated principles section, plus one broken WORKFLOWS.md link.

Suggestions

Collapse the "Quick Reference" popular-llms.txt-locations block and the "Key Principles" section into Phase 1 where the context7.com patterns are already shown, to remove repetition.

Fix or remove the dangling [WORKFLOWS.md](./WORKFLOWS.md) reference — no such file exists in the root or references/ bundle.

Trim verbose restatements like the "Repomix benefits" bullets that describe what Claude can infer from the command block above.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable rather than explanatory, but it pads tokens via redundancy: the "Quick Reference" repeats context7.com URLs already shown in Phase 1, and "Key Principles" restates guidance from earlier sections.	2 / 3
Actionability	Provides concrete URL patterns with real examples, copy-paste bash for Repomix (install/clone/pack), and explicit agent-distribution counts per URL range — fully executable guidance.	3 / 3
Workflow Clarity	Phases 1-4 are clearly sequenced with explicit branch checkpoints ("→ Found? Proceed to Phase 2 / Not found? Phase 3") and a dedicated Error Handling section giving feedback loops for recovery.	3 / 3
Progressive Disclosure	SKILL.md is an overview that signals one-level-deep references to six real ./references/ files (all present), with content appropriately split; navigation is easy, though the referenced ./WORKFLOWS.md does not exist in the bundle.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 well-crafted description that states concrete capabilities and pairs them with explicit, enumerated trigger conditions in third-person voice. It clearly distinguishes this skill from generic research/web-search skills.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "Searching internet for technical documentation using llms.txt standard", "GitHub repositories via Repomix", and "parallel exploration" — rather than vague language.	3 / 3
Completeness	Explicitly answers both what (searching via llms.txt, Repomix, parallel exploration) and when (a five-item "Use when user needs" clause with explicit triggers).	3 / 3
Trigger Term Quality	The numbered "Use when user needs" list covers natural phrasings users would say ("Latest documentation for libraries/frameworks", "GitHub repository analysis", "Multiple documentation sources in parallel"); "llms.txt format" is more jargony but overall coverage is broad.	3 / 3
Distinctiveness Conflict Risk	The llms.txt / Repomix / parallel-agent niche is specific and unlikely to trigger for unrelated skills; the triggers are tightly scoped to documentation discovery.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: mrgoonie/claudekit-skills
Path: .claude/skills/docs-seeker/SKILL.md
Commit: 80113d8

Reviewed: about 8 hours 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.