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

85%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-structured skill with excellent progressive disclosure and workflow clarity. The content efficiently guides Claude through a multi-strategy documentation discovery process with clear decision points and fallback paths. The main weakness is that some agent-related instructions are more descriptive than executable, lacking concrete syntax for launching parallel agents.

Suggestions

Provide concrete syntax for launching Explorer/Researcher agents (e.g., actual Task tool invocation format) rather than descriptive pseudocode

Add a brief executable example showing the exact format for parallel agent task distribution

Dimension	Reasoning	Score
Conciseness	The content is lean and efficient, avoiding explanations of concepts Claude already knows. Each section provides direct, actionable information without padding or unnecessary context.	3 / 3
Actionability	Provides concrete guidance with specific search patterns and bash commands, but some examples are pseudocode-like (e.g., 'Launch 3 Explorer agents simultaneously' without actual syntax). The Repomix commands are executable, but agent launching syntax is abstract.	2 / 3
Workflow Clarity	Clear multi-phase workflow with explicit decision points (Found? → Phase 2, Not found? → Phase 3). Error handling section provides fallback sequences, and the workflow includes clear checkpoints between phases.	3 / 3
Progressive Disclosure	Excellent structure with a concise overview, quick reference section, and well-signaled one-level-deep references to detailed documentation (WORKFLOWS.md, references/*.md). Content is appropriately split between overview and detailed guides.	3 / 3
	Total	11 / 12 Passed

Description

85%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong skill description that clearly articulates specific capabilities and provides explicit trigger conditions through a numbered list. The main weakness is the use of technical jargon (llms.txt, Repomix) that users may not naturally use when requesting help, which could reduce discoverability in natural language queries.

Suggestions

Add more natural user-facing trigger terms like 'docs', 'API documentation', 'how to use [library]', 'find documentation for' to improve discoverability

Consider briefly explaining what llms.txt and Repomix are, or add alternative phrasings users might use when they need these capabilities without knowing the technical terms

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'Searching internet for technical documentation', 'llms.txt standard', 'GitHub repositories via Repomix', and 'parallel exploration'. These are concrete, actionable capabilities.	3 / 3
Completeness	Clearly answers both what (searching for technical documentation using llms.txt, GitHub via Repomix, parallel exploration) AND when with explicit numbered triggers covering five distinct use cases.	3 / 3
Trigger Term Quality	Includes some relevant keywords like 'documentation', 'libraries/frameworks', 'GitHub repository', but uses technical jargon ('llms.txt', 'Repomix') that users may not naturally say. Missing common variations like 'docs', 'API reference', 'readme'.	2 / 3
Distinctiveness Conflict Risk	Clear niche focused on technical documentation search with specific methods (llms.txt standard, Repomix). The combination of these specific tools and documentation focus makes it unlikely to conflict with general search or coding skills.	3 / 3
	Total	11 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: einverne/dotfiles
Commit: b1b2fe0

Reviewed: 5 months 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.