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

75%

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 ./claude/skills/docs-seeker/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 well-organized, mostly lean workflow document with concrete commands and clear phased sequencing. Its main weaknesses are abstract (non-executable) agent-launch guidance and a dangling WORKFLOWS.md reference.

Suggestions

Replace abstract 'Launch N Explorer agents' directions with a concrete, copy-pasteable Task/agent invocation example so the parallel step is executable.

Either add ./WORKFLOWS.md to the bundle or remove the [WORKFLOWS.md](./WORKFLOWS.md) link to avoid a broken navigation reference.

Add an explicit verify/aggregate checkpoint before producing the consolidated report (e.g., 'Confirm every Explorer agent returned before merging') to close the validation gap in the batch workflow.

Dimension	Reasoning	Score
Conciseness	Largely lean — phases, tool-selection, and output template avoid explaining concepts Claude already knows, though 'Repomix benefits' bullets and 'Intelligent discovery and analysis' add mild restatement that could be trimmed.	4 / 5
Actionability	Provides concrete WebSearch query patterns, repomix bash commands, and an output template, but the parallel-agent launches ('Launch 3 Explorer agents simultaneously') are abstract direction rather than executable invocations, leaving a key gap.	3 / 5
Workflow Clarity	A clear four-phase sequence with explicit decision branches and a fallback Error Handling section, but the batch multi-agent aggregation lacks an explicit verify-before-proceeding feedback loop, leaving minor validation gaps.	4 / 5
Progressive Disclosure	Well-structured overview pointing to one-level-deep references that all exist in ./references/, but the body references ./WORKFLOWS.md which is not present in the bundle, breaking navigation for that entry.	4 / 5
	Total	15 / 20 Passed

Description

83%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 pairs a concrete 'what' with an explicit, enumerated 'Use when' trigger list and names distinct strategies. It is mostly specific and distinguishable, with only minor gaps in synonym coverage and verb specificity.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete strategies (llms.txt search, Repomix repository packing, parallel Explorer agents) beyond a single generic action, though 'Searching internet for technical documentation' is a somewhat generic framing rather than discrete verbs.	4 / 5
Completeness	Explicitly answers both what it does (searching via llms.txt, Repomix, parallel exploration) and when to use it via a numbered 'Use when user needs' clause with concrete triggers.	5 / 5
Trigger Term Quality	Includes natural terms a user would say ('latest documentation for libraries/frameworks', 'GitHub repository analysis', 'llms.txt') with good coverage, but misses common synonyms like 'docs' or 'API reference'.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (llms.txt / Repomix documentation discovery) with distinct triggers, with only minor overlap risk against general web-search or research skills.	4 / 5
	Total	17 / 20 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: einverne/dotfiles
Path: claude/skills/docs-seeker/SKILL.md
Commit: 837e856

Reviewed: ~6 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.