CtrlK
BlogDocsLog inGet started
Tessl Logo

repomix-explorer

Analyze or explore a codebase (remote or local repository) by packing it with the Repomix CLI, then reading and searching the generated output. Use when the user wants a high-level understanding of an unfamiliar or large repo, not a targeted edit. Trigger for: - Structure/overview: "analyze this repo", "what's the structure", "explain this codebase", "what's in vercel/next.js" - Pattern discovery across many files: "find all auth code", "where are the API endpoints", "show me all React components" - Metrics: "how many files/tokens", "largest files", "TypeScript vs JavaScript ratio" - Remote repos: any github.com URL or "owner/repo" the user wants explored DO NOT trigger for: - Editing, refactoring, or writing code in the current project - Reading or searching a known file/path in the local project (use Read or grep directly) - Single-symbol lookups in the local project answerable with one grep - Git operations, running tests, builds, or installs

66

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/repomix-explorer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 highly actionable with concrete commands and a clear workflow, but it is padded with redundant sections and a generic checklist that inflate token cost, and it makes no use of progressive disclosure despite its length.

Suggestions

Remove redundant sections — 'User Intent Examples' (duplicates the description), 'Important Notes' (duplicates 'Best Practices'), and 'Communication Style' (generic advice) — to tighten the body.

Trim or cut the 'Self-Verification Checklist' to a short inline validation gate within the workflow steps rather than a trailing 9-item list.

Move the five full example workflows and the search-pattern catalog into reference files under ./references/ and link to them one level deep to improve progressive disclosure.

DimensionReasoningScore

Conciseness

Noticeably verbose across several padded/redundant sections: 'User Intent Examples' restates the description's triggers, 'Important Notes' restates 'Best Practices', the 9-item 'Self-Verification Checklist' and 'Communication Style' add generic guidance Claude already knows, and the search-pattern catalog appears in two places.

2 / 5

Actionability

Fully executable, copy-paste-ready commands throughout — 'npx repomix@latest --remote yamadashy/repomix --output /tmp/repomix-analysis.xml', concrete grep patterns, and --include globs — covering remote, local, large-repo, and file-type cases.

5 / 5

Workflow Clarity

Clear four-step sequence (Pack → Check Output → Analyze → Insights) with a Self-Verification Checklist and an Error Handling section providing feedback loops, but validation is a separate trailing checklist rather than interleaved checkpoints gating each step.

4 / 5

Progressive Disclosure

No bundle files exist and the skill is a single ~296-line monolithic document; sections are well-organized with headers, but content that could be split out (five full example workflows, the search-pattern catalog) is inlined with no one-level-deep references.

3 / 5

Total

14

/

20

Passed

Description

95%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.

A strong, well-targeted description that clearly states capabilities and trigger conditions with natural user phrasing and explicit boundary guidance. Its only weakness is a somewhat narrow set of concrete action verbs.

DimensionReasoningScore

Specificity

Names the domain and concrete actions — 'packing it with the Repomix CLI, then reading and searching the generated output' — plus four categorized trigger types, but the core action list is narrow (pack + read/search), leaving minor coverage gaps versus a fully comprehensive enumeration.

4 / 5

Completeness

Explicitly answers both 'what' (analyze/explore a codebase by packing with Repomix and reading/searching output) and 'when' via a 'Use when...' clause plus concrete 'Trigger for' and 'DO NOT trigger for' lists.

5 / 5

Trigger Term Quality

Comprehensive natural phrasing users would actually say — 'analyze this repo', 'what's the structure', 'find all auth code', 'where are the API endpoints', 'how many files/tokens' — covering synonyms and the github.com URL/owner-repo forms.

5 / 5

Distinctiveness Conflict Risk

Clear niche (Repomix-based repository exploration) with explicit disambiguation — 'DO NOT trigger for ... Reading or searching a known file/path ... use Read or grep directly' — minimizing conflict with built-in tools.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
yamadashy/repomix
Reviewed

Table of Contents

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.