repomix

Guide for using Repomix - a powerful tool that packs entire repositories into single, AI-friendly files. Use when packaging codebases for AI analysis, generating context for LLMs, creating codebase snapshots, analyzing third-party libraries, or preparing repositories for security audits.

Quality

67%

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/repomix/SKILL.md

Quality

Content

56%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 throughout, but it is padded with repetition and stale token figures, and it inlines a large reference catalog that should be progressively disclosed into separate files. Workflow and actionability are solid; conciseness and progressive disclosure are the weak spots.

Suggestions

Split the CLI options catalog, full config-file schema, and troubleshooting entries into reference files under references/, keeping SKILL.md as a concise overview that links one level deep.

Deduplicate the repeated --style/--include/--ignore examples that recur across Basic Usage, Output Configuration, Output Formats, and Common Patterns, and remove the stale GPT-3.5/GPT-4 token counts from the Token Management section.

Tighten the Implementation Workflow's 'Validate Output' step into an explicit command-based check (e.g. 'grep -i secret repomix-output.xml' or confirm security scan passed) with a fix-and-retry loop.

Dimension	Reasoning	Score
Conciseness	The 445-line body is noticeably verbose: the intro restates the description verbatim, the same flags recur across Basic Usage, Output Configuration, Output Formats, and Common Patterns, and the Token Management section carries stale, time-sensitive figures (GPT-3.5 ~16K, GPT-4 ~128K) that the guidelines say should penalize conciseness.	2 / 5
Actionability	Dense with copy-paste-ready commands and a complete config-file JSON example covering common cases, with only minor gaps such as placeholder troubleshooting steps ('Review flagged files / Add to .repomixignore').	4 / 5
Workflow Clarity	The Implementation Workflow gives a clear five-step sequence (Assess → Configure → Execute → Validate → Deliver) with a 'Validate Output' checkpoint, though the validation is review-based rather than an explicit tool-driven validate→fix→retry loop.	4 / 5
Progressive Disclosure	Section headers are well organized, but this is a large monolithic SKILL.md with no bundle files at all — the CLI reference, config schema, and troubleshooting content that belong in separate reference files are inlined rather than split out.	3 / 5
	Total	13 / 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 states a concrete capability and follows with an explicit, scenario-rich 'Use when' clause. Its main weakness is specificity, since the listed use cases describe scope rather than multiple distinct tool actions.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete core action ('packs entire repositories into single, AI-friendly files'), but the use-case list enumerates scopes rather than additional distinct tool actions, leaving coverage non-comprehensive.	3 / 5
Completeness	Explicitly answers both what ('packs entire repositories into single, AI-friendly files') and when ('Use when packaging codebases for AI analysis, generating context for LLMs, ...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('packaging codebases', 'AI analysis', 'context for LLMs', 'codebase snapshots', 'security audits') with good coverage, though a few synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	The repository-packaging niche is mostly distinct with clear triggers, though 'generating context for LLMs' is broad enough to risk minor overlap with related context-generation skills.	4 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: einverne/dotfiles
Path: claude/skills/repomix/SKILL.md
Commit: 7d18cf4

Reviewed: 4 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.