repomix

Package entire code repositories into single AI-friendly files using Repomix. Capabilities include pack codebases with customizable include/exclude patterns, generate multiple output formats (XML, Markdown, plain text), preserve file structure and context, optimize for AI consumption with token counting, filter by file types and directories, add custom headers and summaries. Use when packaging codebases for AI analysis, creating repository snapshots for LLM context, analyzing third-party libraries, preparing for security audits, generating documentation context, or evaluating unfamiliar codebases.

Quality

86%

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

72%

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

The content is highly actionable with executable commands and good progressive disclosure to real reference files, but loses points for repeated flag listings and a Token Management section that pads with knowledge Claude already has. The workflow has validation but no explicit retry feedback loop.

Suggestions

Consolidate the repeated --include/--style/--remove-comments/--copy examples into a single 'Command Line Reference' section to remove duplication across Quick Start, Common Use Cases, and Output Options.

Cut the 'Token Management' LLM context-limit table — Claude already knows these limits and the version numbers (Sonnet 4.5, GPT-4) are time-sensitive; keep only the note that Repomix reports per-file and total token counts.

Add an explicit feedback loop to the Implementation Workflow: after 'Validate Output', state 'If sensitive data is found or token limits are exceeded, adjust --include/--ignore and re-run before delivering.'

Dimension	Reasoning	Score
Conciseness	The body is mostly command-driven and efficient, but repeats flags across 'Quick Start', 'Common Use Cases', and 'Command Line Reference' (--include, --style, --remove-comments, --copy, -o), and the 'Token Management' section restates LLM context limits Claude already knows with time-sensitive version numbers (Sonnet 4.5, GPT-4).	2 / 3
Actionability	Commands are concrete, executable, and copy-paste ready throughout — 'npm install -g repomix', 'repomix --include "src/*/.ts" --remove-comments -o output.md', 'npx repomix --remote owner/repo' — matching the fully-executable anchor.	3 / 3
Workflow Clarity	The 'Implementation Workflow' lists a clear 5-step sequence including a 'Validate Output' step, but lacks an explicit validate→fix→retry feedback loop; checkpoints are named but the error-recovery path is implicit rather than stated, matching the anchor with validation gaps.	2 / 3
Progressive Disclosure	The body is an organized overview that defers detail to well-signaled, one-level-deep references — '[Configuration Reference](./references/configuration.md)' and '[Usage Patterns](./references/usage-patterns.md)' — both of which exist as real files, with clear one-line descriptions for each.	3 / 3
	Total	10 / 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.

The description is specific, third-person, and cleanly separates capability statements from explicit 'Use when' triggers, hitting the top anchor on every dimension. It is concise yet comprehensive without fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'pack codebases with customizable include/exclude patterns', 'generate multiple output formats (XML, Markdown, plain text)', 'preserve file structure and context', 'optimize for AI consumption with token counting', 'filter by file types and directories', 'add custom headers and summaries' — matching the anchor for listing several specific actions.	3 / 3
Completeness	Explicitly answers both 'what' ('Package entire code repositories into single AI-friendly files using Repomix') and 'when' via a clearly marked 'Use when...' trigger clause, satisfying the top anchor for both.	3 / 3
Trigger Term Quality	The 'Use when...' clause covers natural phrasings a user would say — 'packaging codebases for AI analysis', 'repository snapshots for LLM context', 'security audits', 'evaluating unfamiliar codebases' — giving good coverage of common variations rather than jargon.	3 / 3
Distinctiveness Conflict Risk	The Repomix-specific packaging niche with distinct triggers ('repository snapshots for LLM context', 'packaging codebases for AI analysis') is unlikely to overlap with or mis-trigger other skills.	3 / 3
	Total	12 / 12 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: mrgoonie/claudekit-skills
Path: .claude/skills/repomix/SKILL.md
Commit: 80113d8

Reviewed: about 9 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.