repomix-unmixer
Extracts files from repomix-packed repositories, restoring original directory structures from XML/Markdown/JSON formats. Activates when users need to unmix repomix files, extract packed repositories, restore file structures from repomix output, or reverse the repomix packing process.
82
75%
Does it follow best practices?
Impact
93%
1.43xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./repomix-unmixer/SKILL.mdQuality
Discovery
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.
This is an excellent skill description that clearly communicates what the skill does (extract and restore files from repomix-packed repositories across multiple formats) and when to use it (with an explicit 'Activates when...' clause covering multiple trigger scenarios). The description is concise, uses third-person voice, includes domain-specific trigger terms, and occupies a clear niche that minimizes conflict risk.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: 'Extracts files from repomix-packed repositories', 'restoring original directory structures', and specifies the formats handled (XML/Markdown/JSON). These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (extracts files from repomix-packed repos, restoring directory structures from XML/Markdown/JSON) and 'when' (explicit 'Activates when...' clause with multiple trigger scenarios). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'repomix', 'unmix', 'packed repositories', 'extract', 'restore file structures', 'repomix output', 'reverse the repomix packing process'. These cover multiple natural phrasings a user might use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — 'repomix' is a very specific tool/format, making this unlikely to conflict with general file extraction or repository management skills. The niche is clearly defined. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is highly actionable with clear, executable commands, but is severely bloated for what amounts to running a single Python script with two arguments. The content repeats the same advice (use temp directories, review before moving) in multiple sections, explains internal script behavior Claude doesn't need to know, and includes format details that belong in the referenced files. Trimming to ~40-50 lines with the core command, key principles, and references would dramatically improve token efficiency.
Suggestions
Reduce the skill to: core command with parameters, one example, the 'extract to temp first' principle (stated once), validation checklist, and references. Remove the 'What the Script Does' section, redundant use cases, and inline format details.
Move the Supported Formats section entirely to references/repomix-format.md since it's already referenced—just note that XML/Markdown/JSON are supported and point to the reference.
Consolidate the 'Important Principles' and 'Best Practices' sections into a single short list—they currently repeat the same temp-directory and review advice.
Move the Troubleshooting section to a separate reference file or drastically shorten it to one-liners, as most issues (permissions, encoding, path conflicts) are things Claude can diagnose without detailed guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose for what is essentially a single-command operation. The skill explains what the script does internally (parses, extracts, creates, writes, reports), provides redundant use cases that are all identical invocations with different paths, repeats the same 'extract to temp first' advice multiple times, and includes extensive troubleshooting for issues Claude could handle on its own. The core skill could be conveyed in ~30 lines. | 1 / 3 |
Actionability | Provides fully executable bash commands throughout, with concrete paths and parameters. The primary command is copy-paste ready, and examples cover real scenarios with specific flags and arguments. | 3 / 3 |
Workflow Clarity | The core workflow is a single command which is clear, but the validation workflow is listed as general advice ('spot check content', 'check file count') without concrete commands or explicit checkpoints. For a destructive operation like overwriting files, the 'extract to temp, review, then move' pattern is mentioned but not formalized as a mandatory workflow with validation gates. | 2 / 3 |
Progressive Disclosure | References to external files (repomix-format.md, validation-workflow.md) are present and well-signaled, but the main SKILL.md contains far too much inline content that could be offloaded—troubleshooting, format details, and repetitive use cases bloat the overview. The supported formats section duplicates what should live in the format reference. | 2 / 3 |
Total | 8 / 12 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- fernandezbaptiste/claude-code-skills
- Commit
4f0eae8
- 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.