CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

84

1.43x
Quality

77%

Does it follow best practices?

Impact

93%

1.43x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

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 well-structured and actionable with verified references and a validation workflow, but it is longer than necessary due to repeated use-case examples and overlapping Best Practices/Important Principles sections. Tightening redundancy and inlining validation as a checkpoint would lift the weaker dimensions.

Suggestions

Consolidate the three Common Use Cases into a single section with parameter variations, and merge Important Principles with Best Practices to remove redundancy and improve conciseness.

Move the detailed XML/Markdown/JSON format structure examples into references/repomix-format.md, keeping only a brief pointer in the body, to improve progressive_disclosure.

Add an inline validation checkpoint directly after the extraction command (e.g., 'verify file count with `find <output> -type f | wc -l`') to tighten the workflow feedback loop toward the 5 anchor.

DimensionReasoningScore

Conciseness

Mostly functional but noticeably padded: the three Common Use Cases largely restate the same extraction command, and the Best Practices section duplicates the Important Principles section, matching the 3 anchor for content that could be tightened.

3 / 5

Actionability

Provides concrete, copy-paste-ready commands with parameters and a worked example, plus per-format examples, but the 'What the Script Does' section is descriptive rather than executable, leaving a minor gap from the 5 anchor.

4 / 5

Workflow Clarity

The core extraction flow and a separate Validation Workflow are clearly sequenced, and Troubleshooting supplies error-recovery guidance, but validation is a separate section rather than an inline checkpoint within the core flow, so it sits at the 4 anchor rather than 5.

4 / 5

Progressive Disclosure

Structure is good with clearly signaled, one-level-deep references (repomix-format.md, validation-workflow.md, unmix_repomix.py) that exist as real files, but detailed XML/Markdown/JSON format examples are inlined in the body rather than fully pushed to the reference, keeping it at 4.

4 / 5

Total

15

/

20

Passed

Description

87%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 explicitly states both capability and activation triggers with concrete, natural language, and occupies a distinctive niche. The only weakness is trigger-term and specificity coverage that, while good, is not maximally comprehensive.

Suggestions

Add explicit file extensions as natural trigger terms (e.g., '.xml', '.md', '.json' packed files) to push trigger_term_quality toward comprehensive coverage.

Broaden the action list slightly (e.g., 'inspect', 'validate', or 'repack' repomix output) to increase specificity breadth beyond pure extraction.

DimensionReasoningScore

Specificity

Lists several concrete actions (extracts files, restores directory structures, handles XML/Markdown/JSON formats) but coverage stays within the single repomix-reversal domain rather than comprehensive multi-action breadth, matching the 4 anchor.

4 / 5

Completeness

Explicitly answers 'what' (extracts files and restores directory structures from XML/Markdown/JSON) and 'when' ('Activates when users need to...') with concrete trigger phrases, matching the 5 anchor.

5 / 5

Trigger Term Quality

Includes natural trigger phrases users would say ('unmix repomix files', 'extract packed repositories', 'restore file structures', 'reverse the repomix packing process') plus format names, but stops short of comprehensive file-extension-style synonym listing that the 5 anchor shows.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (repomix reversal) with distinct, domain-specific triggers tied to 'repomix', yielding minimal conflict risk with other skills, matching the 5 anchor.

5 / 5

Total

18

/

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
daymade/claude-code-skills
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.