repomix-safe-mixer
Safely package codebases with repomix by automatically detecting and removing hardcoded credentials before packing. Use when packaging code for distribution, creating reference packages, or when the user mentions security concerns about sharing code with repomix.
89
85%
Does it follow best practices?
Impact
96%
1.81xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Quality
Discovery
85%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 a well-structured description that clearly communicates both the skill's purpose and when to use it. The explicit 'Use when...' clause with multiple trigger scenarios is a strength. The main weakness is limited trigger term coverage for security-related vocabulary that users commonly use.
Suggestions
Expand trigger terms to include common security vocabulary like 'secrets', 'API keys', 'tokens', 'sensitive data', or 'environment variables'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'package codebases with repomix', 'automatically detecting and removing hardcoded credentials', and 'packing'. Uses third person voice correctly. | 3 / 3 |
Completeness | Clearly answers both what ('Safely package codebases with repomix by automatically detecting and removing hardcoded credentials') and when ('Use when packaging code for distribution, creating reference packages, or when the user mentions security concerns about sharing code with repomix'). | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'repomix', 'packaging code', 'credentials', 'security concerns', but misses common variations users might say like 'secrets', 'API keys', 'tokens', 'sensitive data', or 'code sharing'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche combining repomix tool with credential detection/removal. The combination of 'repomix' and 'hardcoded credentials' creates a distinct trigger profile unlikely to conflict with general code packaging or security scanning skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill with excellent actionability and workflow clarity. The multi-step processes are clearly sequenced with built-in validation (scan blocks pack if secrets found). Minor verbosity in explanatory sections and some redundancy between overview and description slightly reduce token efficiency, but overall this is a strong, production-ready skill.
Suggestions
Remove the Overview section's first paragraph which duplicates the skill description - start directly with 'This skill prevents accidental credential exposure...'
Condense 'Post-Exposure Actions' to a brief checklist or move to a reference file - Claude knows incident response basics
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some redundancy - the overview repeats the description, and some sections like 'Common False Positives' and 'Post-Exposure Actions' explain concepts Claude likely knows. The examples are good but could be tighter. | 2 / 3 |
Actionability | Excellent actionability with fully executable bash commands, concrete code examples for replacing secrets, and copy-paste ready workflows. Every instruction has specific commands with real output examples. | 3 / 3 |
Workflow Clarity | Clear multi-step workflows with explicit validation checkpoints. The 'Clean and Package' workflow shows scan → fix → verify → pack sequence. The tool itself enforces validation by blocking packaging when secrets are found. | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from quick start to advanced options. References to external files (common_secrets.md, scripts) are one level deep and clearly signaled. Content is appropriately split between overview and detailed references. | 3 / 3 |
Total | 11 / 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
- daymade/claude-code-skills
- Commit
392d34c
- 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.