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.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

85%

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

A well-structured, actionable skill body with clear multi-step workflows, validation checkpoints, and properly signaled one-level-deep references to real bundle files. Its main weakness is verbosity from repeated command examples and re-stating the description in the Overview.

Suggestions

Consolidate the repeated `python3 scripts/safe_pack.py` invocations: show the full command once with all options, then reference it briefly in subsequent workflows instead of repeating the full block each time.

Trim the Overview and 'When to use' lines that duplicate the frontmatter description, keeping the body focused on workflow and details Claude cannot infer.

Consider moving the 'Detected Secret Types' and 'Common False Positives' lists into `references/common_secrets.md` (already referenced) and summarizing categories inline to reduce token load.

Dimension	Reasoning	Score
Conciseness	The body is largely useful, but the `safe_pack.py` invocation is repeated ~8 times across examples and the Overview/'When to use' section restates the frontmatter description, so it could be tightened.	2 / 3
Actionability	It provides fully executable commands (`python3 scripts/safe_pack.py <directory>`), concrete before/after code edits, and copy-paste-ready option examples with expected output.	3 / 3
Workflow Clarity	The 'Handling Detected Secrets' section sequences Steps 1–5 with an explicit 'Verify Cleanup' checkpoint, and safe_pack blocks packaging when secrets are found — a clear validate-then-proceed feedback loop.	3 / 3
Progressive Disclosure	The body is an overview that signals one-level-deep references to real bundle files (`references/common_secrets.md`, `scripts/scan_secrets.py`, `scripts/safe_pack.py`) listed in a Resources section, with the detailed secret catalog split into the reference file.	3 / 3
	Total	11 / 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.

A strong, third-person description that states concrete capabilities and gives explicit use-when triggers tied to repomix packaging and security concerns. It cleanly answers both what and when without fluff.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'package codebases with repomix', 'detecting and removing hardcoded credentials', and 'before packing' — rather than vague language.	3 / 3
Completeness	It answers both what ('Safely package codebases... by automatically detecting and removing hardcoded credentials') and when (an explicit 'Use when...' clause with several triggers).	3 / 3
Trigger Term Quality	It covers natural terms users would say — 'packaging code for distribution', 'creating reference packages', 'security concerns about sharing code with repomix', and 'repomix'.	3 / 3
Distinctiveness Conflict Risk	The repomix-plus-credential-scanning niche is distinctive, and its triggers ('security concerns about sharing code with repomix') are unlikely to fire for unrelated 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: daymade/claude-code-skills
Path: repomix-safe-mixer/SKILL.md
Commit: b3b4af8

Reviewed: 8 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.