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

82%

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

81%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.

A highly actionable, well-sequenced skill body with real validation feedback loops and verifiable bundle references. Its main weakness is verbosity from repeated command examples across overlapping sections and inlining of content already present in the reference file.

Suggestions

Consolidate the repeated safe_pack/scan_secrets command examples from 'Options', 'Integration with Repomix', and 'Example Workflows' into one canonical usage section to cut ~80 lines.

Replace the inlined 'Detected Secret Types' list with a brief summary plus a single pointer to references/common_secrets.md to avoid duplicating the catalog.

Trim 'Post-Exposure Actions' to a short checklist or move it to the reference, since it is generic incident-response advice Claude already knows.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands, but ~310 lines for a two-script skill includes notable repetition — the same safe_pack/scan_secrets invocations reappear across 'Options', 'Integration with Repomix', and 'Example Workflows', and 'Post-Exposure Actions' restates generic security advice Claude already knows.	3 / 5
Actionability	Fully executable, copy-paste-ready commands cover the common cases (scan, pack, --output, --config, --exclude, --json, --force) with concrete expected output blocks for both clean and secret-found paths.	5 / 5
Workflow Clarity	The 'Handling Detected Secrets' section sequences Step 1-5 with an explicit feedback loop (Step 4 'Verify Cleanup' re-runs the scanner, Step 5 packs only once clean), and safe_pack blocks on detection while flagging --force as dangerous.	5 / 5
Progressive Disclosure	Good structure with a clearly signaled one-level reference (references/common_secrets.md) and separate script files all listed in Resources; the inlined 'Detected Secret Types' catalog partially duplicates the reference file, a minor organization gap.	4 / 5
	Total	17 / 20 Passed

Description

83%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.

A well-formed description that clearly states capability and triggers in third person with concrete actions. Minor improvements possible by trimming the generic 'security concerns' trigger and acknowledging the report/verify behavior rather than implying automatic removal.

Dimension	Reasoning	Score
Specificity	Names the domain ('package codebases with repomix') and several concrete actions ('detecting and removing hardcoded credentials', 'packing'), but coverage stops at the core scan/pack loop without enumerating reporting, exclusion, or JSON-output capabilities.	4 / 5
Completeness	Explicitly answers both what ('Safely package codebases with repomix by automatically detecting and removing hardcoded credentials before packing') and when ('Use when packaging code for distribution, creating reference packages, or when the user mentions security concerns').	5 / 5
Trigger Term Quality	Strong natural triggers ('packaging code for distribution', 'creating reference packages', 'security concerns about sharing code with repomix') but missing common synonyms like 'sharing code', 'bundle', or explicit file extensions.	4 / 5
Distinctiveness Conflict Risk	The repomix-plus-credential-detection niche is distinct, but the broad 'security concerns about sharing code' trigger creates minor overlap risk with general security-auditing skills.	4 / 5
	Total	17 / 20 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: b8556f2

Reviewed: 2 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.