Name: codebase-audit-pre-push
Rating: 44 (1 reviews)
Author: administrakt0r

codebase-audit-pre-push

Deep audit before GitHub push: removes junk files, dead code, security holes, and optimization issues. Checks every file line-by-line for production readiness.

Quality

45%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/codebase-audit-pre-push/SKILL.md

The canonical home for this skill is codebase-audit-pre-push in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

35%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 a thorough but verbose checklist of well-known concepts with weak executable guidance and no validation checkpoints for its destructive operations. Structure exists but nothing is split into references.

Suggestions

Trim explanations of basic concepts Claude already knows (junk-file lists, magic numbers, N+1 definitions) to a lean checklist so every token earns its place.

Add executable audit commands (e.g. grep/ripgrep patterns for secrets, dead-code detection commands) and concrete fix templates rather than abstract directives.

Insert validation/feedback checkpoints between destructive steps (e.g. confirm a file is truly unused before deleting, re-run tests after each code change) to lift workflow clarity above 3.

Dimension	Reasoning	Score
Conciseness	The ~230-line body catalogs concepts Claude already knows (OS junk files, magic numbers, === vs ==, N+1 queries) with several padded explanatory sections, matching 'noticeably verbose; several unnecessary explanations'.	2 / 5
Actionability	Audit steps are high-level hints ('rename to be descriptive', 'use JOINs', 'add LIMIT') with almost no executable commands or concrete find/fix code; only the output-format block and `npm audit` are concrete, leaving minimal executable guidance.	2 / 5
Workflow Clarity	Ten numbered steps give a clear sequence, but the workflow performs destructive/batch operations (file deletion, code modification, secret removal) with no per-step validation checkpoints or feedback loops, which per the rubric caps this score at 3.	3 / 5
Progressive Disclosure	A single ~230-line file inlines content (junk-file patterns, security checklist) that could live in separate reference files; it has section structure but no well-signaled one-level-deep references, and it exceeds the 50-line simple-skill exception.	3 / 5
	Total	10 / 20 Passed

Description

55%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 states a clear purpose and several concrete audit actions but lacks an explicit 'Use when...' trigger clause, capping completeness. It is reasonably distinct yet overlaps with general review skills.

Suggestions

Add an explicit 'Use when...' clause with natural user phrases such as 'audit the codebase', 'review before push', 'clean up the code', or 'optimize everything'.

Sharpen the action list from broad categories (e.g. 'security holes') to more concrete operations to push specificity toward 5.

Tighten distinctiveness by naming the specific pre-push gating context so it is clearly separate from generic security-audit skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('removes junk files, dead code, security holes, and optimization issues') plus a line-by-line check, but the actions are domain categories rather than granular operations, so it falls below the comprehensive anchor 5.	4 / 5
Completeness	Has a clear 'what' but no explicit 'Use when...' trigger clause; 'when' is only weakly implied by 'before GitHub push', which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Includes relevant keywords ('audit', 'GitHub push', 'production readiness') but omits common natural phrases users would say like 'clean up the code' or 'review before pushing', so it matches the 'some relevant keywords, missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'Deep audit before GitHub push' carves a niche, but 'dead code, security holes, optimization issues' overlaps broadly with general code-review and security-audit skills, so it could still trigger the wrong skill.	3 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/codebase-audit-pre-push/SKILL.md
Commit: 57c135b

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.