Name: production-code-audit
Rating: 40.8 (1 reviews)
Author: administrakt0r

production-code-audit

Autonomously deep-scan entire codebase line-by-line, understand architecture and patterns, then systematically transform it to production-grade, corporate-level professional quality with optimizations

Quality

40%

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/production-code-audit/SKILL.md

The canonical home for this skill is production-code-audit in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

38%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 skill has a recognizable workflow and some concrete before/after code examples, but it is heavily padded, inlines template and checklist content that belongs in separate files, and lacks the validation feedback loops a destructive batch transformation requires. Operational guidance stays abstract where specific tooling would help.

Suggestions

Move the Audit Report Template and Production Audit Checklist into separate reference files (e.g., references/report-template.md, references/checklist.md) and link to them from the body to cut the SKILL.md to a lean overview.

Add an explicit validate-fix-retry feedback loop (e.g., run tests after each fix category, only proceed on green) rather than a single final 'run tests' step, given the destructive batch scope.

Replace abstract fix instructions ('Optimize performance', 'Refactor architecture') with concrete tooling or commands (specific linters, profiling steps, migration commands) and trim the embellished example metrics and emoji.

Dimension	Reasoning	Score
Conciseness	The ~534-line body is noticeably verbose: an inlined full Audit Report Template, a long Production Audit Checklist, three embellished examples with fake metrics and emoji, and Do/Don't lists that restate the issue catalog, much of which Claude already knows.	2 / 5
Actionability	The before/after examples contain executable TypeScript snippets (parameterized queries, bcrypt, Zod schemas), but the operational workflow itself is high-level ('Refactor architecture', 'Optimize performance', 'Fix everything automatically') with no concrete tooling or commands.	3 / 5
Workflow Clarity	A clear four-step sequence (Discover, Detect, Fix, Verify) exists with a final 'run tests' verification, but for a destructive whole-codebase batch transformation the validation is only a final check with no fix-and-revalidate feedback loop or gating checkpoint, which caps the score at 3 per the rubric.	3 / 5
Progressive Disclosure	No bundle files exist and everything is inlined into one monolithic SKILL.md, including a full report template and a multi-section checklist that clearly belong in separate reference files; section headers provide some structure but there are no one-level-deep references to split the bulk.	2 / 5
	Total	10 / 20 Passed

Description

42%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 conveys a clear 'what' but is padded with corporate buzzwords, lacks natural user-facing trigger phrases, and omits an explicit 'when to use' clause. It is distinguishable but has non-trivial overlap with adjacent review/refactor skills.

Suggestions

Add an explicit 'Use when...' clause with natural user phrases (e.g., 'Use when the user says make this production-ready, audit my codebase, or wants enterprise-grade quality').

Replace buzzword padding ('corporate-level professional quality with optimizations') with concrete actions like 'fix security vulnerabilities, resolve N+1 queries, refactor god classes, and add tests'.

Tighten the trigger terms to phrases users actually say ('production-ready', 'audit my code', 'enterprise-grade') rather than 'deep-scan line-by-line'.

Dimension	Reasoning	Score
Specificity	Names the domain and a few actions ('deep-scan entire codebase line-by-line', 'understand architecture and patterns', 'transform it to production-grade'), but the payload 'corporate-level professional quality with optimizations' is buzzword padding rather than a concrete action, keeping it short of a 4.	3 / 5
Completeness	The 'what' is clearly stated (scan, understand, transform), but there is no 'Use when...' clause or equivalent explicit trigger guidance in the description, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Keywords like 'codebase', 'architecture', and 'optimizations' are present but 'deep-scan line-by-line' is jargon, not a phrase a user would naturally say; the natural triggers ('make this production-ready', 'audit my codebase') appear only in the body, not the description.	2 / 5
Distinctiveness Conflict Risk	The whole-codebase production-grade transformation framing is a recognizable niche, but the broad scope (architecture, security, performance, quality, testing, infrastructure) overlaps materially with code-review, security-review, and refactoring skills.	3 / 5
	Total	11 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (544 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

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

Reviewed: 3 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.