production-code-audit — Claude Code skill: audit code for production
Skill for systematic code review covering security flaws, logic errors and performance issues before deployment. Identifies specific problems, proposes fixes and validates them.
npx skills add sickn33/agentic-awesome-skills --skill production-code-audit -a claude-codeWhat production-code-audit does
production-code-audit scans an explicitly defined section of your repository — specific files or directories you choose — and flags security vulnerabilities, incorrect logic and performance bottlenecks. For each issue found, it shows the path and line number, explains the risk, proposes a minimal fix and tests the fix on real data.
Take SQL injection as an example: if a query is assembled by string concatenation, the skill replaces it with parameterized binding to your database driver and validates the change against normal input, empty values and quote-bearing strings. Each finding includes the observed behavior, why it matters and the rationale behind the proposed repair.
The output report shows what was checked, which issues remain unresolved (e.g., gaps that need environment-specific validation or production access) and readiness status. This is not a production certification and does not replace manual code review, but it catches obvious flaws before they reach deployment.
What it helps with
- find and fix SQL injection in database queries
- detect unsafe user input handling and validate fixes
- identify leaked secrets and sensitive data in code
- spot performance bottlenecks in critical paths
- confirm error handling logic is correct and secure
Example prompts for the agent
- audit src/auth.ts for security issues before production release
- scan all files in api/ and fix vulnerabilities you find
- optimize database queries in db/models/ and show they run faster
How to install production-code-audit
1Skills CLI (Vercel)
npx skills add sickn33/agentic-awesome-skills --skill production-code-audit -a claude-code2Manually: put the files in place
~/.claude/skills/production-code-audit/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/production-code-audit/
1Skills CLI (Vercel)
npx skills add sickn33/agentic-awesome-skills --skill production-code-audit -a codex2Manually: put the files in place
.agents/skills/production-code-audit/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add sickn33/agentic-awesome-skills --skill production-code-audit -a cursor2Manually: put the files in place
.cursor/skills/production-code-audit/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install sickn33/agentic-awesome-skills production-code-audit2Manually: put the files in place
.github/skills/production-code-audit/SKILL.md1Skills CLI (Vercel)
npx skills add sickn33/agentic-awesome-skills --skill production-code-audit -a gemini-cli2Platform CLI
gemini skills install https://github.com/sickn33/agentic-awesome-skills --path skills/production-code-auditManually: put the files in place
.devin/skills/production-code-audit/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add sickn33/agentic-awesome-skills --skill production-code-audit -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set80
The whole set →Similar
Questions about production-code-audit
How do I install production-code-audit for Claude Code?
Run npx skills add sickn33/agentic-awesome-skills --skill production-code-audit -a claude-code, then open ~/.claude/skills/production-code-audit/SKILL.md for agent instructions.
What does production-code-audit do?
It finds security flaws, logic errors and performance issues in the code you scope, proposes repairs and validates them. It only examines the files and directories you explicitly select.
Does this replace code review?
No. production-code-audit catches explicit issues like SQL injection, credential leaks and broken error handling, but cannot assess overall logic or architecture. Use it as a first-pass check before human review.
Source text
SKILL.md · MIT
---
name: production-code-audit
description: "Audit an explicitly scoped codebase for evidenced security, correctness and performance issues; implement authorized targeted repairs and report validation plus residual readiness gaps."
risk: critical
source: community
date_added: "2026-02-27"
---
# Production Code Audit
## Detailed Guide
Read [the detailed guide](references/detailed-guide.md) before executing this skill. It retains the complete procedure and reference material. Treat its safety, prerequisites, and validation requirements as mandatory. For focused work, load the relevant sections; for end-to-end work, read the guide completely.
## When to Use This Skill
- Use when user says "make this production-ready"
- Use when user says "audit my codebase"
- Use when user says "make this professional/corporate-level"
- Use when user says "optimize everything"
- Use when user wants enterprise-grade quality
- Use when preparing for production deployment
- Use when code needs to meet corporate standards
## Worked Example: Query Repair
For a request-controlled email used in a concatenated PostgreSQL query, trace the input and confirm the driver, then replace concatenation with its parameter-binding API:
```typescript
// pg-compatible example; driver and database fixtures must be supplied.
const result = await db.query('SELECT id FROM users WHERE email = $1', [email]);
```
Validate a normal match, no match and a synthetic quote-containing input. Record actual commands and results; do not assert the test passed from the snippet alone. If a credential was found, removing it from source does not revoke it: report rotation and history/artifact exposure to the authorized owner without copying the value.
## Output Example (Illustrative Structure)
```markdown
Scope: repository, base/head, files fully read, excluded/unavailable files.
Finding: path:line, trigger, observed behavior, impact and severity rationale.
Repair: minimal change and why it preserves the intended behavior.
Validation: command/environment/result, or explicitly not run with reason.
Remaining gaps: unsupported runtime, unreviewed deployment, external configuration.
Readiness: evidence available and specific unresolved criteria; no blanket certification.
```
Any metrics must come from reproducible measurements with dataset, environment and baseline/head. Zero scanner findings does not mean zero vulnerabilities, and OWASP Top 10 is an awareness list rather than a “compliance” certificate. An audit request does not authorize deploying, provisioning telemetry/caches or contacting third parties.
## Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
© sickn33 · MIT · sickn33/agentic-awesome-skills