skill

production-code-audit · davila7 — Claude Code skill: audit and install

Q: How do I install production-code-audit in Claude Code?

Run `npx claude-code-templates@latest --skill development/production-code-audit`.

This skill scans a codebase, finds architecture, security, performance, and quality issues, then applies fixes. Use it when preparing a project for production.

Install into Claude Code · claude-code-templates All methods and platforms ↓

npx claude-code-templates@latest --skill development/production-code-audit

Open on GitHub

What production-code-audit does

The skill reads project files recursively and maps the stack, entry points, dependencies, architecture, and data flow. Its line-by-line review covers circular dependencies, tight coupling, insecure queries, exposed secrets, missing validation, inefficient database access, code duplication, complex logic, test gaps, and production-readiness checks.

It then applies changes across the codebase. The workflow can split oversized classes, address security flaws, improve queries and algorithms, add tests, set up logging, monitoring, and health checks, and extend project documentation. Afterward, it runs the tests, checks the changes, and produces a report with before-and-after metrics.

The skill edits architecture and project infrastructure automatically, so review its changes in a working branch before merging. Claude Code installation uses npx claude-code-templates@latest --skill development/production-code-audit.

What it helps with

scan a codebase line by line
detect SQL injection and hardcoded secrets
untangle circular dependencies and oversized classes
fix N+1 queries and inefficient algorithms
cover critical paths with tests and production checks

Example prompts for the agent

Make this project ready for production and fix the issues you find.
Audit the whole codebase for security, architecture, performance, and testing problems.
Scan the project, apply the necessary fixes, and report what changed.

How to install production-code-audit

1claude-code-templates

npx claude-code-templates@latest --skill development/production-code-audit

2Skills CLI (Vercel)

npx skills add davila7/claude-code-templates --skill production-code-audit -a claude-code

3Manually: put the files in place

~/.claude/skills/production-code-audit/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/production-code-audit/

Manually: put the files in place

.agents/skills/production-code-audit/SKILL.md

For all projects use ~/.agents/skills/

Manually: put the files in place

.cursor/skills/production-code-audit/SKILL.md

Cursor also reads .agents/skills/ and .claude/skills/

1GitHub CLI

gh skill install davila7/claude-code-templates production-code-audit

2Manually: put the files in place

.github/skills/production-code-audit/SKILL.md

Platform CLI

gemini skills install https://github.com/davila7/claude-code-templates --path cli-tool/components/skills/development/production-code-audit

Manually: put the files in place

.devin/skills/production-code-audit/SKILL.md

The legacy .windsurf/skills/ path still works

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about production-code-audit

How do I install production-code-audit in Claude Code?

Run npx claude-code-templates@latest --skill development/production-code-audit.

What does production-code-audit do?

It inspects the full codebase, identifies architecture, security, performance, quality, testing, and production-readiness problems, then applies fixes and checks the result.

What does production-code-audit examine?

It reviews dependencies, database queries, validation, authentication, test coverage, logging, monitoring, health checks, and documentation.

production-code-audit by other authors comes first.

production-code-audit sickn33 Skill for systematic code review covering security flaws, logic errors and performance issues before deployment. Identifies specific problems, proposes fixes and validates them. CX Codex +1 1,200installs improve-codebase-architecture Matt Pocock This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review. 1,163,035installs tdd Matt Pocock Guides the red-green TDD loop: ensures tests are written first, keep them at public interfaces, and avoid coupling to implementation details. 1,141,062installs triage Matt Pocock This skill moves issues and external PRs through triage states, verification, and agent briefs. It fits maintainers managing an issue queue. 990,453installs codebase-design Matt Pocock This skill helps design modules with small interfaces and hidden complexity. Use it when refactoring code, choosing a seam, or making tests easier to write. 850,344installs code-review Matt Pocock Reviews changes from a chosen reference point against repository standards and the originating spec. Use it for a branch, PR, or work in progress. 789,521installs implement Matt Pocock Implements work from a specification or tickets, following a test-driven flow and ending with review and a commit. Use it when a coding task needs a defined delivery routine. 774,700installs

From the same set495

The whole set →

blueprint-mode-codex A subagent that picks one of four workflows for a task and verifies every step against the project files instead of guessing. 201installs prompt-engineering-instructor Shows your agent how to pull typed data out of model responses with Instructor and Pydantic, retries included. 198installs tanstack-query-expert This skill guides TanStack Query work in React and Next.js, from query design and cache handling to mutations and server-side hydration. Use it when building or revising data-fetching flows. 196installs voice-agents Walks you through picking a voice agent architecture, budgeting latency and handling interruptions without awkward pauses. 194installs monte-carlo-simulator A slash command that runs Monte Carlo simulations: probability distributions, confidence intervals and risk metrics. 193installs tdd-gate The hook blocks edits to production files until a matching test exists. Useful if you want the agent to keep the TDD order. 192installs debug-window Opens a live-tailing debug log window when Claude starts with --debug or -d, then closes it when the session ends. 189installs semantic-kernel-dotnet A Claude subagent that writes and refactors .NET code for Semantic Kernel, checking the current Microsoft docs instead of trusting its own memory of the API. 189installs