Standalone skills for Claude Code and Codex: product discovery, architecture, implementation, technical foundations, reviews and delivery, with explicit scope and verification.

testing devops openai developer-tools code-review software-architecture codex performance-optimization ai-agents github-actions developer-productivity software-development-lifecycle product-discovery anthropic ai-driven-development agent-skills claude-code plugin-marketplace claude-code-skills codebase-audit

• Updated Nov 11, 2026
• Shell

The most complete Claude Code toolkit in the wild. 348 skills, 80 commands, 35 agents, stage-gate pipelines, multi-model orchestration, and thinking frameworks -- distilled from six months and 19,030 commits across 104 repositories.

visualization developer-tools multi-model slash-commands claude ai-agent ai-development prompt-engineering claude-code agent-os stage-gate codebase-audit html-visualization

• Updated Aug 16, 2026
• Python

Engineering guardrails and reusable skills for AI coding agents: project context, planning, documentation, verification, Git workflows, bug fixes, and codebase audits.

developer-tools cursor harness bug-fixing ai-agents claude developer-workflow ai-coding agent-skills claude-code codex-cli codebase-audit harness-engineering ai-harness dev-harness

• Updated Nov 10, 2026
• Python

LLM-assisted code auditing. 54 phases, custom overlays, accountability.

security audit code-review code-quality cursor copilot devsecops windsurf code-audit anthropic llm-agent ai-code-review llm-agents mcp-server agent-skills claude-code ai-coding-agents cursor-composer codebase-audit

• Updated Oct 10, 2026
• Shell

Selective Intelligence turns minimal intent into grounded, token-efficient AI work: research, product design, one-prompt websites, verified UI/UX, repository realignment, and developer-grade execution across AI clients—free, open, and model-neutral.

product-design developer-tools cursor codex ux-design frontend-development github-copilot gemini-cli ai-coding agent-skills vibe-coding claude-code token-efficiency intent-alignment kiro codebase-audit repository-audit human-intent selective-intelligence selective-inheritance

• Updated Nov 1, 2026
• Python

Evidence-driven codebase hardening skill. Audits OWASP Top 10:2025, OWASP LLM and Agentic Top 10 when AI is detected, supply chain (SBOM, SLSA v1.2), reliability, and tests. Reports only. Agent Skills layout.

security-audit static-analysis supply-chain owasp code-quality security-scanner owasp-top-10 devsecops vulnerability-scanner slsa ai-code-review ai-coding agent-skills codebase-audit

• Updated Nov 5, 2026
• JavaScript

A Claude skill that audits a codebase end-to-end and produces a top-5-per-dimension improvement plan across seven lenses (Performance, Functionality, Stability, Reliability, Security, Usability, Attractiveness).

code-review claude anthropic claude-code claude-skill codebase-audit

• Updated Jun 8, 2026

Grok Build skill: audit, validate, and improve existing (brownfield) codebases with assumption-aware analysis and optional PR execution

grok ai-agents brownfield agent-skill codebase-audit grok-build

• Updated Jun 8, 2026
• Shell

Gemma Doc Pro is a privacy-first, serverless codebase auditing and interactive documentation platform.

serverless ai-tools codebase-audit

• Updated Jun 20, 2026
• TypeScript

🩺 Zero-dependency .env & .env.example linter, synchronizer, and code auditor CLI. Prevents missing environment variables and deploy crashes.

python cli security devops dotenv linter configuration secrets developer-tools synchronizer codebase-audit

• Updated Oct 30, 2026
• Python

Codebase Health Audit Prompt

refactoring security-audit static-analysis devtools code-review software-engineering code-quality technical-debt developer-productivity prompt-engineering code-health ai-prompt git-analytics llm-prompt codebase-audit

• Updated May 18, 2026

Self-improving repo health remediation skill with audit/fix/diff modes, evidence coverage, counter-review, and stable HP-* findings.

testing developer-tools cursor codex ai-agents openai-codex agent-skills agent-memory claude-code claude-skills skill-md repo-health codebase-audit self-improving-agents reliability-remediation

• Updated Jul 4, 2026
• Python

A fast, local-first repository health check and onboarding brief with strict CI gates and shareable reports.

python cli static-analysis onboarding developer-tools github-actions repository-health codebase-audit

• Updated Sep 21, 2026
• Python

Audits AI-generated codebases for the six failure modes that cause production collapse: disconnected schema, missing RLS, exposed secrets, broken auth, unwired integrations, and N+1 queries. Outputs a severity-ranked remediation register, not inline fixes.

security-audit developer-tools code-review technical-debt devsecops row-level-security code-audit ai-security anthropic ai-generated-code secrets-scanning vibe-coding claude-code n-plus-one claude-skill codebase-audit

• Updated Sep 20, 2026
• Shell

Multi-phase codebase recon → improve for Claude Code: map → hunt → gated fix/optimize, plus feature suggest/plan. Installable plugin.

refactoring code-review claude-code claude-code-plugin claude-skill codebase-audit

• Updated Jun 22, 2026

Multi-host Agent Skill — evidence-backed whole-repo architecture and maintainability audit. Cursor, Claude Code, Codex, Antigravity. macOS/Linux/Windows.

python static-analysis cursor codex maintainability antigravity agent-skills claude-code codebase-audit architecture-audit

• Updated Aug 21, 2026
• Python

Toque: AI-powered codebase grading, planning, auditing, and operational readiness. Claude Code plugin.

developer-tools software-quality ai-assisted-development operational-readiness claude-code-plugin codebase-audit

• Updated Sep 13, 2026
• JavaScript

Audit code health with AI using evidence-based checks, risk metrics, and prioritized findings for clear refactor decisions

refactoring static-analysis devtools code-review software-engineering code-quality technical-debt developer-productivity prompt-engineering code-health ai-prompt git-analytics claude-code llm-prompt codebase-audit

• Updated Oct 14, 2026

Veridence: Deterministic Algorithmic Technical Due Diligence (The Sovereignty Protocol & 4-Quadrant Infrastructure Risk Quantification). Aligned with the August 2026 Technical Report.

slack-bot compliance private-equity mergers-and-acquisitions ast-parsing deterministic-analysis codebase-audit technical-due-diligence infrastructure-risk sovereignty-protocol

• Updated Oct 18, 2026