Production-ready security skills for Claude Code and compatible AI coding agents

Engineering habits for coding agents that keep scope, context, and quality under control. Build with intent — 如切如磋，如琢如磨

Reusable Claude skills (SKILL.md) for Cowork/Claude Code, focused on legal AI: pure-Python BAILII downloader solving Anubis proof-of-work, UK employment-law verifier, legal writing, prompt generators

9-stage enterprise development pipeline for Claude Code. TDD, adversarial testing, mechanical verification. Any stack.

Next.js to Postgres — build and ship a modern web app end to end.

Audit a GitHub repository for risk before integrating it into your stack. Seven-dimension framework with weighted scoring and ADOPT/EVALUATE/CAUTION/AVOID verdict.

Yuheng's Claude Code skills marketplace

GitHub-only and Linear-only Claude Code skills that port the jot CLI loop — capture brain-dumps into well-formed tracker issues, decide what to work on next, and keep the backlog tidy. Each skill is a single SKILL.md invoked from inside Claude Code.

Claude Code, Codex, OpenClaw and Ottili AI Skills - powered by Ottili ONE

Essential Claude Skills I Use

Kilo/agent skill for building OpenCode extensions, plugins, and integrations

Claude Code skills for shipping: single PRs, parallel PR fan-out, multi-phase epics, and a ruthless pre-ship critic. One session chairs; context never splits.

Grade your AI-agent repo. One command, one report card — scored, evidence-backed reviews (reliability, security, prompts, evals, token cost, UX, accessibility) for AI/LLM apps.

Versionierte Heimat meiner Agent Skills für Claude (claude.ai, Claude Code, API).

Custom Claude Code skills, installable via npx skills add dlomibao/dl_skills

Skills públicas da MSCREATIVE.SYSTEMS para o Claude. Ferramentas de decisão, em PT-BR. Primeira: premortem.

DDD + TDD harness for Claude Code — 5 hooks enforce Domain layer purity, cross-context call rules, and red-green discipline at edit time. Ships 4 skills + project templates.

Installable library of AI coding agents, skills, commands, guides & tools — the copy-paste mirror of agentscamp.com

Claude Code skills for genuine property-based testing: discovery workflow, anti-patterns, Hypothesis & beyond.

LLM agent skills for software architecture analysis and review. This repository equips AI agents with reusable capabilities to evaluate system design, review architecture decisions, identify risks, analyze trade-offs, and recommend improvements for scalable, reliable, and maintainable systems.

Multi-LLM Plan and TDD flow

Reidworks skills marketplace — install once, every shared skill loads in Cowork and Claude Code.

AI dev infrastructure framework for Claude Code. /dotclaude:bootstrap authors CLAUDE.md + docs/ + .claude/ tuned to your project. Per-domain: design (showpiece), coding, planning, testing, data, ai-workflow.

Companheiro executável de Deep Claude · O Currículo Executivo do Ecossistema Anthropic

Move old code to modern stacks without a risky big-bang rewrite.

Claude Code plugin marketplace: a set of domain experts (subagents) grouped into installable plugins.

Agentic CLI tool skills for Claude Code — 7 domain-grouped skills covering 26 CLI tools

Java books distilled into Claude Agent Skills — bilingual (简体中文 / English) skills for writing and reviewing Java code. First skill: Alibaba Java Development Manual (Huangshan Edition).

Reusable, provider-agnostic AI team. Drop a project brief, get end-to-end delivery. 12 role agents + 112 skills + orchestrator + self-improvement. Works with Claude Code, Codex, or Gemini.

Pre-ship audit suite for Claude Code: 13 skills — security (OWASP), code quality, dependencies, GDPR/ISO compliance, accessibility (WCAG), SEO/GEO, forms, responsive, deploy readiness, and LLM hallucination risk — under one /audit plugin, with an orchestrator and a report differ.

Skills to make your AI coding agent an Arcjet security expert.

Spec-driven development skills for Claude Code: PRD → spec/contract → implement → contract-based evaluation with auto-fix

Ranks your installed Claude Code skills/agents for a task and routes to the best one — and learns from your ratings.

Agents and skills that bring Quality Engineering into AI-assisted SDLC workflows. badquality.dev

Defensive security skills for Claude Code and the Claude Agent SDK — web applications and generative AI systems.

A Claude Code skill written by Claude Fable 5: transfers its operating discipline to Opus, Sonnet & Haiku — do the same work on cheaper models without burning frontier-model tokens. Distilled from Anthropic's official Fable 5 prompting guide. EN + RU.

🎭 Persona — role-based operating modes for Claude. Hire an expert, not a tool: each persona is a mindset, a method, a quality bar, and the skills to deliver.

Project-scoped Zotero references for Claude Code — auto-triggering skill, vendored scripts, no MCP server. For surfacing curated literature while you code.

Production Postgres survival skills for Claude Code — schema design, safe migrations, query performance, connection pooling, autovacuum/bloat, and queue/partitioning patterns.

Slack for agents: threads, flat replies, cross-thread links, pull notifications

A Claude Code harness that turns a session into an agentic data engineer for SMBs — packaged as an installable plugin, built from a skillpack of skills that stand up a cheap, self-hostable Modern Data Stack (Tailscale + dlt + BigQuery + dbt + optional MCP), end-to-end and headless.

🧠 Custom skills for Claude AI — includes Smart Orchestrator (adaptive response depth) and Omni-Expert (precision expert persona selector). Plug-and-play SKILL.md files for Claude environments that support custom skills.

Open-source AI agent skills for Claude Code, OpenAI Codex, Cursor, and modern developer workflows.

Claude Code skills for bug bounty hunting and security-auditing web apps you own — recon, scope, report, triage, self-audit. Judgment, not tool wrappers.

A structured knowledge base and reference guide for mastering the .NET ecosystem, covering core fundamentals, advanced architecture, WPF, and interview preparation.

Claude Code plugin: m_* toolkit (m_plan plan->execute->verify, deploy/infra commands, Playwright full-test loop, m_code quality framework)

Coding agent skills to help projects adopt spec-driven development with durable product memory documents

A coherent, opinionated toolkit for documentation-driven development with twin-model adversarial checks.

Defensive security audit skills for Claude — tech-stack-keyed and audit-domain-keyed packs for SaaS apps.

Claude Code plugin marketplace for the hard, production-critical parts of engineering — backend reliability (API contracts, idempotency, rate limiting, resilience, caching, auth), adversarial code review, and frontend motion/UX.

Agent Skills for Kora Framework — compile-time DI for Java/Kotlin backend development.

Persistent Obsidian wiki pattern for LLM agents: starter template + init script + Claude Code skills for continuous, cumulative knowledge archives.

AI skills as executable code, not prose. A declarative framework for writing skills as syntax trees of named operations, distributed as agentskills.io-format Agent Skills.

Precise specs, redlines, and docs that eliminate guesswork at the design-to-code boundary.

Claude Code skills marketplace — backend & frontend engineering conventions + step-by-step third-party integration recipes: Stripe, Rapyd, CyberSource, UOB & wallet payments, Singpass/Keycloak OIDC & 3-D Secure, Twilio SMS, Docker & CI/CD. NestJS/TypeScript + React, language-flexible.

Claude Code skill: Conventional Commits + best-practice workflow + project-dialect scaffolding. Treats commits as durable history serving four readers — git log scanners, git blame tracers, git bisect hunters, and AI agents.

Agent Skills for character LoRA dataset tagging: booru tag auditing (keep/delete/replace with visual verification, dual-character support) and visual-weight prompt ordering. Production prompts of BooruDatasetTagManager+.

EU-first, stack-agnostic Claude Skills for auditing and remediating production-readiness across security, compliance, testing, reliability, observability, supply chain, data protection, and scalability.

Reusable Claude Code skills for managing public GitHub repos at commit, push, and release time, plus the generic repo files every project should carry.