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

Blazing-fast WSL2 to Windows file search bridge for AI Agents via MCP

A collection of Claude skills.

Claude-Skill für systematische MCP-Server-Audits gegen einen kuratierten Best-Practice-Standards-Korpus · 68 Checks · 8 Kategorien · OAuth 2.1, OWASP, Lethal Trifecta, Schweiz-Compliance (DSG/ISDS) · MIT

Turn vague tasks into mission focused long runnig /goal prompts for Codex, Claude Code, Hermes, and autonomous AI agents.

Claude Code skill that finds the exact commit that broke it — describe the bug in plain English and it writes the check, drives git bisect in an isolated worktree, and explains why the guilty commit is guilty. 🎯

Claude Code skill that hunts flaky tests — separates flaky from broken, diagnoses the root cause (shared state, timing, ordering, network), fixes the cause, and proves it with 20+ runs. Retries and sleeps are banned. 🧪

Search GitHub for Claude Code skills, plugins, and agents — ranked by relevance + stars. Use as a Claude Code skill or a single-file web app.

Find a Verified Interview Scheduling Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for hr agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).

Measure Claude Code Adoption

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

A collection of skills for an AI agent that helps filing bug reports as GitHub issues

Universal toolkit for building, discovering, reviewing, testing, and securing Claude skills. 7 scripts, 10 reference docs, 6 workflows. Includes quality scoring, auto-testing, prompt injection detection, quarantine-based install, and conflict detection.

An AI-powered database architecture review framework that performs senior-level engineering audits for Prisma, PostgreSQL and relational databases

A Claude Code plugin that runs a full pentest engagement from inside your coding agent. Point it at a target and it works through recon, deep testing, exploit verification, chain-building, judging, and writes audit report.

Repo for Salesforce Agentforce Script

Turn any coding-agent harness into a disciplined personal knowledge-base builder — curation + transcription skills over plain Markdown. 双线知识库工具包:策展+转录,无需向量库。

A Claude Code skill that audits, rewrites, and guards code across 10 quality dimensions — SOLID, design patterns, security, performance, and more. Every finding cites a named principle; every fix is stack-specific.

A small library of Claude skills, built for real analytical work and validated before publishing.

Este repositorio agrupa skills reutilizables para Claude Code. Cada skill se define en su propia carpeta con un archivo SKILL.md que incluye el frontmatter (name, description) y las instrucciones que Claude seguirá al invocarla.

A complete, original suite of 12 Claude agent skills for SEO and growth. Runs audits, technical SEO, content, AI search visibility (GEO and AEO), SXO, schema, authority, CRO, and reporting off real data from Ahrefs, GSC, GA4, and Clarity, with every decision tied to leads and revenue. Built on the CITED framework by Avik Bal.

Atlas — Engineering Agent for Claude Code. Sprint planning, standup, task management, and coding agent loops.

A Claude Skill that turns Claude into a structured events research agent for B2B growth marketers.

A disciplined 10-stage autonomous agent pipeline (Reflexion, Tree Search, ReAct) for Claude Code and AI coding agents. Lifts local LLMs to senior engineering quality.

Claude Code skill for Fable 5 and Codex routing

Docs people actually read — READMEs, guides, changelogs, and specs.

Let AI research you back—answer ~15 multiple-choice questions to get YOUR AI config (CLAUDE.md / AGENTS.md / custom skills), instead of copy-pasting templates. By FantasyMax.

Audit and reduce Claude token usage in your context files. Measures cost, finds waste, safely compresses prose, preserves code. Zero dependencies.

DooTask 插件开发的 Claude Code 技能集：脚手架建插件 / 发版到应用商店 / 写优化 CLAUDE.md。安装：/plugin install dootask@dootask-skills

Export your Claude chat as a compact JSON snapshot. Resume anywhere — Claude, ChatGPT, Gemini — without losing context.

Knowledge base skill — search articles, detect gaps, create drafts, collect feedback via mcp-knowledge-base

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.

Claude Code skill that writes the end-of-session note your future self needs — what changed and why, the half-done state, the landmines, rejected paths, and next steps precise enough to run without archaeology. 🤝

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.

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.

Claude Code skills for querying the ecosyste.ms APIs

Zaira Labs building-for-agents Agent Skill: make a developer tool agent-ready, grounded in the open Zaira Standard v0.9.

Team-ready Claude Code skill pack: 15 multi-account integrations for Rails + React Native + e-commerce. Trello, Azure DevOps, Heroku, Shopify, Firebase, Sentry, Slack, Postgres, Maestro, Fastlane + 5 more. Real value: multi-account profiles, audit logging, safety gates, xlsx-testcases unique workflow.

Prototyping skills for AI coding agents. Astro, Tailwind CSS, DaisyUI workflow for designers. Turns product docs into a working coded prototype.

Claw-skills any thing

Maps any directory into an LLM-readable taxonomy — a Claude Code skill with an AgentIngress XML block for agent context injection

ByteStack Labs marketplace for Claude Code. Open reliability skills that audit AI which passes evaluation but fails in production. Every number reproducible.

用 AI Agent 做出你的第一个 AI 小项目，普通人也能上手实操。Stop tool-hopping. Ship your first AI MVP with agents.

Battle-tested Claude Code & Cowork skills that double your usage, same quality.

Two Agent Skills that make code understandable: turn a concept into staged, runnable learning code — or turn source code into a self-contained, annotated HTML walkthrough.

Comprehensive Claude Code skill bundle for Flare-family EVM development: chain registry, FTSO/FDC/FAssets/Smart Accounts protocols, Enosys + SparkDEX integrations, Flare-specific security overlays, and audit/gas/test workflows.

Environment deployment skill — health checks, promotion, rollback, drift detection

Agentic loop skill for building SaaS, DaaS, and AIaaS projects — as a Senior Software Developer. you would need the caveman skill.md file.

> 为项目生成**项目专属的 CLAUDE.md / AGENTS.md** + 活的 **TODO.md** 任务清单，让 Claude Code / Codex 真正读完并执行。 > 零依赖、零 hook、跨平台、自动维护。

White-box, OSWE-style security audit for Claude Code: traces source→sink, chains findings to unauthenticated RCE, verifies each chain, and writes an evidence-backed Markdown + HTML report. PHP · Node · Python · Java · .NET.

Open-source compliance skill pack for Claude Code, OpenCode, and other AI CLIs. Adds DPDP, GDPR, CCPA, HIPAA, and PCI-DSS knowledge + codebase scanning to any agentic AI assistant.

Outbound sales, autopiloted.

Opiniated AI Assistant skills to help you analyze and optimize your Azure cost

Session memory skill — typed state, recall, replay snapshots, and resumable workflows

A Claude skill that researches GitHub before you build, so you don't ship the 47th version of someone else's skill.

A Claude Skill that turns any codebase into an AI-ready project with project memory, session continuity, safe agent workflows, build/test discovery, context linting, review playbooks, and project health reports.

Linlin's curated AI agent harness configuration: workflow rules, skills, hooks, plugin recommendations, tooling preferences, and project templates. Loadable into any new project so a fresh /init can pick the relevant subset.