Autonomous terminal AI agent for workflows and feasible project procedures. Co-Worker Co-Wrangler 🐙

Agent skills that make Claude Code (and other AI coding agents) genuinely better at infrastructure, scheduling, and configuration work. Battle-tested, zero-dependency.

Five agent skills that cut your coding agent's token weight: weigh in, read the bill, slim the replies, cap the thinking, cut bloated sessions. Claude Code, Codex, Cursor, any SKILL.md agent.

PenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.

Skill suite for better usage of agent ( openclaw, hermes and more)

Catch what's off before you ship. A Claude Code skill that audits UI and routes each issue to layout, interaction, copy, or engineering.

Harness agnostic skill pack for AI coding agents that audits codebases for technical debt across ten categories

Turn your ai agent into senior engineer..The result is fast code that fails slowly. AI Agent Skills solves this by giving agents the same disciplined workflows senior engineers use

Production-ready skills for AI coding agents. 13 skills, 9 agents, harness hooks & quality gates (signed optional for long sessions). Plan, build, test, debug, ship. Any repo, any language. Claude Code native, universal LLM compatible.

Canonical AI engineering workflow skills, aggregated by wakqasahmed/skills

Engineering discipline for AI harnesses. Drop-in skill library for LLM coding agents.

Claude Code skill suite — auto-generate GeneralUpdate auto-update integration code for any .NET app in under 5 minutes. Covers scaffold, UI, strategy, advanced, and troubleshooting.

Operational doctrine as installable skills for Claude Code and Codex — the DEViance Intelligence method pack.

Build Claude skills for B2B demand gen, RevOps, and marketing leaders to improve HubSpot, ABM, pipeline, and sales alignment

Intelligent Agent-Skill dependency butler: discover, security-audit, quality-grade, and install Agent Skills into any AI coding agent (Claude Code, Cursor, Codex, Gemini, Hermes, OpenClaw).

🧿 Minimal but effective AI agent skill definitions in 100 lines or less.

Production-grade coding workflow, execution scaffolding, and tuning skills for OpenClaw agents, part of the MyClaw.ai ecosystem.

Hermes Agent skill for safely delegating repository work to Cursor CLI (agent), utilizing the newest Grok models.

Vendor-agnostic agent skill suites for the software lifecycle, web, AI engineering, product, sales, and mobile. Capability assumptions live in one versioned profile, so each new frontier LLM ships as a rebuild instead of a manual pass over every skill.

Easy-to-use, high-quality threat modeling agent skills.

AI agent skills for Pwnote Pentest Notebook

Salesforce Org Intelligence for AI agents - a read-only, offline, source-available MCP server and CLI answering metadata, dependency, permission, Apex and Flow questions grounded in real retrieved org metadata.

A production full-stack engineering skill suite for AI coding agents—covering UI, UX, security, databases, auth, caching, testing, performance, and deployment.

Geospatial MCP server for earthquake, tsunami, volcano, disaster, and FX data queries.

Portfolio risk analytics MCP server — VaR, Monte Carlo, stress testing, and more.

GPU-accelerated MCP server for molecular dynamics, N-body simulations, and particle systems

An MCP server for MySQL databases.

Zero-trust MCP security proxy with policy enforcement, PII scrubbing, approvals, and audit trails.

Dokploy MCP server: manage apps, Docker Compose, databases, domains, backups, and servers.

Tencent Lexiang AI knowledge base MCP server for searching, managing entries, and editing docs.

Foundation MCP server — chain discovery, daemon management, health checks, raw transactions

Crypto & equity orderflow: whale detection, spoofing, liquidation heatmaps, smart money for AI

Agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more by @JohnWayneeee

持续分享我自己编写、长期使用并不断打磨的 Claude Code Skills。欢迎使用，更欢迎你动手做出自己的。

Inputs the content of any video into Claude Code prompt / context window as a multimodal bundle of voice transcription and data summary, time synced with keyframes - screenshots of key moments from the video so it can be used for all further requests related to that content.

Open-source agent skills for Claude Code, Codex, GitHub Copilot, and other coding agents: GPT-5.6-style rigor, delegation, linear probes, and self-evolving workflows.

A ready-to-use Claude Code project scaffold — rules, commands, skills, agents, and hooks in one command.

CSS development workflows with Tailwind composition, semantic naming, and dark mode by default

Stop your AI from shipping half-baked code. A disciplined senior-engineer workflow for Claude Code (spec, vet, build, prove, review, seal, ship) that keeps each feature's state on disk, catches spec drift mid-build, gates every phase on your project's principles, and refuses to claim "done" without proof.

Claude Code skills for web scraping & content extraction — Twitter/X tweet scraper, Xiaohongshu (Little Red Book) OCR to Markdown. CDP + httpx architecture.

AI's biggest bug isn't wrong code — it's original code. Character-driven coding skill: copy-paste hierarchy, code-as-memory, progressive disclosure.

Claude Code skills and plugins for verification-first development, independent code review, and skill engineering. 19 skills across 3 plugins.

Build a complete, secure SaaS end to end in Claude Code: prevention-first security (not audit), real Stripe payments (not just a catalog), and 15 lifecycle skills. Pairs with Superpowers — needs nothing else.

Usage-aware status line for Claude Code: session & weekly rate-limit gauges with reset countdowns and a precise context-window meter, plus tokens, git & weather. Template-driven and extensible — set it up by chatting with Claude or via a TUI. Pure-stdlib Python, no pip install. macOS, Linux & Windows.

Growth marketing skills for Claude Code, Cursor, and any AI agent: SEO, CRM, marketing automation, inbox triage, and pre-launch QA. Paste one prompt and your agent installs the method, then applies it to your own accounts.

Two Claude Code skills for setting up and maintaining a best-practice Claude Code configuration, distributed as a Claude Code plugin.

Frontend/Next.js Claude Code Skills — curated + custom

Local, folder-first LLM knowledge bases: format spec, CLI, MCP server, and agent skills.

Glanceable Claude Code and Codex state in your terminal tabs: white=idle, blue=working, orange=waiting. Multi-terminal (iTerm2, WezTerm, AI Power Term), a live status bar with Anthropic usage limits, /sfl and /nil window save-and-restore, and twelve companion skills. macOS only.

🛠️ macOS dotfiles + my Claude Code config — GNU Stow managed

Curated Claude Code plugins by Digital Pine. Framework setup, auditing, and modernization skills.

20 Claude Code skills for evaluating business ideas — bootstrapper-first, revenue-focused

Claude Code skills to bootstrap, compact, and maintain AI-readable project documentation — doc-init · doc-compact · doc-update

A collection of custom Claude Code Skills to supercharge your development workflow.

Lightweight Claude Code skills for daily AI-assisted development workflows.

Claude Code plugin with skills shared across project

AI-native version number toolkit in Go — Skills + MCP + SDK + CLI. Parse, compare, sort, group, check constraints & range-query version numbers. Works with Claude Code, Codex, Cursor, Windsurf, Cline, VS Code Copilot.

Open-source AI Skills library for building, improving, and scaling modern SaaS applications.

Vault-first toolkit for Claude Code — curated plugins over an Obsidian-compatible knowledge vault, governed by an explicit contract, gated by evals, continuously delivered.

Production-grade configuration management for Claude Code. Hooks, agents, skills, multi-project orchestration.