🔍 Discover + safety-vet Claude Code extensions before you install them - a 0-100 trust score for discovery + a 1-5 static-scan risk verdict, SHA-pinned install. Skills/MCP/plugins/commands.

A complete terminal-style UI design system for IDE Skills

Production-grade financial UI skills for Claude Code. Composable correctness + 10 aesthetic styles (Bloomberg, TradingView, Robinhood, Coinbase, Financial Times, Massive, Wise, and more).

The world's most advanced AI-powered research paper creation framework — built for the top 0.0001%

AI学术工作流 · 乔淼PhD「AI学术训练营」skills 库：选题 / 文献搜索 / 文献分析 / 研究设计 / 数据分析 / 全文初稿，30 个 skills 拆到步骤颗粒度，单个可独立运行、可自由组合（Claude Code / Codex）

Generate native OmniGraffle .graffle files programmatically

Claude Plugin for CompChem , Drug Discovery & Organic Chemistry reasoning

Structured scientific reasoning skill for AI agents — Claude Code, OpenClaw, Hermes, Pi-Mo, Codex, SkillsMP

29 free Claude Skills for SEO and AI search. Built by Hawk Academy + StudioHawk. Drop into Claude Desktop and run.

Turn AI agents into team SMEs. Kluris builds a shared, human-curated knowledge brain (decisions, constraints, incidents, tribal knowledge) as markdown in a git repo. Queryable via slash commands from Claude Code, Codex, Cursor, Windsurf, Cline, Gemini CLI.

Claude Code plugins by System Operator - alto.index, tinydot, and more

Your AI agent skill doctor - 5-dimension scoring + security gate + leaderboard

Twelve Claude Code skills enforcing strict code quality, security, and modern language patterns across TypeScript, Rust, Swift, Go, JavaScript, and PostgreSQL.

The SAP consultant's AI operating system - enforced workflows, checklists, and hard gates for Claude Code. Debugging, estimation, and go-live readiness.

Skills that make Claude dangerously good at your workflow

Audit, grade, and rewrite generic AI-slop patterns in prose, social posts, UI/design, and code. Use when asked to de-slop writing, humanize AI copy, grade a draft, review a landing page or generated interface, remove vague claims and repetitive rhetoric, or inspect AI-written code for generic abstractions and happy-path-only logic.

AI 漫剧 / MV 端到端制作流水线 Skill 套装 · 1 小时出方案，180 元跑成片 (Claude Code Skills)

Human-in-the-loop skill for AI agents — create tasks for humans to review, approve, or complete. REST API + MCP.

Open-source thinking-framework skills that make rigorous reasoning executable for AI agents — first-principles, inversion, second-order thinking, Occam's razor, Bayesian reasoning. Built by deciqAI.

A three-gate Agent Skill for editorial paper-collage B-roll prompts.

会看画面的 AI 剪辑 Skill — 先用视觉模型看懂每段素材拍了什么、哪几秒能用，再决定取舍、顺序、节奏、调色和配乐。An AI editing skill that actually watches your footage.

Independent Agent Skills for repository analysis, planning, implementation, review, delivery, design, and runtime verification.

Reader-first academic writing skill for Codex and Claude Code

Agent skills that give GitHub Copilot, Claude Code, and other AI coding assistants procedural knowledge of J.P. Morgan Payments APIs. Walks external developers from onboarding and credential setup through OAuth implementation and live API integration with Checkout and Online Payments.

Rule-first Georgian grammar, punctuation, translation, and writing QA skill for OpenAI Codex.

Agent skills for design engineers: state machine design, component API design, engineering writing, changeset writing.

Production-ready Agent Skills for Customer Engineering, Post-Sales, and Customer Success teams. Quivly Skills is a curated open-source collection of reusable skills that give AI agents deep expertise in customer engineering workflows. Every skill follows the official Agent Skills specification.

Liquid Glass CSS/SVG skill for AI agents — Apple iOS 26 refraction effect

a kinds of skills can run in any agents, totally free.

Agent Skill for AI coding assistants (Cursor, Copilot, Windsurf, Claude) - Adobe Express add-on development with OAuth patterns and code samples

Claude agent skill that plans multi-step work as a dependency graph. Subagent fan-out, layered fan-in, model tiering, verification retry loops, human approval gates. No framework, just instructions.

a startup but not simple agent demo using google adk.

Race a baseline vs a skill or MCP on real tasks. Hard checks show if it got better, faster, or cheaper. Numbers, not vibes.

AI coding agent skills for ZenML MLOps workflows — quick wins, pipeline setup, and more

A portable agent skill that stops AI coding agents from overfitting or gaming tests they don't own.

Background pattern-finding for a Zo Computer workspace. Modeled on Anthropic's Dreaming feature for Claude Managed Agents.

Claude skills for agencies that ship — 8 production-tested Agent Skills (brief, approvals, reports, quotes, shooting, social calendar). EN+IT.

resumable engineering loops for Claude Code — audit a codebase into an acceptance-gated backlog, then execute it one verified commit at a time.

Curated agent skills for TxnLab's Algorand ecosystem — NFDomains, use-wallet, Haystack Router

76 AI-agent security skills for Kali Linux tools — pentest, red team, forensics, OSINT, and more. Machine-readable skill definitions by Red Hound InfoSec.

Public Claude Code skills and agents from simiancraft. Marketplace-installable.

ProgramAsWeights agent skill - compile natural-language specs into tiny, locally-running neural functions for fuzzy text tasks (classify, extract, repair, fuzzy-match, triage, route). npx skills add programasweights/skills

Specialized Agent Skills to automate GitHub workflows using the GitHub CLI

Coding principles for Claude Code and AI agents. KISS, DRY, SOLID, YAGNI, separation of concerns, and more. Language-agnostic skills that help agents ship production-quality code.

A reusable skill for turning SwiftUI codebases into a governed, previewable, tokenized UI workflow.

An Obsidian vault health checker for finding broken links, orphan attachments, duplicate files, frontmatter drift, stale tags, and large files.

Audit your Salesforce RevOps. Then fix it. A Claude Agent Skills pack for Salesforce admins and RevOps practitioners.

45 production-grade AI agent skills for real dev workflows. Code review, shipping, docs, git. Works with any skill-compatible agent.

Agent skills for the VivaDicta for Mac CLI (vivadicta). Install with npx skills add n0an/vivadicta-cli-skills.

AI Agent skill for Zotero — search your local library with zero dependencies, no MCP server, no embedding

SendX's best practices for message performance, email sending deliverability and compliance.

Code review tool for arbitrary diffs (Phoenix + Rust CLI)

Catch your AI agent lying about "done" A one-file proof-gate for Claude Code, Cursor & Codex. it must verify before it can finish

Repository-native agent memory, skills, AGENTS.md, llms.txt, and knowledge workflows for coding agents.

Structured alignment audit for AI agents and creators. Checks drift across 4 pillars and 6 dimensions — from design currency to artifact verification. Report-only, never auto-fixes.

SOC子引擎，基于agent-skills技术通过AI赋能SOC平台，对SOC告警进行研判、调查、响应。

102 AI Agent Skills for the full product lifecycle. Compatible with Trae / Claude Code. 9 modules from discovery to launch to growth. | 102 个覆盖产品全生命周期的 AI Agent Skills，兼容 Trae / Claude Code，9 大模块从探索发现到上线增长。