A Claude skill for collaborative code architecture planning. Interviews you, challenges assumptions, audits for over-engineering, and produces a full architecture doc with diagrams. Supports web (Node/Express), game (Unity/C#), and C++/CMake projects.

LLM agent skills collection

Agent skills for Stitch MCP, Project Graph MCP, and Symbiote.js component generation.

Agent skills for Maestro end-to-end testing for Mobile and Web apps

Manage and generate API specs from requirements and stories using a structured, reusable skills-based approach focused on OpenAPI compatibility.

Official Agent Skills for Zot — teach Claude Code, Cursor & other AI agents to integrate Zot waitlists, emails, and subscriptions correctly using the official SDK and CLI.

Agent prompting skill for writing actionable instructions

Auto-maintained index of installed Claude Code / agent skills. Reduces skill discovery from ~12.5 min to ~15s for 150+ skills. Zero dependencies, SHA256 integrity, audit log.

A local-first coding-agent hygiene skill that audits installed skills, tool setup, and usage signals to help reduce context noise and keep agent workflows focused.

Universal self-driving mission runner for AI coding agents (Claude Code, Codex, Cursor, Gemini, ...)

so-me.studio Hermes Agent skill — registry tap for hermes skills install

Visual-first Agent Skill for Codex and Claude Code: Mermaid diagrams, timelines, tables, and note-ready explanations.

Local-first dashboard that shows whether AI coding agents actually loaded, read, or invoked the right skills.

Agent skills for unit, widget, UI, and end-to-end testing of mobile apps across platforms.

Agent skill to accurately persist context before compaction, restarts or handoffs.

Storytelling Operating System built on Claude Code — draft, rewrite, critique, and lint narrative voice across you + your brands. Ships with a Voice Fingerprint linter, an Audience Simulator (parallel persona subagents), and a Brand Guide PDF generator. File-based, no hidden state, hybrid protagonist model.

Runtime skill graph resolver for progressive disclosure of AI agent skills.

Dual-mode Claude skill that wraps AgriciDaniel/claude-blog into a complete publishing lifecycle. Mode 1 ships a new post via the 8-step workflow. Mode 2 audits an existing post and returns a prioritized retrofit list. MIT licensed. By @johnericforte.

Cross-agent coding skills for Claude Code, Cursor, Codex, Gemini, Copilot, and any tool that supports the Agent Skills spec.

Skills published by 5dive — drop-in SKILL.md bundles for Claude Code, openclaw, hermes, and any harness that loads skills.sh-format prompts.

Skills for automate workflows, assist in daily tasks, and enhance overall productivity.

Agent skill for writing execution-ready Codex goal handoffs

Local-first MCP server for agent skills — validate, lint, convert, optimize tokens, and sync across Cursor, Claude, Kiro, Windsurf, and VS Code.

Setup a PM OS Workspace.

Skills that know your codebase. Repo-grounded, contract-validated, agent-routable.

Fast ≠ efficient. A Claude Code skill + pre-push hook that makes AI coding agents check the math before `git push` — so they stop trading the user's two hours for their own twenty seconds.

Data Journalist Agent Transforming Data into Reproducible Multimodal Story

Biolytics Rhetoric Engine: a staged presentation cognition pipeline for user-led slide creation

All AI agentic development workflow I use myself and found helpful

Reusable skill for setting up lightweight shared workspace memory with AGENTS.md, PROJECT_PROGRESS.md, and WORKING_MEMORY.md.

GitHub Action: pin approved AI Skill behavior; block unapproved drift in CI.

🎨✨ Agent-driven toolkit for generating editable PowerPoint slides — skills, plugins, and design profiles.

Next.js Vercel Template — add real-time chat to any Next.js app via your AI coding agent. CometChat skills pre-installed at .agents/skills/.

Agent skills for Primitive — primitive-chat (email another agent and wait for the reply) and primitive-inbox (a managed inbox that receives mail). Works with Claude Code, Codex, Cursor, and 50+ agents.

Offline Ubuntu server recovery over USB with signed jobs and an agent skill

Production-ready AI agent skill for building, testing, deploying, and integrating confidential dApps with Zama FHEVM, Hardhat, fhevmjs, and ERC-7984.

Persistent, searchable persona knowledge base — MemPalace + Knowledge Graph + Karpathy LLM Wiki. Data layer for OpenPersona persona training pipeline.

Static + runtime linter for LLM agent prompts, skills, and tool definitions. Model-aware policy for Claude, GPT, OpenRouter.

Reusable capability packs for human-AI co-evolution in real work

An AI Agent skill & CleanMyMac alternative for LLMs (Claude/Gemini). It acts as a smart storage analyzer for macOS, Windows & Linux: the scanner collects disk data, and the AI Agent interprets, classifies UUID container apps, and builds a premium Apple-style interactive cleanup dashboard.

Curated agent skills, conventions, and workflows for building Java Android apps with AI coding agents.

《明日方舟：终末地》角色「庄方宜」角色扮演+任务协作Agent Skill.

ROSTR Agent — Self-improving multi-agent framework with built-in PAL, NPAO, RAG DAL, and Rostr Hub. Built on Hermes Agent by Nous Research.

Codex 프롬프트 패턴을 분석해 Skill 후보 생성·설치까지 지원하는 로컬 CLI | Local CLI that analyzes Codex prompt patterns and generates installable Skills

Agent skills for Stripe-native SaaS founders fighting churn — by Unchurn (https://unchurn.dev)

A meta-skill for AI agents: scaffolds new skills via structured interview, cookbook architecture, and cross-skill connection discovery.

Agent Skills 的插件市场（Claude Code marketplace）：市场登记若干插件，每个插件自带若干通用格式的 skill，也可脱离市场手动装进任意支持 Agent Skills 的 Agent。目前主要是操作 Obsidian vault 的 obsidian 插件。

Provider-neutral autonomous ML research paper writer — ideation -> LaTeX writeup -> peer review -> anti-hallucination numerical audit. Spun out from hermes-sci to remove Hermes-runtime coupling.

Audit persuasive copy (landing pages, emails, sales sequences) for missing influence principles using Robert Cialdini's seven principles + Pre-Suasion. Returns per-principle audit with prioritized fixes. MIT licensed. By @johnericforte.

把横向项目、企业系统、AI/RAG/机器人项目转成硕士论文主线的 Agent Skill

Two complementary AI agent skills for comprehensive mental health support: Crisis Detection for safety monitoring, and Praise Group for positive reinforcement.

Portable Markdown skill for AI vibe coding with specialised platform SDKs: Shopify, Salesforce, CRM/ERP integrations, commerce platforms, messaging bots, and workflows.

Transparency verifier for Agent Skills — verify that AI skills declare their behavior honestly. Scans code for network, filesystem, shell, and env access patterns.

Local web UI for managing AI agent skills through the skills CLI.

18 AI agent skills that catch what your agent misses: hidden code debt, false completions, missing error handling, context amnesia, imprecise UI edits. Self-improving with TF-IDF routing + SkillOpt loop. Cursor, Claude Code, Codex, Copilot. Install: npx skills@latest add Adit-Jain-srm/skill-forge

Import Excel and PowerPoint skills into Claude Code to automate spreadsheets and presentations using local filesystem access.

Xiaohongshu downloader skill and AI CLI adapters for Codex, Claude Code, Gemini CLI, and terminal use

Token-efficient Agent Skills for Claude — Pillar 1: meta-skills ≤650t, Pillar 1.5: coding discipline

GenPark Distilled Skill: wukong-workflow-automator