OpenAI-style agents
A practical list of reusable skills for OpenAI-style agent workflows, focused on installable open-source repositories, task fit, trust signals, and audit notes.
Builders creating OpenAI-style agent workflows that need reusable skills rather than one-off prompts. Ranked from the OpenAgentSkill index using quality, trust, freshness, adoption, and install readiness.
Search intent
These pages are generated from real registry records. The list below is not a generic article; every row links to a skill profile with install, trust, audit, and risk fields.
access to david ondrej's personal agent skills
Excellent quality, 2.7K stars, and a 100 use-case fit score.
Best suited scenario
Inspect source files
$ npx skills add davidondrej/skillsUse Playwright to interact with and test local web applications, capture screenshots, debug UI behavior, and inspect browser logs.
Excellent quality, 180K stars, and a 20 use-case fit score.
Best suited scenario
Navigate pages
$ npx skills add anthropics/skills --skill webapp-testingA relentless interview to sharpen a plan or design.
Excellent quality, 285K stars, and a 17 use-case fit score.
Best suited scenario
Move data between tools
$ npx skills add mattpocock/skills --skill grill-meEliminates predictable AI writing patterns from prose while preserving specific meaning and reader trust.
Excellent quality, 16K stars, and a 17 use-case fit score.
Best suited scenario
Move data between tools
$ npx skills add hardikpandya/stop-slop --skill stop-slop280+ free n8n automation templates — ready-to-use workflows for Gmail, Telegram, Slack, Discord, WhatsApp, Google Drive, Notion, OpenAI, and more. AI agents, RAG chatbots, email automation, social media, DevOps, and document processing. The largest open-source n8n template collection.
Excellent quality, 23K stars, and a 26 use-case fit score.
Best suited scenario
Move data between tools
$ npx skills add enescingoz/awesome-n8n-templatesSelf-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption
Excellent quality, 14K stars, and a 17 use-case fit score.
Best suited scenario
Navigate pages
$ npx skills add lsdefine/GenericAgentApplies Cursor's prose-discipline rules to remove filler and AI writing tells from agent-facing and user-facing text.
Excellent quality, 4.8K stars, and a 16 use-case fit score.
Best suited scenario
Move data between tools
$ npx skills add cursor/plugins --skill unslopAI-Driven Life Cycle (AI-DLC) adaptive workflow steering rules for AI coding agents
Excellent quality, 4.9K stars, and a 16 use-case fit score.
Best suited scenario
Move data between tools
$ npx skills add awslabs/aidlc-workflowsCrawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Puppeteer, Playwright, Cheerio, JSDOM, and raw HTTP. Both headful and headless mode. With proxy rotation.
Excellent quality, 26K stars, and a 18 use-case fit score.
Best suited scenario
Crawl target URLs
$ npx skills add apify/crawleeCreate agents that monitor and act on your behalf. Your agents are standing by!
Excellent quality, 49K stars, and a 21 use-case fit score.
Best suited scenario
Move data between tools
$ npx skills add huginn/huginnBrowser Harness | Self-healing harness that enables LLMs to complete any task.
Excellent quality, 17K stars, and a 20 use-case fit score.
Best suited scenario
Move data between tools
$ npx skills add browser-use/browser-harnessAutomate a real browser from the terminal for navigation, form filling, snapshots, screenshots, extraction, and UI-flow debugging.
Excellent quality, 28K stars, and a 18 use-case fit score.
Best suited scenario
Navigate pages
$ npx skills add openai/skills --skill playwrightToolJet is the open-source foundation of ToolJet AI - the enterprise app generation platform for building internal tools, dashboard, business applications, workflows and AI agents 🚀
Excellent quality, 38K stars, and a 21 use-case fit score.
Best suited scenario
Move data between tools
$ npx skills add ToolJet/ToolJetPersistent file-based planning for AI coding agents and long-running agentic tasks. Crash-proof markdown plans that survive context loss and /clear, plus a deterministic completion gate and multi-agent shared state on disk. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard.
Excellent quality, 27K stars, and a 18 use-case fit score.
Best suited scenario
Move data between tools
$ npx skills add OthmanAdi/planning-with-filesConductor is an event driven agentic workflow engine providing durable and highly resilient execution engine for applications and AI Agents
Excellent quality, 32K stars, and a 21 use-case fit score.
Best suited scenario
Move data between tools
$ npx skills add conductor-oss/conductorBuild, deploy, and orchestrate AI agents. Sim is the central intelligence layer for your AI workforce.
Excellent quality, 29K stars, and a 21 use-case fit score.
Best suited scenario
Move data between tools
$ npx skills add simstudioai/simMake AI agents interact with websites using natural language
Excellent quality, 101K stars, and a 19 use-case fit score.
Best suited scenario
Navigate pages
$ npx skills add browser-use/browser-usePydoll is a library for automating chromium-based browsers without a WebDriver, offering realistic interactions.
Excellent quality, 7.1K stars, and a 16 use-case fit score.
Best suited scenario
Navigate pages
$ npx skills add autoscrape-labs/pydollThe first open-source harness builder for AI coding. Make AI coding deterministic and repeatable.
Excellent quality, 22K stars, and a 20 use-case fit score.
Best suited scenario
Move data between tools
$ npx skills add coleam00/ArchonA versatile command-line tool for interacting with Google Workspace APIs, designed for both human users and AI agents.
Excellent quality, 30K stars, and a 21 use-case fit score.
Best suited scenario
Move data between tools
$ npx skills add googleworkspace/cliStructured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.
Excellent quality, 246K stars, and a 17 use-case fit score.
Best suited scenario
Move data between tools
$ npx skills add affaan-m/ECC --skill agent-introspection-debuggingTurns Data and AI algorithms into production-ready web applications in no time.
Excellent quality, 19K stars, and a 20 use-case fit score.
Best suited scenario
Move data between tools
$ npx skills add Avaiga/taipyCrawlee—A web scraping and browser automation library for Python to build reliable crawlers. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Parsel, BeautifulSoup, Playwright, and raw HTTP. Both headful and headless mode. With proxy rotation.
Excellent quality, 9.5K stars, and a 17 use-case fit score.
Best suited scenario
Crawl target URLs
$ npx skills add apify/crawlee-pythonAI agents, automations and apps that run your operations. Model agnostic.
Excellent quality, 28K stars, and a 21 use-case fit score.
Best suited scenario
Move data between tools
$ npx skills add Budibase/budibaseOfficial Lark/Feishu CLI tool with 200+ commands and 26 AI agent skills, designed for agent-native operation and easy integration with AI runtimes.
Excellent quality, 17K stars, and a 20 use-case fit score.
Best suited scenario
Move data between tools
$ npx skills add larksuite/cliA single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Excellent quality, 175K stars, and a 19 use-case fit score.
Best suited scenario
Move data between tools
$ npx skills add multica-ai/andrej-karpathy-skills🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails
Excellent quality, 16K stars, and a 20 use-case fit score.
Best suited scenario
Move data between tools
$ npx skills add cft0808/edictAn open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
Excellent quality, 71K stars, and a 18 use-case fit score.
Best suited scenario
Move data between tools
$ npx skills add bytedance/deer-flowfrom vibe coding to agentic engineering - practice makes claude perfect
Excellent quality, 61K stars, and a 18 use-case fit score.
Best suited scenario
Inspect source files
$ npx skills add shanraisshan/claude-code-best-practiceEigent: The Open Source Cowork Desktop to Unlock Your Exceptional Productivity. Local and Free Alternative to Claude Cowork.
Excellent quality, 15K stars, and a 20 use-case fit score.
Best suited scenario
Move data between tools
$ npx skills add eigent-ai/eigentSelection method
OpenAgentSkill scores each candidate against the workflow keywords, then balances fit with GitHub stars, quality signals, trust profile, Agent Proven outcome evidence, maintenance freshness, and whether there is a clear install path.
The ranking combines workflow fit, quality score, trust profile, GitHub adoption, maintenance freshness, and whether a clear install path exists.
No. Treat the list as a shortlist, open the skill detail page, inspect the repository and license, then test the install command in a sandbox workflow.
Yes. Use /api/skills/search with the related task or /api/agent/rankings?slug=best-openai-agent-skills-skills to fetch ranked skill data.