882GitHub
OPENAGENTSKILL / DIRECTORY
AI Agent Skills
Find a skill for your next task. Explore tools for Codex, Claude Code, Cursor and more.
Results · “ocr-python”
33–48 / 188
More filters · 1
Candidates in this shortlist, not the full registry. GitHub stars belong to repositories, not individual skills.
Results: 188
Econ Writing Skill
hanlulong
Agent Skill that transforms AI assistants into expert economics paper writers. Synthesizes 50+ guides by Cochrane, McCloskey, Shapiro, Head, Bellemare, Goldin, Kremer. C…
470GitHub
General Agentic Memory
VectorSpaceLab
A general memory system for agents, powered by deep-research
ResearchSkill source unconfirmed
855GitHub
Deep Research Bench
Ayanami0730
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
ResearchSkill source unconfirmed
753GitHub
AgentHarness
ApodexAI
Evaluation harness for Apodex-1.0 on public deep-research benchmarks.
ResearchSkill source unconfirmed
433GitHub
Computational Chemistry Agent Skills
jinzhezenggroup
Agent skills to run computational-chemistry tasks, used in OpenClaw
128GitHub
Databend
databendlabs
Data Agent Ready Warehouse : One for Analytics, Search, AI, Python Sandbox. — rebuilt from scratch. Unified architecture on your S3.
ResearchSkill source unconfirmed
9.4KGitHub
Genkit
genkit-ai
Open-source framework for building AI-powered apps in JavaScript, Go, and Python, built and used in production by Google
ResearchSkill source unconfirmed
6.1KGitHub
Marco DeepResearch
AIDC-AI
Marco Search Agent for Realistic and Challenging Agentic Search
ResearchSkill source unconfirmed
327GitHub
nature-writing
Yuan1z0825
Draft, restructure, or plan Nature-style manuscript sections and initial-submission materials from author-provided claims, results, figures, notes, or Chinese drafts. Us…
38.7KGitHub
Ir Search
djfksjd
🇰🇷 한국 정부 지원사업 전수조사 에이전트 스킬 [Claude Code·Codex·agy(Antigravity)·Cursor·Gemini CLI·Grok Build 지원] K-Startup·기업마당·NIPA·KOCCA·SMTECH 크롤링 + 즉시/로드맵/변형 3분류 (Korea-only)
185GitHub
BrowseComp Plus
texttron
BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent (ACL 2026 Main)
ResearchSkill source unconfirmed
302GitHub
auto-paper-improvement-loop
wanshuiyin
Autonomously improve a generated paper via GPT-5.6-Sol xhigh review → implement fixes → recompile, for 2 rounds. Use when user says \"改论文\", \"improve paper\", \"论文润色循环\…
15.6KGitHub
discernment-nudge
anthropics
After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails,…
173KGitHub
academy-guide
anthropics
Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases…
173KGitHub
agent-launcher-orchestrator
alirezarezvani
Use when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account — "build me an agent", "launch this as a managed a…
25.1KGitHub