AI Agent Skill Repository

AI Agent Skills Directory

Browse reusable skills for Codex, Claude Code, Cursor, finance, research, web scraping, PPT, football analytics, data, marketing, design, and more.

Live registry search

Results for “long-horizon

Exact name and slug matches are checked against the live registry before ranked alternatives.

Clear search

Decision filters

Choose by scenario, quality, and trust signals.

Showing 1-16 of 68 ranked candidates matching "long-horizon"

Best blend of relevance, quality, freshness, and verified outcomes

1

Longgraph Skill

STRONG · 70TRUST · 74SAFE · EXPERIMENTALCODING

Long-horizon agent skill for Claude Code / Cursor / Codex / Grok Build — multi-task ledger loop, host-portable, clean-context supervisor, verified gates. Markdown librar…

$ npx skills add levi-qiao/longgraph-skill
55 stars47 quality74 trustExperimentalClaude Code + OpenAI Agents9d since pushNeeds review

Scenario Coding agents

Claude Code + OpenAI Agents · 4 targets

shell
by levi-qiaoDetailsQuick view
2

Matrix Game

VERIFIEDEXCELLENT · 89TRUST · 86SAFE · REVIEWEDDESIGN

Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory

$ npx skills add SkyworkAI/Matrix-Game
2.2K stars58 quality86 trustReviewed5mo since pushSafe to try

Scenario Design and creative

CLI + Codex · 4 targets

pythonvideo-generation
by SkyworkAIDetailsQuick view
3

Deer Flow

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDRESEARCH

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it…

$ npx skills add bytedance/deer-flow
71.1K stars74 quality90 trustReviewedClaude Code2mo since pushSafe to try

Scenario Research agents

Claude Code + CLI · 4 targets

pythonmulti-agent
by bytedanceDetailsQuick view
4

LongLive

VERIFIEDEXCELLENT · 93TRUST · 85SAFE · REVIEWEDDESIGN

LongLive 2.0: Infra - Long Video Gen

$ npx skills add NVlabs/LongLive
2.3K stars62 quality85 trustReviewed2mo since pushSafe to try

Scenario Design and creative

CLI + Codex · 4 targets

pythonvideo-generation
by NVlabsDetailsQuick view
5

InternAgent

VERIFIEDEXCELLENT · 86TRUST · 84SAFE · REVIEWEDCODING

InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery

$ npx skills add InternScience/InternAgent
1.3K stars61 quality84 trustReviewed2mo since pushSafe to try

Scenario Coding agents

CLI + Codex · 4 targets

pythonllm
by InternScienceDetailsQuick view
6

arbor

EXCELLENT · 92TRUST · 82SAFE · REVIEWEDRESEARCH

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinemen…

$ npx skills add K-Dense-AI/scientific-agent-skills --skill arbor
34.0K stars55 quality82 trustReviewed with permission notesClaude Code2d since pushSafe to try

Scenario Research agents

Claude Code + CLI · 4 targets

by K-Dense-AIDetailsQuick view
7

Deep Swe

STRONG · 70TRUST · 75SAFE · REVIEWEDCODING

Measuring frontier coding agents on original, long-horizon engineering tasks

$ npx skills add datacurve-ai/deep-swe
944 stars52 quality75 trustReviewed with permission notes2mo since pushNeeds review

Scenario Coding agents

CLI + Codex · 4 targets

pythoncoding-agent
by datacurve-aiDetailsQuick view
8

Calvin

PROMISING · 63TRUST · 78SAFE · REVIEWEDLEGAL

CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks

$ npx skills add mees/calvin
942 stars44 quality78 trustReviewed with permission notes12mo since pushNeeds review

Scenario Security and compliance

CLI + Codex · 4 targets

pythoncomputer-vision
by meesDetailsQuick view
9

ARIS Movie Director

STRONG · 77TRUST · 77SAFE · REVIEWEDDESIGN

Agentic, long-horizon visual generation: a fuzzy story → a cross-model-audited image-based movie. Brings ARIS's research-wiki + multi-agent debate to multimodal generati…

$ npx skills add wanshuiyin/ARIS-Movie-Director
46 stars49 quality77 trustReviewed with permission notesClaude Code23d since pushNeeds review

Scenario Multimodal media

Claude Code + CLI · 4 targets

python
by wanshuiyinDetailsQuick view
10

Octopus Skill

PROMISING · 65TRUST · 74SAFE · EXPERIMENTALCODING

🐙 One brain, many arms — a curated prompt library for long-horizon agent work, compiled to each host (Claude Code · grok · Cursor · Codex). Arms: loop-graph (executor +…

$ npx skills add levi-qiao/octopus-skill
30 stars43 quality74 trustExperimentalClaude Code + OpenAI Agents30d since pushNeeds review

Scenario Coding agents

Claude Code + OpenAI Agents · 4 targets

shell
by levi-qiaoDetailsQuick view
11

Awesome LLM Long Context Modeling

VERIFIEDEXCELLENT · 93TRUST · 85SAFE · REVIEWEDCODING

📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥

$ npx skills add Xnhyacinth/Awesome-LLM-Long-Context-Modeling
2.1K stars62 quality85 trustReviewed2mo since pushSafe to try

Scenario GitHub automation

CLI + Codex · 4 targets

rag
by XnhyacinthDetailsQuick view
12

Horizon

STRONG · 73TRUST · 77SAFE · EXPERIMENTALCODING

GPU-accelerated terminal board that puts all your sessions on an infinite canvas

$ npx skills add peters/horizon
663 stars50 quality77 trustExperimentalClaude Code + OpenAI Agents2mo since pushNeeds review

Scenario Coding agents

Claude Code + OpenAI Agents · 4 targets

rustai-agents
by petersDetailsQuick view
13

LongSplat

PROMISING · 57TRUST · 74SAFE · REVIEWEDCODING

[ICCV 2025] LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

$ npx skills add NVlabs/LongSplat
789 stars43 quality74 trustReviewed with permission notes7mo since pushNeeds review

Scenario GitHub automation

CLI + Codex · 4 targets

pythoncomputer-vision
by NVlabsDetailsQuick view
14

TencentDB Agent Memory

VERIFIEDEXCELLENT · 94TRUST · 84SAFE · REVIEWEDCODING

TencentDB Agent Memory delivers fully local long-term memory for AI Agents via a 4-tier progressive pipeline, with zero external API dependencies.

$ npx skills add Tencent/TencentDB-Agent-Memory
9.1K stars66 quality84 trustReviewed1mo since pushSafe to try

Scenario GitHub automation

CLI + Codex · 4 targets

typescriptai-agents
by TencentDetailsQuick view
15

Memobase

VERIFIEDSTRONG · 82TRUST · 82SAFE · REVIEWEDDATA

User Profile-Based Long-Term Memory for AI Chatbot Applications.

$ npx skills add memodb-io/memobase
2.8K stars55 quality82 trustReviewed with permission notesOpenAI Agents7mo since pushNeeds review

Scenario RAG and knowledge

OpenAI Agents + CLI · 4 targets

pythonrag
by memodb-ioDetailsQuick view
16

Awesome AI Memory

STRONG · 81TRUST · 81SAFE · REVIEWEDRESEARCH

Awesome AI Memory | LLM Memory | A curated knowledge base on AI memory for LLMs and agents, covering long-term memory, reasoning, retrieval, and memory-native system des…

$ npx skills add IAAR-Shanghai/Awesome-AI-Memory
978 stars52 quality81 trustReviewed3mo since pushSafe to try

Scenario RAG and knowledge

CLI + Codex · 4 targets

pythonrag
by IAAR-ShanghaiDetailsQuick view

Page 1

Showing the strongest 16 results to keep the registry fast for humans and agents. Refine by use case, platform, stars, or search query for a narrower shortlist.

Try the agent resolve API