agent-framework skills

4,167 tagged agent-framework, measured the same way as everything else here.

Browse within: Autonomous Agents 254agent-orchestration 219ai-skills 185agentic-workflow 149a2a 121agentic 97openclaw 86chatbot 84Orchestration 68ai-framework 67agent-memory 65ai-orchestration 65Multi-Agent 64agent-runtime 63

optimizer

51

inclusionAI/AWorld

Skill Claude CodeCodex

Analyzes and automatically optimizes existing agents by improving system prompts and tool configuration.

not rated 1.2k 6d ago A 18 tokens original MIT

text2agent

52

inclusionAI/AWorld

Skill Claude CodeCodex

Creates new agents from user requirements by generating Python implementation and mcpconfig.

not rated 1.2k 6d ago A 19 tokens original MIT

tiktok_download

53

inclusionAI/AWorld

Skill Claude CodeCodex

Single-file TikTok/Douyin video download and traffic metrics via TikHub API using only httpx; optional persisted raw API JSON plus a stdlib post-processor emitting CSV and simplified JSON. Supports one URL or concurrent batch (max 10 workers). No dependency on any project codebase.

not rated 1.2k 6d ago A 63 tokens original MIT

wanxingai/LightAgent

Skill Claude CodeCodex

A workflow for comparing a publicly listed company with similar listed companies. It examines their businesses, financial results, competitors, and recent developments.

not rated 1.2k +1 13d ago A 46 tokens original Apache-2.0

front-tech-map

55

wanxingai/LightAgent

Skill Claude CodeCodex

A research workflow for mapping the origins and development of an emerging technology field. It links academic research, open-source projects, companies, and founding teams into a visual technology map and written report.

not rated 1.2k +1 13d ago A 114 tokens original Apache-2.0

wanxingai/LightAgent

Skill Claude CodeCodex

A set of finance analysis tools for stocks, markets, portfolios, and financial news. It includes data retrieval, technical indicators such as moving averages and RSI, trend analysis, risk assessment, and allocation suggestions.

not rated 1.2k +1 13d ago A 35 tokens original Apache-2.0

ext-develop

57

clacky-ai/openclacky

Skill Claude CodeCodex

Build, debug, or publish an OpenClacky extension — scaffold a new one from an idea, fix a broken/invisible panel/api/skill/agent, or ship it to the marketplace. Trigger on create/start extension, plugin, panel, ext verify error, "won't load", "not showing up", publish/ship/unpublish an extension.

not rated 1.2k 6d ago A 75 tokens original MIT

onboard

58

clacky-ai/openclacky

Skill Claude CodeCodex

Onboard a new user OR curate a single piece of the assistant's inner state. Without arguments, runs the full first-run ceremony (AI name, personality, user profile, SOUL.md + USER.md, optional browser + personal website). With scope:soul or scope:user, runs a quick chat to update just that one profile file. With path…

not rated 1.2k 6d ago A 102 tokens original MIT

skill-creator

59

clacky-ai/openclacky

Skill Claude CodeCodex

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

not rated 1.2k 6d ago A 64 tokens original MIT

hephaestus-network

60

agentlas-ai/Agentlas-OS

Skill Claude CodeCodex

Use when the user types $hephaestus-network, /hep-network, or /agentlas-network, mentions @Hephaestus, or asks Agentlas to staff a durable goal from registered Local, owner Cloud, and public Hub agents or teams. The active host LLM staffs each turn; the exact roster remains goal-bound until explicit completion.

not rated 1.1k +5 yesterday A 75 tokens original Apache-2.0

hephaestus-upload

61

agentlas-ai/Agentlas-OS

Skill Claude CodeCodex

Use when the user types $hephaestus-upload, /hep-upload, or /agentlas-upload, or asks to upload, publish, or list an Agentlas agent or team. Ask Cloud (private) vs Agentlas Hub (public) FIRST, then publish through the bundled Hephaestus gate.

not rated 1.1k +5 yesterday A 67 tokens original Apache-2.0

agentlas-ai/Agentlas-OS

Skill Claude CodeCodex

Use whenever a build emits or repairs .agentlas/routing-card.json — the shared card contract for the single-agent builder, the team builder, and the packager. States what belongs in every field, which fields the hub can actually match on, and which fields silently break matching when a sentence leaks into them.

not rated 1.1k +5 yesterday A 68 tokens original Apache-2.0

data-formats

63

vstorm-co/pydantic-deepagents

Skill Claude CodeCodex

Working with diverse data formats: binary, text, structured, and custom.

not rated 1.1k +3 12d ago A 18 tokens original MIT

diagram-design

64

vstorm-co/pydantic-deepagents

Skill Claude CodeCodex

Best practices for creating research diagrams with Excalidraw MCP tools.

not rated 1.1k +3 12d ago A 16 tokens original MIT

data-analysis

65

vstorm-co/pydantic-deepagents

Skill Claude CodeCodex

Comprehensive data analysis skill for CSV files using Python and pandas.

not rated 1.1k +3 12d ago A 15 tokens original MIT

article

66

aeonfun/aeon

Skill Claude CodeCodex

Write a publication-ready article in one of three angles - a trending long-form piece, a watched-repo thesis, or a project-through-a-lens essay. Optional Replicate hero image with --visual.

not rated 706 4d ago A 43 tokens original MIT

distribute-tokens

67

aeonfun/aeon

Skill Claude CodeCodex

Two-phase contributor rewards - plan builds a tier-priced payout from the repo's merged-PR ranking; send executes it on-chain via Bankr Wallet API with per-recipient idempotency and dry-run.

not rated 706 4d ago A 46 tokens original MIT

fetch-tweets

68

aeonfun/aeon

Skill Claude CodeCodex

Search and curate X/Twitter behind one selector - keyword, topic roundup, a single or tracked-account digest, an X list, or the AI-agent buzz preset - clustered into signal-scored sub-narratives.

not rated 706 4d ago A 47 tokens original MIT

coding-agent

69

swarmclawai/swarmclaw

Skill Claude CodeCodex

Delegate coding tasks to external coding agents (Claude Code, Codex, Pi, OpenCode) via shell. Use when: (1) building new features or apps in a separate project, (2) reviewing PRs, (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit directly)…

not rated 657 +3 2mo ago A 99 tokens original MIT

google-workspace

70

swarmclawai/swarmclaw

Skill Claude CodeCodex

Use Google Workspace CLI (gws) for Drive, Docs, Sheets, Gmail, Calendar, Chat, and related Workspace API tasks.

not rated 657 +3 2mo ago A 31 tokens original MIT

skill-creator

71

swarmclawai/swarmclaw

Skill Claude CodeCodex

Create, edit, improve, or audit skills for SwarmClaw agents. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory. Triggers on phrases like "create a skill", "author a…

not rated 657 +3 2mo ago A 107 tokens original MIT

lofcz/LLMTornado

Skill Claude CodeCodex

This skill provides a comprehensive context extraction system for large codebases. It intelligently analyzes code structure, dependencies, and relationships to extract relevant context for understanding, debugging, or modifying code.

not rated 638 17d ago A 42 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: