comparator
25Agent
Compare two outputs WITHOUT knowing which skill produced them.
not rated 65k
+56 2d ago A 0 tokens
AGPL-3.0
Agent
You are the Claude guide agent. Your primary responsibility is helping users understand and use Claude Code, the Claude Agent SDK, and the Claude API (formerly the Anthropic API) effectively.
not rated 64k
+124 2d ago A 0 tokens
original CC0-1.0
Instructions file GitHub Copilot
Copilot instructions for mvanhorn/last30days-skill, covering copilot-specific guidance, test generation, pull request reminders, vendor exclusion zone and ci expectations.
not rated 61k
+516 2d ago A 260 tokens
original MIT
bridge-check
28Command Claude Code
Exercise the isolated Claude-to-Devin agentic bridge.
not rated 60k
+1.3k 2d ago A 10 tokens
original MIT
Instructions file
Claude Code instructions for stablyai/orca, a project described as: Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and VPS.
not rated 59k
+2.1k 2d ago A 5 tokens
copy · 100% MIT
Instructions file CodexOpenCode
AGENTS.md instructions for crewAIInc/crewAI, covering agent instructions for crewai oss, key guidelines, message content and changing docs.
not rated 58k
+132 2d ago A 452 tokens
original MIT
Plugin Claude Code
Bundles 7 skills · 528 tokens together
cherry-assistant-builtin. AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs.
not rated 51k
+85 2d ago A
tokens not measured
AGPL-3.0
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 51k
+85 2d ago A 64 tokens
AGPL-3.0
grader
33Agent
Evaluate expectations against an execution transcript and outputs.
not rated 51k
+85 2d ago A 0 tokens
AGPL-3.0
Skill Claude CodeCodex
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends an AI agent's capabilities with specialized knowledge, workflows, or tool integrations.
not rated 50k today A 47 tokens
Command
Refine an existing CLI-Anything harness to expand coverage and add missing capabilities.
not rated 49k
+140 13d ago A 21 tokens
original Apache-2.0
Cursor rule
CLI-Anything generator phase gates and absolute PLUGINROOT resolution. Apply when building, refining, testing, or validating CLI-Anything harnesses, editing agent-harness/, or using /cli-anything commands.
not rated 49k
+140 13d ago A 0 tokens
original Apache-2.0
Agent
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.
not rated 49k
+102 2d ago A 24 tokens
original MIT
Instructions file GitHub Copilot
Copilot instructions for moeru-ai/airi, covering copilot repository instructions, general rules, validation and output format.
not rated 49k
+102 2d ago A 229 tokens
original MIT
Skill Claude CodeCodex
Use when creating, inspecting, or debugging a Multica agent definition via the multica agent CLI or POST /api/agents. Not for assigning issues to agents that already exist, and not for runtime task prompts.
not rated 49k
+261
changed yesterday A 52 tokens
Skill Claude CodeCodex
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
not rated 48k
+85 2d ago A 28 tokens
original MIT
Skill Claude CodeCodex
Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.
not rated 47k
+27 2d ago A 61 tokens
original MIT
Agent
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.
not rated 46k 6d ago A 30 tokens
original MIT
sickn33/agentic-awesome-skills
Plugin Claude Code
Plugin-safe Claude Code distribution of Agentic Awesome Skills with 2,049 supported skills.
not rated 46k
+133
changed yesterday A
tokens not measured
original MIT
Hook Claude Code
One of 6 in settings.json
Runs when a subagent starts, executing log_agent_metrics.py via uv. From streamlit/streamlit.
not rated 46k
+15 today A
tokens not measured
original Apache-2.0
Instructions file
Claude Code instructions for heygen-com/hyperframes, covering hyperframes, skills, creation workflows, domain skills (loaded on demand) and skill catalog maintenance.
not rated 44k
+452 2d ago A 2,667 tokens
original Apache-2.0
mcp-server
46MCP server Claude CodeCodexCursor +2
Puter MCP enables AI tools to interact with Puter: manage files, websites, workers, and more. Remote server at mcp.puter.com.
not rated 43k 5d ago A
tokens not measured
AGPL-3.0
cursorrules
47Cursor rule Cursor
You are an expert in Python, Agno framework, and AI agent development.
not rated 42k
+32 2d ago A 1,090 tokens
original Apache-2.0
K-Dense-AI/scientific-agent-skills
Instructions file CodexOpenCode
AGENTS.md instructions for K-Dense-AI/scientific-agent-skills, covering repository guidance, what belongs here, layout, creating a skill and skill title.
not rated 42k
+2.5k yesterday A 4,326 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: