test-prompt
neolabhq
Prompts tested against real agent behavior.
Prompt engineering
AI agents & skills skills for AI agents
This is where agents get better at being agents: building them on platforms such as Microsoft Foundry, connecting them through MCP servers and giving them memory. Next come Skills about Skills, which write, find and manage them, then prompt engineering and evaluation of AI features.
Sort by
Most installed
840 Skills
Showing Skills in AI agents & skills.- 1.2k
- 1.2k
create-rule
neolabhq
Turn repeated agent mistakes into clear rules.
Agent instruction design
- 1.2k
create-skill
neolabhq
Create agent skills tested before deployment.
Skill authoring
1.2kchannels-setup
copilotkit
Get your agent answering in Slack or Teams.
Agent integration
1.2kagent-coordination
ruvnetKeep specialized agents working together.
Agent orchestration
1.2kinit-claude
fandhe-ai
A Claude Code setup tailored to your repository.
Agent configuration
1.2krole-creator
am-will
Custom Codex agents with settings you confirm.
Agent configuration
- 1.2k
agent-memory-coordinator
ruvnetKeep project knowledge across agent sessions.
Agent memory management
- 1.1k
agent-safla-neural
ruvnetBuild AI agents that learn across sessions.
AI development
CF - 1.1k
copilotkit-channels
copilotkit
Bring your project's agent to Slack or Teams.
Agent integration
+1 
1.1kmode-creator
thedotmack
Make claude-mem remember what matters to you.
Agent memory
+1- 1.1k
agent-automation-smart-agent
ruvnetMatch your coding tasks to specialist agents.
Agent orchestration
- 1.1k
update-claude
fandhe-ai
Fill gaps in your Claude Code configuration.
Agent configuration
- 1.1k
agent-collective-intelligence-coordinator
ruvnetKeep multiple agents working toward shared decisions.
Multi-agent coordination
CF 
1.1kdeveloping-genkit-dart
genkit-ai
Build AI agents for your Dart and Flutter apps.
AI application development
1.1knewapi
quantumnous
Manage your New API tokens without showing keys.
AI gateway management
1.1kcreate-agent-with-sanity-context
sanity-io
Build a chatbot that knows your Sanity content.
AI assistant development
- 1.1k
agent-hierarchical-coordinator
ruvnetTurn complex tasks into coordinated team results.
Agent coordination
CF - 1.1k
agent-coordinator-swarm-init
ruvnetSet up agent teams that share progress and work.
Agent coordination
CF - 1.1k
agent-adaptive-coordinator
ruvnetKeep agent teams tuned as their workload changes.
Agent coordination
CF 
1.1karize-prompt-optimization
github
Better LLM prompts, grounded in real failures.
Prompt engineering
- 1.1k
agent-worker-specialist
ruvnetAssigned work completed with shared progress updates.
Agent coordination
CF 
1.1kilya-sutskever-perspective
alchaincyf
AI research advice through Ilya Sutskever's eyes.
AI research
- 1.1k
agent-mesh-coordinator
ruvnetKeep agent teams coordinated when peers fail.
Multi-agent coordination
CF
A folder of instructions, and sometimes scripts, that an agent loads when a task calls for it. It teaches the agent a way of working it would not follow on its own.
Yes. Skill authoring Skills guide an agent through writing a new Skill, testing it on real tasks and improving it from what went wrong.
The Model Context Protocol, a standard way for an agent to reach outside tools and data. MCP Skills help build servers that expose a service to agents this way.