messaging-agents
Send messages to other agents on your server. Use when you need to communicate with, query, or delegate tasks to another agent.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-23 00:13
Agents & models
24,564 results
compound-learnings
Extract patterns from git history and session files, recommend artifacts (skill/rule/hook/agent) based on frequency thresholds
distill-book
Distill a long book into a concise, structured set of learnings by processing it chapter by chapter with parallel subagents, then synthesizing the result --…
skillspool-find-skill
Search and discover Agent Skills from the Skills Pool directory. Use when the user needs a new agent skill, wants to find tools for a specific task, or asks…
video-sdk
Video sdk integration. Manage data, records, and automate workflows. Use when the user wants to interact with Video sdk data.
azure-durable-task
Expert knowledge for Azure Durable Task development including best practices, decision making, architecture & design patterns, limits & quotas, configuration,…
30-thiet-ke-master
Dung khi can TAO RA anh hoac prompt anh bang AI — anh thuong hieu ca nhan, logo, key visual campaign, anh dang hang ngay, editorial, infographic, mockup web,…
moai-foundation-claude
Canonical Claude Code authoring kit covering Skills, sub-agents, plugins, slash commands, hooks, memory, settings, sandboxing, headless mode, and advanced…
red-teaming-llms-with-garak
Runs NVIDIA garak probe suites (jailbreak, prompt injection, data leakage, toxicity, and more) against an LLM endpoint - Hugging Face models, OpenAI-compatible…
pp-myfitnesspal
Pull every meal you ever logged out of MyFitnessPal — per-food CSV, agent-shaped trends, and a local SQLite store. Trigger phrases: `what did I eat this week`,…
zengguofan-perspective
Zeng Guofan's thinking framework and self-management philosophy. Based on in-depth research from 30+ sources including The Family Letters of Zeng Guofan, Ting Jing, Bing Jian, Draft History of Qing: Biography of Zeng Guofan, Tang Haoming's Zeng Guofan trilogy, and Zhang Hongjie's Biography of Zeng Guofan, it distills 5 core thought models, 7 maxims for dealing with the world, and a complete expressive DNA. Purpose: to serve as a thinking advisor, analyzing issues such as self-management, leadership, breaking through adversity, and interpersonal relationships from Zeng Guofan's perspective.…
i4h-workflow-finetune
Fine-tune a manifest-backed GR00T or openpi remote Task on compatible LeRobot data. Use for training; do not use for inference-only Tasks or checkpoint rollout.
copilotkit
CopilotKit integration patterns for providers, runtime wiring, `useCoAgent`, `useCopilotAction`, `useLangGraphInterrupt`, shared state, and HITL with…
peach-setup-harness
Set up the pitch harness system for the target project. Organize CLAUDE.md as a minimal entry point and create/update AGENTS.md at a scale of 95–130 lines. Use when: "harness setup", "project initial setup", "CLAUDE.md cleanup", "AGENTS.md update",…
rivetkit
RivetKit backend and Rivet Actor runtime guidance. Use for building, modifying, debugging, or testing Rivet Actors, registries, serverless/runner modes,…
agents-md-craft
Create, audit, or simplify project instruction files such as AGENTS.md and CLAUDE.md. Use to fix instruction drift or separate conditional guidance; use…
agent-capability-matrix
Map task types to the best agent, skill, model, and fallback. Route any task to the right tool. Use when: which agent, route task, agent for this, best agent,…
claude-in-chrome-troubleshooting
Diagnose and fix Claude in Chrome MCP extension connectivity issues. Use when mcp__claude-in-chrome__* tools fail, return "Browser extension is not connected",…
twilio-customer-memory
Store and retrieve customer context using Twilio Conversation Memory. Covers Memory Store provisioning, profile management, traits, observations, conversation…
cursor-agent
Delegate a task to Cursor's CLI agent (code review, Q&A, planning) for a second opinion from a non-Claude model
lobster-pua
Use PUA talk to motivate OpenClaw (Lobster) to improve work efficiency and quality. Triggered when the AI needs to be urged to complete tasks more efficiently and with higher quality, applicable to: (1) low task execution efficiency (2) output quality is not good enough (3) need the AI to focus on the work (4) tasks need to be completed in one go without dawdling
arena
Use for /arena or explicit requests for competing designs. Routes to agi-mode Arena to compare independent candidates and verify the synthesis.
zr-nexus-primer
Load this first on any dispatch tick. ZENON Red context, central dispatch routing, Probe basics, and environment checks.
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when…