planning-and-task-breakdown
Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-03 00:11
Agents & models
25,506 results
incarnation
Full character autonomy across all layers of existence
room
Rooms are intertwingled navigable activation context maps. Entering = calling. Exiting = returning.
baoyu-danger-gemini-web
Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input,…
claude-skills-zh-cn
Chinese version of the Anthropic Skills collection, containing Chinese translations of multiple commonly used skills. Use when Chinese skill documentation or reference Chinese skill implementations are needed.
resourceful-problem-solving
Always-on guidance for solving tasks resourcefully. Teaches agents to escalate through skills, CLI tools, and custom scripts instead of refusing. Applies to…
synthesis-agent-conformance
Audit and verify that synthesis behaves the same in Claude Code, Codex and Muse: source lint, installed parity, hook wiring and trust, AGENTS.md/CLAUDE.md…
mission-plan
Use when a measurable spec must become an ordered implementation plan — every file named with its purpose, every step leaving the tree valid, before any code…
mission-specify
Use when a mission brief must become a measurable spec — restates every success criterion as a binary outcome and resolves what cannot be measured before any…
llm-deploy
Deploys ML and LLM models on TrueFoundry with GPU inference servers (vLLM, TGI, NVIDIA NIM). Uses YAML manifests with `tfy apply`. Use when serving language…
agent-native-architecture
Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying…
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
slap
User-invoked correction protocol. Use only when the user types /slap to flag that steering has failed.
ai-coding-agents-tasks
Designs task runtimes for Loop Engineering, Graph Engineering, and background work. Use when work needs task lists, cyclic/workflow graphs, cancellation, or…
decision-mapping
Turn loose ideas into an ordered investigation tickets map, then advance them one by one to resolution.
model_finetuning
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward…
meta prompt
Generate optimal prompts for complex tasks
using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
langgraph-functional
LangGraph Functional API with @entrypoint and @task decorators. Use when building workflows with the modern LangGraph pattern, enabling parallel execution,…
multimodal-rag
CLIP, SigLIP 2, Voyage multimodal-3 patterns for image+text retrieval, cross-modal search, and multimodal document chunking. Use when building RAG with images,…
mcp-expert
Senior MCP Architect & Orchestrator. Master of MCP Apps, Server Development (2025-11-25 Spec), and Multi-Agent Tooling.
llm-workspace-management
Use this skill to manage multiple local wikis maintained by llm-wiki-management: scan all wikis at the workspace level, generate and maintain the global INDEX.md / STATS.md / LINT.md, do cross-wiki comprehensive Q&A (routing / synthesis / comparison / partial), maintain cross-wiki cross-references, do…
zr-claim
Select and claim one ready task when probe next routes claim_task.
cz-perspective
Changpeng Zhao (CZ)'s thinking framework and way of expressing himself. Based on 4,449 tweets (including 1,913 replies), transcripts of 18+ AMAs, 20+ in-depth interviews and open letters, the autobiography "Freedom of Money", a reading list of 30 mind-expanding books, and deep distillation of 110+ primary sources, distills 8 core mental models, 10 decision-making heuristics, and a complete expression DNA. Use: as a thinking advisor, analyze crypto from CZ's perspective...