agent-loops
Agentic workflow patterns for autonomous LLM reasoning. Use when building ReAct agents, implementing reasoning loops, or creating LLMs that plan and execute…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-01 00:15
Agents & models
25,391 results
agentic-rag-patterns
Advanced RAG with Self-RAG, Corrective-RAG, and knowledge graphs. Use when building agentic RAG pipelines, adaptive retrieval, or query rewriting.
prompt-pro
Senior Prompt Engineer & Agentic Orchestrator. Expert in Reasoning Models (o3), Tree-of-Thoughts, and Structured Thinking Protocols for 2026.
structured-prompt-writer
Structured AI prompt writing tool with 395+ built-in prompt templates. Supports detailed mode and simple mode. Used to create professional AI role prompts, system prompts, or task prompts. Use this skill when the user needs to: (1) create new AI prompts/Prompt (2) design AI roles/Persona (3) write system prompts (4) optimize existing prompt structures.
zerion-uniswap-lp
Plan Uniswap v4 LP positions using Zerion CLI portfolio data and PnL to size exposure correctly before deploying capital via the Uniswap /liquidity-planner…
zoonk-technical
Technical decision-making framework for AI agents. Use when making architecture decisions, choosing implementations, or evaluating technical trade-offs.…
1inch-orderbook
Build, sign, create, list, and cancel limit orders via the 1inch MCP `orderbook` tool (Limit Order Protocol v4.1). Use when the user wants buy/sell at a target…
1inch-walletconnect
Pair an EVM or Solana wallet via WalletConnect (non-custodial) using the 1inch MCP `walletconnect` tool, then sign messages or send transactions. Use when the…
mcp-server-orchestrator
Configure, deploy, and troubleshoot Model Context Protocol (MCP) servers for AI agent workflows. Use when setting up MCP servers, debugging connection issues,…
scrum-master
Advanced Scrum Master with data-driven team health analysis, velocity forecasting, retrospective insights, and team development expertise. Features…
macpilot-automation
Core macOS automation skill using MacPilot CLI. Enables Claude Code to control apps, type text, click elements, run shell commands, and automate workflows on…
update-llm-model-list
Audit and update the supported LLM model list in assets.py against litellm's registry (models.litellm.ai). Use when adding new models, pruning outdated ones,…
claude-authenticity
Detect whether an API endpoint is backed by genuine Claude (not a wrapper, proxy, or impersonator) using 9 weighted rule-based checks that mirror the…
multi_agent_collaboration
Use this skill when another agent's expertise or context is needed, or when the user explicitly asks to involve another agent. First list agents, then use…
claude-gif-edit
Edit and modify existing GIFs. Speed change, reverse, ping-pong, crop, resize, text overlay, frame extraction, loop control, trim. Uses gifsicle for…
claude-gif-optimize
Optimize GIF file size and quality. Multi-strategy optimization: gifsicle lossy compression, color reduction, dimension reduction, frame rate reduction,…
spec-kit-checklist
Use when a Spec Kit feature has `spec.md` and you need a requirements-quality checklist (clarity, completeness, consistency, measurability, coverage), not…
index-knowledge
Generate hierarchical AGENTS.md knowledge base for a codebase. Creates root + complexity-scored subdirectory documentation.
skill-creator
Create new skills, modify and improve existing skills, and measure skill quality for OpenCode agents. Load FIRST before writing any SKILL.md. Use when creating…
agent-configuration
AI agent configuration policy and security guide. Project description file writing, Hooks/Skills/Plugins setup, security policy, team shared workflow…
agent-evaluation
Design and implement comprehensive evaluation systems for AI agents. Use when building evals for coding agents, conversational agents, research agents, or…
llm-monitoring-dashboard
Auto-generates an LLM usage monitoring page in a PM admin dashboard. Tokuin CLI-based token/cost/latency tracking + user ranking system + inactive user…
openocta
Operate openocta/openocta, the Apache-2.0 desktop and service AIOps agent for natural-language inspection, alert analysis, data queries, remediation, local…
scientific-agent-skills
Audit, inventory, route, selectively install, and safely refresh the K-Dense-AI/scientific-agent-skills collection for scientific packages, databases, lab…