智能体
Agent 规划、多步流程与编排
workflow-orchestration-patterns
HermeticOrmus
Design durable workflows with Temporal for distributed systems. Covers workflow vs activity separation, saga patterns, state management, and determinism constraints. Use when building long-running processes, distributed transactions, or microservice orchestration.
spec-driven
NikiforovAll
Guide spec-driven development workflow (Requirements → Design → Tasks → Implementation) with approval gates between phases. Use when user wants structured feature planning or says "use spec-driven" or "follow the spec process".
ai-dev-loop
shipshitdev
Orchestrate autonomous AI development with task-based workflow and QA gates
agent-browser
shipshitdev
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
debridge
sendaifun
Complete deBridge Protocol SDK for building cross-chain bridges, message passing, and token transfers on Solana. Use when building cross-chain applications, bridging assets between Solana and EVM chains, or implementing trustless external calls.
Architect
simota
æ°è¦ã¹ãã«ã¨ã¼ã¸ã§ã³ãã®è¨è¨ã»çæãè¡ãã¡ã¿ãã¶ã¤ãã¼ãã¨ã³ã·ã¹ãã ã®ã®ã£ããåæãéè¤æ¤åºãSKILL.mdï¼ãªãã¡ã¬ã³ã¹çæãNexusçµ±åè¨è¨ãæ å½ãæ°è¦ã¨ã¼ã¸ã§ã³ãä½æãå¿ è¦ãªæã«ä½¿ç¨ã
agent-browser-3
sundial-org
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
agent-browser-2
sundial-org
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection
agent-browser-5
sundial-org
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
agent-zero-bridge
sundial-org
Delegate complex coding, research, or autonomous tasks to Agent Zero framework. Use when user says "ask Agent Zero", "delegate to A0", "have Agent Zero build", or needs long-running autonomous coding with self-correction loops. Supports bidirectional communication, file attachments, task breakdown, and progress reporting.
agent-browser-4
sundial-org
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
agent-registry
sundial-org
MANDATORY agent discovery system for token-efficient agent loading. Claude MUST use this skill instead of loading agents directly from ~/.claude/agents/ or .claude/agents/. Provides lazy loading via search_agents and get_agent tools. Use when: (1) user task may benefit from specialized agent expertise, (2) user asks about available agents, (3) starting complex workflows that historically used agents. This skill reduces context window usage by ~95% compared to loading all agents upfront.
agent-orchestrator
sundial-org
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
agentic-compass
sundial-org
Top OpenClaw skills, with the most popular and useful ones.
agent-development
sundial-org
Design and build custom Claude Code agents with effective descriptions, tool access patterns, and self-documenting prompts. Covers Task tool delegation, model selection, memory limits, and declarative instruction design. Use when: creating custom agents, designing agent descriptions for auto-delegation, troubleshooting agent memory issues, or building agent pipelines.
agents-manager
sundial-org
Manage Clawdbot agents: discover, profile, track capabilities, define routing hierarchy, and assign tasks.
django-celery-expert
vintasoftware
Expert Django and Celery guidance for asynchronous task processing. Use when designing background tasks, configuring workers, handling retries and errors, optimizing task performance, implementing periodic tasks, or setting up production monitoring. Follows Celery best practices with Django integration patterns.
🤖 Multi-Agent Orchestration & State Management
Dokhacgiakhoa
Created by Antigravity Orchestrator - Based on Autonomous Agent Architectures.
factory
akashgit
Launch the Factory CEO agent to autonomously evolve any software project through systematic experimentation. Detects project state, spawns specialist agents, runs evals, and archives learnings.
Atlas
simota
ä¾åé¢ä¿ã»å¾ªç°åç §ã»God ClassãåæããADR/RFCãä½æãã¢ã¼ããã¯ãã£æ¹åãã¢ã¸ã¥ã¼ã«åå²ãæè¡çè² åµã®è©ä¾¡ãå¿ è¦ãªæã«ä½¿ç¨ã
openai-screenshot
trailofbits
Use when the user explicitly asks for a desktop or system screenshot (full screen, specific
kanban
flpbalada
Visualize and optimize workflow with Kanban boards. Use when managing team
QA Fix Loop
DmitrL-dev
Автономный цикл Reviewer → Fixer для непрерывного улучшения качества
refine
tkersey
Refine an existing Codex skill via $ms with minimal diffs, then validate with quick_validate. Trigger when asked to improve a skill's trigger description/frontmatter, workflow text, metadata, scripts/references/assets, or agents/openai.yaml; also for requests to iterate, refactor, rename, or fix a skill using usage/session-mining evidence (for example from $seq).