智能体

Ai Workflow Automation

omer-metin

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.

agent-folder-init

shipshitdev

Initialize a comprehensive .agents/ folder structure for AI-first development. Use this skill when starting a new project that needs AI agent documentation, session tracking, task management, and coding standards. Generates full structure based on proven patterns from production projects.

context-fundamentals

shipshitdev

Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.

ln-513-agent-reviewer

levnikolaevich

"Worker that runs parallel external agent reviews (Codex + Gemini) on code changes. Background tasks, process-as-arrive, critical verification with debate. Returns filtered suggestions with confidence scoring."

swarm-expert

desplega-ai

Multi-agent coordination expert for agent-swarm MCP. Use when the user asks about swarm coordination, delegating tasks to agents, checking swarm status, agent messaging, or managing multi-agent workflows.

n8n

sachacoldiq

Expert n8n workflow automation consultant for B2B sales and GTM teams. Use when the user asks about n8n workflows, n8n nodes, n8n triggers, n8n webhooks, n8n credentials, n8n self-hosting, n8n Docker setup, n8n queue mode, n8n error handling, n8n sub-workflows, Clay + n8n integration, n8n CRM automation, n8n pricing, n8n vs Zapier vs Make, or building automations with n8n. Also triggers on "n8n workflow", "n8n automation", "n8n webhook", "n8n node", "n8n self-host", "n8n Docker", "n8n queue", "n8n Clay", "n8n HubSpot", "n8n Salesforce", "n8n vs Zapier", "n8n pricing", "workflow automation". Do NOT use for Clay-only questions without n8n context or general automation strategy without n8n.

openclaw-ops

chujianyun

OpenClaw 运维助手。用于用户提到 OpenClaw、小龙虾、gateway、渠道连接、消息发送失败、服务不可达、日志排查、渠道或 Agent 管理时使用。优先执行状态检查与故障分流；涉及重启、修复、更新、配置变更等高影响操作时，先向用户说明再执行。

copaw-ops

chujianyun

CoPaw 运维助手。用于用户提到 copaw 运维、服务无响应、渠道断连、MCP 失败、模型调用失败、cron 不执行、Docker 部署、重载、重启或重置恢复时使用。优先执行状态检查与故障分流；涉及重启、重载、重置、配置修改等高影响动作时，先向用户说明再执行。

pymc-bayesian-modeling

jaechang-hits

"Bayesian modeling with PyMC 5. 8-step workflow: define model, set priors, define likelihood, sample (NUTS/ADVI), diagnose (R-hat, ESS, divergences), interpret posteriors, compare models (LOO/WAIC), predict. Hierarchical, logistic, GP model variants. Prior/posterior predictive checks."

learning-medusa

medusajs

Load automatically when user asks to learn Medusa development (e.g., "teach me how to build with medusa", "guide me through medusa", "I want to learn medusa"). Interactive guided tutorial where Claude acts as a coding bootcamp instructor, teaching step-by-step with checkpoints and verification.

openclaw-wiki

chujianyun

OpenClaw 官方文档知识库，一个多渠道 AI Agent 网关。当用户询问 OpenClaw 相关问题（如安装、配置、Gateway、WhatsApp/Telegram/Discord 等渠道连接、Sessions、Tools、Skills、Pi Agent、故障排查等）时使用此 skill。

root-cause-analysis

kopai-app

Analyze telemetry data for root cause analysis using Kopai CLI. Use when debugging errors, investigating latency issues, tracing request flows across services, or correlating logs with traces.

fastgpt-design-skill

labring

当用户需要设计 FastGPT 的代码时，可调用此 Skill。

fable-opus

mrtooher

Run fable-mode execution discipline on Claude Opus — the strongest staged run available. Routes the task to the @fable-orchestrator agent (Opus, Write-less), which stages the work, delegates artifact production to @fable-worker-sonnet / @fable-worker-haiku, and cold-checks deliverables with @fable-verifier. Trigger when the user explicitly asks for thorough/systematic/"deep work" handling on the strongest model ("fable on opus", "stage this on opus", "deep work mode, opus"). Do NOT use for ordinary single-pass tasks — and prefer fable-sonnet or fable-haiku when the task doesn't need peak reasoning.

sag

elizaOS

ElevenLabs text-to-speech with mac-style say UX.

browser-tools

yonatangross

OrchestKit orchestration wrapper for browser automation. Adds security rules, rate limiting, and ethical scraping guardrails on top of the upstream agent-browser skill. Use when automating browser workflows, capturing web content, or extracting structured data from web pages.

Agent Evaluation

omer-metin

explore

yonatangross

"explore — Deep codebase exploration with parallel agents. Use when exploring a repo, discovering architecture, finding files, or analyzing design patterns."

Agent Communication

omer-metin

git-workflow

yonatangross

Complete git workflow patterns including GitHub Flow branching, atomic commits with interactive staging, merge and rebase strategies, and recovery operations using reflog. Essential patterns for clean history. Use when managing branches, defining branching strategy, or recovering git history.

review

Yeachan-Heo

Alias for /plan --review

ultrawork

Yeachan-Heo

Parallel execution engine for high-throughput task completion

koala-strategy

Senpi-ai

KOALA v1.0.0 — Set-and-Forget Trail HODL. The simplest possible Senpi agent. Pick an asset (default BTC). Fire LONG once on deploy. Hold with an ultra-wide DSL trail (max_loss 30%, retrace 25, 90d hard_timeout). Done. No scoring, no scheduling, no multi-timeframe analysis. For users whose entire trading thesis is "I want to own BTC and have a safety net." Onboarding tier.