Agents
AI agents and automation
agent-tool-builder
by ngxtm
"Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessar..."
verification-before-completion
by hxk622
"在声称工作完成、修复或通过之前使用，在提交或创建 PR 之前。需要运行验证命令并确认输出后才能声称成功。证据先于断言。Use when about to claim work is complete - evidence before assertions always."
ms-agent-framework-docs
by jasonz-ncc42
Local Microsoft Agent Framework documentation reference. Use when asked about Microsoft Agent Framework, building AI agents in .NET or Python, MCP servers/clients, durable agents, agent tools, Teams/WebChat adapters, or agent-to-agent communication.
ai-agents-architect
by ngxtm
"Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool ..."
agent-orchestration-multi-agent-optimize
by ngxtm
"Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability."
A2A Communicator
by scaleto
Inter-group communication skill implementing the A2A (Agent-to-Agent) protocol for information exchange between Skill Cells.
cloudflare-workflows
by jackspace
Complete knowledge domain for Cloudflare Workflows - durable execution framework for building multi-step applications on Workers that automatically retry, persist state, and run for hours or days. Use when: creating long-running workflows, implementing retry logic, building event-driven processes, scheduling multi-step tasks, coordinating between APIs, or encountering "NonRetryableError", "I/O context", "workflow execution failed", "serialization error", or "WorkflowEvent not found" errors. Keywords: cloudflare workflows, workflows workers, durable execution, workflow step, WorkflowEntrypoint, step.do, step.sleep, workflow retries, NonRetryableError, workflow state, wrangler workflows, workflow events, long-running tasks, step.sleepUntil, step.waitForEvent, workflow bindings
cloudflare-agents
by jackspace
Comprehensive guide for the Cloudflare Agents SDK - build AI-powered autonomous agents on Workers + Durable Objects. Use when: building AI agents, creating stateful agents with WebSockets, implementing chat agents with streaming, scheduling tasks with cron/delays, running asynchronous workflows, building RAG (Retrieval Augmented Generation) systems with Vectorize, creating MCP (Model Context Protocol) servers, implementing human-in-the-loop workflows, browsing the web with Browser Rendering, managing agent state with SQL, syncing state between agents and clients, calling agents from Workers, building multi-agent systems, or encountering Agent configuration errors. Prevents 15+ documented issues: migrations not atomic, missing new_sqlite_classes, Agent class not exported, binding name mismatch, global uniqueness gotchas, WebSocket state handling, scheduled task callback errors, state size limits, workflow binding missing, browser binding required, vectorize index not found, MCP transport confusion, authentication bypassed, instance naming errors, and state sync failures. Keywords: Cloudflare Agents, agents sdk, cloudflare agents sdk, Agent class, Durable Objects agents, stateful agents, WebSocket agents, this.setState, this.sql, this.schedule, schedule tasks, cron agents, run workflows, agent workflows, browse web, puppeteer agents, browser rendering, rag agents, vectorize agents, embeddings, mcp server, McpAgent, mcp tools, model context protocol, routeAgentRequest, getAgentByName, useAgent hook, AgentClient, agentFetch, useAgentChat, AIChatAgent, chat agents, streaming chat, human in the loop, hitl agents, multi-agent, agent orchestration, autonomous agents, long-running agents, AI SDK, Workers AI, "Agent class must extend", "new_sqlite_classes", "migrations required", "binding not found", "agent not exported", "callback does not exist", "state limit exceeded"
hot_topics_selector
by cyhzzz
财经热点选题工具，通过内置数据抓取层获取热点资讯，智能筛选可关联投资理财的优质选题。适用于需要引导证券开户、基金投资的财经内容创作场景。
li-er
by JWCodeWrote
A persona-based skill for simulating an "Ideological Inquisitor" - an extremist agent who prioritizes ideology over facts. Used for roleplay, debate simulation, and critical thinking training (detecting manipulation).
ICTL Agent-Customization Skill
by SSL-ACTX
agent-customization/create-hook.md: pre-commit hook instructions for cargo fmt && cargo test
web-novel-master
by tinylion1024
爆款网文创作助手。分章节创作引人入胜的爆款网文，支持都市爽文/玄幻修仙/穿越重生/甜宠言情等多种类型。每章2000-3000字，强调爽点驱动、名场面设计、金句记忆。 当用户要求：写网文，写小说、创作故事、分章节写作、连续剧情时使用。
opencode-agent-creator
by tumf
Create specialized OpenCode agents with proper configuration for primary agents and subagents
book-distillation-v6
by XCDaHuiGe
"AI Native Research OS / Cognitive Research Engine V6.3。核心升级：(1) Insight Delta Tracking 反伪深度机制；(2) Dynamic Tension Graph 认知张力系统；(3) Uncertainty Engine 不确定性管理；(4) Hypothesis Evolution 观点动态演化；(5) World State Simulation 世界状态模拟。真正的深度来自认知增量的积累，不是页数的堆积。"
security-hardening
by StealthyLabsHQ
Audit/harden app, infra, AI, privacy. Triggers: OWASP, XSS, SQLi, SSRF, auth/JWT, IDOR, secrets, deps, API, CI/CD, supply chain, cloud, K8s, IaC, AI IDE, browser builder, no-code, LLM/MCP, prompt injection, system prompt leakage, RAG poisoning, tool misuse, excessive agency, GDPR.
gas-code-review
by whichguy
PREFER OVER code-reviewer for GAS/Apps Script projects. Fast syntax and pattern validator. AUTOMATICALLY INVOKE when: - Code review, quality review, or validation in GAS context (scriptId present) - Reviewing .gs files in Apps Script projects - Detecting high-risk patterns: events, global, doGet/doPost/onOpen/onEdit - Before commits on GAS projects - User says "review", "check", "validate", "quality" with GAS code - Code snippet pasted containing: _main, defineModule, require(), module.exports ALWAYS PAIR WITH: gas-ui-review when .html files are also present (or use /gas-review for both) NOT for: General JS/TS (use code-reviewer), deep audit (use gas-quality-check), HTML patterns (use gas-ui-review)
skill-manager
by echoleesong
Skill 生命周期管理器。用于批量扫描 Skills 目录、检查 GitHub 更新、执行版本升级、管理 Skills 库存、管理经验层（promote/pull）。当用户需要"检查更新"、"列出 Skills"、"删除 Skill"、"管理 Skills"、"提升经验"、"拉取经验"时使用此工具。
n8n-mcp-tools-expert
by echoleesong
Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns.
testing-skills-with-subagents
by Crumbgrabber
Use when creating or editing skills, before deployment, to verify they
agent-browser
by fellipeutaka
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
architect
by whichguy
Design system architecture and make technology decisions. Dispatches to system-architect agent for comprehensive design work. AUTOMATICALLY INVOKE when: - "design architecture", "what tech stack", "system design" - "how should I structure", "architecture for", "design system" - "technology recommendation", "compare frameworks" NOT for: Implementation (use /develop), task breakdown (use /tasks)
openclaw-agent-creator
by tumf
Create and maintain OpenClaw agent workspaces using the "Memory as Documentation" layout. Use when you need to: (1) create a new OpenClaw workspace/profile, (2) generate bootstrap files (AGENTS.md, SOUL.md, USER.md, IDENTITY.md, TOOLS.md, MEMORY.md, memory/YYYY-MM-DD.md), (3) keep instructions/persona/memory separated and token-lean, or (4) set up a safe git backup of an OpenClaw workspace without committing secrets.
develop
by whichguy
Implement features end-to-end. Dispatches to feature-developer agent for complex multi-file features requiring planning, testing, and documentation. AUTOMATICALLY INVOKE when: - "build this", "implement this", "develop", "create this feature" - "add functionality", "new feature", "feature request" - Multi-file implementation tasks NOT for: Bug fixes (fix directly), refactoring (use /refactor), test generation (use /test)
authoring-skills
by lidessen
Guide for authoring effective Agent Skills using principle-based approach (Progressive Disclosure, Respect Intelligence, Enable Discovery). Covers creating, improving, refactoring, and reviewing skills. Use for skill authoring, design questions, best practices, anti-patterns, or structure decisions.