智能体
Agent 规划、多步流程与编排
mobile-browser-workflow-orchestrator
neonwatty
Orchestrates the full mobile browser workflow pipeline - generates, executes, and converts mobile workflows to Playwright tests. Use this when the user says "generate and execute mobile workflows", "run mobile workflow pipeline", "mobile browser test pipeline", or "test mobile experience". Manages configuration (URL, credentials, device), chains generator→executor→converter with approval gates between phases.
ios-workflow-executor
neonwatty
Executes web app workflows in Safari on the iOS Simulator from /workflows/ios-workflows.md. Use this when the user says "run ios workflows", "execute ios workflows", or "test ios workflows". Tests each workflow step by step in mobile Safari, captures before/after screenshots, documents issues, and generates HTML reports with visual evidence of fixes.
cleanddd-requirements-analysis
netcorepal
需求澄清与拆解，识别干系人并将需求条目标注所属对象与业务实体；仅产出结构化需求描述，不做建模定义，可作为后续建模输入
ios-workflow-generator
neonwatty
Generates, creates, or updates iOS workflow files for testing web apps in Safari on the iOS Simulator. Use this when the user says "generate ios workflows", "create ios workflows", "update ios workflows", or "iterate on ios workflows". Thoroughly explores the web app's codebase to discover all user-facing features, pages, and interactions. Creates comprehensive numbered workflows with substeps that cover the full user experience when viewed on iOS Safari.
browser-workflow-executor
neonwatty
Executes browser-based user workflows from /workflows/browser-workflows.md using Claude-in-Chrome MCP. Use this when the user says "run browser workflows", "execute browser workflows", or "test browser workflows". Tests each workflow step by step, captures before/after screenshots, documents issues, and generates HTML reports with visual evidence of fixes.
openclaw-evolution
H1an1
Interactive guide for new OpenClaw users to set up and grow their agent. Two paths - Tool Path (automation, efficiency, getting things done) or Awakening Path (memory, personality, relationship, growth). Use when a user is new to OpenClaw, asks how to get started, wants to set up their agent, or asks about agent configuration. Triggers on "getting started", "new to openclaw", "how do I set up", "agent setup", "onboarding", "进化之路", "新手教程".
AppFactory Builder Skill
0xAxiom
Built by @AxiomBot and @meltedmindz. Ship something.
sp-coding-agent
cuongpt083
Use when a coding task is vague or under-specified. Extracts missing context across 9 code-native categories before the agent executes file changes. Designed for OpenAI Codex, Anthropic Claude Code, and Google Gemini Code Assist.
sp-chat-agent
cuongpt083
Use for custom chat agents (Custom GPTs, Gemini Gems, chatbot workflows) that require strict SMART POLE validation and machine-readable XML output. Not for coding-agent code execution workflows.
parallel-agents
xenitV1
Native multi-agent orchestration using Claude Code's Agent Tool. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives.
team-review
mgiovani
"Multi-agent PR review team orchestration with 7 specialized reviewers for security-sensitive or architectural PRs. Spawns architecture, security, performance, testing, style, docs/UX, and adversary reviewers as a coordinated team. Premium review for critical code changes."
writing-skills
christopher-buss
Use when creating new skills, editing existing skills, or verifying skills work before deployment
docs-diagram
mgiovani
Generate Mermaid diagrams from codebase analysis including architecture,
review-code
mgiovani
Perform comprehensive multi-agent code review for PRs, commits, or entire
compose-ui-control
forketyfork
Control a running Compose Desktop application via HTTP. Use when you need to interact with UI elements, click buttons, enter text, wait for elements to appear, or capture screenshots in a Compose Desktop app that has compose-ui-test-server enabled.
create-command
mgiovani
Create a new slash command (skill) following best practices and prompt
review-security
mgiovani
Perform comprehensive security review targeting OWASP Top 10 2025 vulnerabilities
agent-browser
mgiovani
"Headless browser automation CLI optimized for AI agents. Uses snapshot + refs system for 93% less context overhead vs Playwright. Purpose-built for web testing, form automation, screenshots, and data extraction."
team-implement
mgiovani
"Spec-driven team orchestration: adaptive development team that scales from 3 to 11 agents based on project complexity. Accepts plain text, Jira tickets, GitHub issues, PRs, files, directories, or URLs as input. Plans thoroughly first, gets user approval, then implements with parallel agents."
jira-todo
mgiovani
Generate smart daily work plans with intelligent prioritization from
temporal
mikkelkrogsholm
"Temporal — enterprise-grade durable workflow orchestration platform used by Stripe, Netflix, and Coinbase. Use when building with Temporal: durable workflows, long-running background processes, saga patterns, activity retries and timeouts, signals, queries, updates, worker setup, task queues, Temporal Cloud configuration, or migrating from cron jobs or message queues to reliable orchestration. Covers the TypeScript SDK exclusively."
trellis-meta
mindfold-ai
Meta-skill for understanding and customizing Mindfold Trellis - the AI workflow system for Claude Code and Cursor. This skill documents the ORIGINAL Trellis system design. When users customize their Trellis installation, modifications should be recorded in a project-local trellis-local skill, NOT in this meta-skill. Use this skill when: (1) understanding Trellis architecture, (2) customizing Trellis workflows, (3) adding commands/agents/hooks, (4) troubleshooting issues, or (5) adapting Trellis to specific projects.
dev-skill-creator
mikkelkrogsholm
"Create a new technology documentation skill for the dev-skills library. Use when adding a skill for a specific technology (e.g., bun, hono, react, prisma, stripe, rustfs) that links to official documentation and includes curated best practices. Handles three doc source types: llms.txt URL, GitHub repository, or documentation website. Each skill is thin and agent-agnostic: a triggering description + a live docs pointer + a small curated layer of evergreen gotchas."
fengge-skill
PeterYang0
峰哥亡命天涯 - 独立学者、极限旅行家、纪录片导演，B站独特的深度内容创作者，以"解答世间万物"直播闻名