智能体
Agent 规划、多步流程与编排
oss-hunter
jackjin1997
Automatically hunt for high-impact OSS contribution opportunities.
Azure Backup Recovery
markus41
Deep expertise in Azure Backup Recovery operations with deterministic runbooks, fail-fast context validation, and redacted output requirements.
langsmith-evaluator
jackjin1997
Use this skill for ANY question about CREATING evaluators. Covers creating custom metrics, LLM as Judge evaluators, code-based evaluators, and uploading evaluation logic to LangSmith. Does NOT cover RUNNING evaluations.
langchain-agents
jackjin1997
Use this skill for ANY coding question involving LangChain products (LangChain, LangGraph, LangSmith SDK). Covers agent development patterns, primitives, context management, multi-agent systems, and when to use create_agent vs create_deep_agent vs raw LangGraph. Consult this BEFORE writing any LangChain-related code.
guidelines-advisor
runkids
Smart contract development advisor based on Trail of Bits' best practices. Analyzes codebase to generate documentation/specifications, review architecture, check upgradeability patterns, assess implementation quality, identify pitfalls, review dependencies, and evaluate testing. Provides actionable recommendations.
designing-workflow-skills
runkids
Guides the design and structuring of workflow-based Claude Code skills with multi-step phases, decision trees, subagent delegation, and progressive disclosure. Use when creating skills that involve sequential pipelines, routing patterns, safety gates, task tracking, phased execution, or any multi-step workflow. Also applies when reviewing or refactoring existing workflow skills for quality.
multiversx-protocol-experts
multiversx
Deep protocol knowledge for MultiversX architecture including sharding, consensus, ESDT standards, and cross-shard transactions. Use when reviewing protocol-level code, designing complex dApp architectures, or troubleshooting cross-shard issues.
mvx_protocol_experts
multiversx
Expert knowledge of the MultiversX Protocol, Consensus (SPoS), Sharding, and Standard Implementations (MIPs).
secure-workflow-guide
runkids
Guides through Trail of Bits' 5-step secure development workflow. Runs Slither scans, checks special features (upgradeability/ERC conformance/token integration), generates visual security diagrams, helps document security properties for fuzzing/verification, and reviews manual security areas.
cosmos-vulnerability-scanner
runkids
Scans Cosmos SDK blockchains for 9 consensus-critical vulnerabilities including non-determinism, incorrect signers, ABCI panics, and rounding errors. Use when auditing Cosmos chains or CosmWasm contracts.
c3-change
lagz0ne
Orchestrates architectural changes through Agent Teams with ADR-first workflow. This skill should be used when the user asks to: - "add a component", "add feature", "add X to Y", "new component", "create new service" - "add endpoint", "add API", "add middleware", "add handler", "add route" - "change architecture", "modify X", "update component", "refactor X" - "fix X", "fix bug", "fix issue", "implement X", "implement feature" - "remove component", "delete component", "deprecate X" - "provision X", "design the architecture for X", "plan X architecture" - "replace X with Y", "migrate X", "upgrade X" DO NOT use for: "what is X", "how does X work", "explain X" (route to c3-query). DO NOT use for: "add pattern", "create ref", "update ref" (route to c3-ref). DO NOT use for: "audit C3", "validate docs" (route to c3-audit). Requires .c3/ to exist. All changes flow through ADR process with Agent Teams.
Agent Foundry
markus41
Deep expertise in the Azure AI Foundry agent lifecycle — scaffold agent definitions, deploy to Azure AI Agent Service, manage threads and runs, configure built-in tools (code interpreter, file search, Azure AI Search, function calling), run quality and safety evaluations, and monitor agent health. Use this skill when a user asks to build an agent on Azure AI Foundry, create or deploy a Foundry agent, test an agent thread or run, configure agent tools, evaluate agent output quality, troubleshoot Azure AI Agent Service errors, or set up Service Principal authentication for AI Foundry.
eachlabs-workflows
eachlabs
Build and orchestrate multi-step AI workflows combining multiple EachLabs models. Create custom pipelines, trigger executions, and manage workflow versions. Use when the user needs to chain multiple AI models or automate multi-step content creation.
cloud-agent
malue-ai
将任务委托给云端 Agent 执行。云端拥有隔离代码沙箱、项目构建发布到公网、24/7 持续运行等本地不具备的能力。适用于需要沙箱执行、应用发布、不受开机限制的长任务。支持带文件委托。
wardley
neurofoo
Wardley Mapping strategic analysis—map value chains against evolution to reveal build vs buy decisions and competitive dynamics. Use for technology strategy or investment decisions.
writing-skills
julianromli
Use when creating new skills, editing existing skills, or verifying skills work before deployment
dispatching-parallel-agents
julianromli
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
shadcn-management
julianromli
Manage shadcn/ui components using MCP tools. Use when user needs to: (1) Add new shadcn components to a project (2) Build complex UI features requiring multiple components (3) Research component implementations and examples (4) Get component installation commands Triggers: "add shadcn", "shadcn component", "build UI with shadcn", "install component", "create form", "create dialog"
verification-before-completion
julianromli
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
find-skills
julianromli
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
mobile-browser-workflow-executor
neonwatty
Executes mobile browser workflows from /workflows/mobile-browser-workflows.md using Playwright MCP with mobile viewport emulation. Use this when the user says "run mobile browser workflows", "execute mobile browser workflows", or "test mobile browser workflows". Tests each workflow step by step in a mobile Chrome viewport (393x852), captures before/after screenshots, audits iOS HIG anti-patterns, documents issues, and generates HTML reports with device frame mockups.
mobile-browser-workflow-generator
neonwatty
Generates, creates, or updates mobile browser workflow files for testing web apps with Chrome mobile viewport emulation. Use this when the user says "generate mobile browser workflows", "create mobile browser workflows", "update mobile browser workflows", or "iterate on mobile browser 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 mobile user experience.
browser-workflow-to-playwright
neonwatty
Translates browser workflow markdown files into Playwright E2E tests for CI. Use this when the user says "convert workflows to playwright", "translate workflows to CI", "generate playwright tests from workflows", or wants to promote refined browser workflows to automated CI tests.
browser-workflow-generator
neonwatty
Generates, creates, or updates browser workflow files. Use this when the user says "generate browser workflows", "create browser workflows", "update browser workflows", or "iterate on browser workflows". Thoroughly explores the app's codebase to discover all user-facing features, routes, and interactions. Creates comprehensive numbered workflows with substeps that cover the full user experience.