智能体
Agent 规划、多步流程与编排
readiness-report
OpenHands
Evaluate how well a codebase supports autonomous AI development. Analyzes repositories across eight technical pillars (Style & Validation, Build System, Testing, Documentation, Dev Environment, Debugging & Observability, Security, Task Discovery) and five maturity levels. Use when users request /readiness-report or want to assess agent readiness, codebase maturity, or identify gaps preventing effective AI-assisted development.
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.
llamaindex-agent
a5c-ai
LlamaIndex agent and query engine setup for RAG-powered agents
cron
HKUDS
Schedule reminders and recurring tasks.
async-jobs
yonatangross
Async job processing patterns for background tasks, Celery workflows, task scheduling, retry strategies, and distributed task execution. Use when implementing background job processing, task queues, or scheduled task systems.
agent-orchestration
yonatangross
Agent orchestration patterns for agentic loops, multi-agent coordination, alternative frameworks, and multi-scenario workflows. Use when building autonomous agent loops, coordinating multiple agents, evaluating CrewAI/AutoGen/Swarm, or orchestrating complex multi-step scenarios.
improvement-loop
aaddrick
Use after resolving a bug, failed task, or unexpected agent behavior to improve the pipeline skills, agents, hooks, or scripts that contributed to the problem. Also proactively suggest improvements when recurring patterns or inefficiencies are observed.
pivoting-tunneling
blacklanternsecurity
Network pivoting, port forwarding, and tunneling through compromised hosts to reach internal networks.
orchestrator
blacklanternsecurity
USE THIS SKILL when the user provides a target or list of targets (IPs, hostnames, URLs, subnets) and asks to attack, pentest, hack, scan, assess, or test them. ALSO USE THIS SKILL when the user references an existing engagement — resuming, continuing, picking up, checking status, or asking about next steps. Trigger phrases: "attack X", "pentest X", "hack X", "scan X", "start testing X", "pop X", "CTF target X", "engage X", "these targets", "resume engagement", "pick it up", "continue testing", "next steps", "where were we", "resuming", "advise next steps", "what should we do next", "engagement status". This is the entry point for all multi-phase penetration tests — handles recon, attack surface mapping, vulnerability chaining, and routes to technique skills for exploitation. Do NOT use when the user names a specific single technique (e.g., "run kerberoasting against X").
assess
yonatangross
"Assesses and rates quality 0-10 with pros/cons analysis. Use when evaluating code, designs, or approaches."
human-oversight-protocol
bdfinst
Approval gates, intervention commands, and transparency requirements. Use to classify any agent action as autonomous/notify/approve, respond to override/pause/stop commands, or structure a plan review before the implementation phase begins.
core-agent-browser
actionbook
Rust Developer AI Assistance System — Meta-Problem-Driven Knowledge Indexing
digital-twin-modeling
kishorkukreja
When the user wants to build digital twins, simulate supply chain operations, or create virtual replicas for testing. Also use when the user mentions "digital twin," "simulation modeling," "discrete event simulation," "system simulation," "virtual supply chain," "what-if analysis," "scenario simulation," or "operational testing." For network optimization, see network-design. For forecasting, see demand-forecasting.
skill-authoring
knoopx
Writes effective pi skills with proper structure, concise content, and progressive disclosure. Use when creating new skills, improving existing skills, or reviewing skill quality.
daily-standup
knoopx
Generates daily standup updates from session activity and commits. Use when preparing standups, reviewing daily progress, or aggregating work across projects.
ghost-scan-deps
ghostsecurity
Ghost Security - Software Composition Analysis (SCA) scanner. Scans dependency lockfiles for known vulnerabilities, identifies CVEs, and generates findings with severity levels and remediation guidance. Use when the user asks about dependency vulnerabilities, vulnerable packages, CVE checks, security audits of dependencies, or wants to scan lockfiles like package-lock.json, yarn.lock, go.sum, or Gemfile.lock.
electronics-supply-chain
kishorkukreja
When the user wants to optimize electronics manufacturing supply chains, manage semiconductor sourcing, handle PCB assembly, or navigate component allocation. Also use when the user mentions "electronics manufacturing," "semiconductor supply chain," "PCB assembly," "EMS/ODM," "component allocation," "lead time management," "electronics sourcing," "PCBA," "contract manufacturing," or "electronics lifecycle management." For general manufacturing, see production-scheduling. For quality, see quality-management.
debug-mode
BasedHardware
"Debug mode workflows and best practices for troubleshooting bugs, regressions, and performance issues. Use when debugging tricky issues that standard agent interactions struggle with."
agent-modes
BasedHardware
"Guidance on choosing and using Cursor agent modes: Agent, Ask, Plan, and Debug. Use when selecting the right mode for a task or when explaining mode capabilities."
agentation-self-driving
benjitaylor
Autonomous design critique mode using the Agentation annotation toolbar. Use when the user asks to "critique this page," "add design annotations," "review the UI," "self-driving mode," "auto-annotate," or wants an AI agent to autonomously add design feedback annotations to a web page via the browser. Requires the Agentation toolbar to be installed on the target page and agent-browser skill to be available.
complex-task
TeamWiseFlow
长程/复杂任务编排工作指导。接收复杂任务后，依次完成验收标准确认、计划拆分与自审、项目文件初始化、子任务文档创建、执行者-评估者 subagent
agent-review
BasedHardware
"Agent Review workflows and best practices for catching bugs before merging. Use for reviewing agent-generated code and local changes."
pydantic-ai-testing
existential-birds
Test PydanticAI agents using TestModel, FunctionModel, VCR cassettes, and inline snapshots. Use when writing unit tests, mocking LLM responses, or recording API interactions.
pydantic-ai-dependency-injection
existential-birds
Implement dependency injection in PydanticAI agents using RunContext and deps_type. Use when agents need database connections, API clients, user context, or any external resources.