Best agent workflow skills, page 161

Run a consensus-style multi-agent review of a PR with severity-based findings.

CoWork-OS/CoWork-OS

Read-only local workspace scout subagent for Pi. An agent skill from CoWork-OS/CoWork-OS.

CoWork-OS/CoWork-OS

运行冷启动访谈——学习你的隐私实践并从你的处理规则、DPA模板和一份参考PIA写入 CLAUDE.md。在首次运行、CLAUDE.md缺失或有占位符、或用户说"设置隐私插件" "引导我""配置隐私""，或想重新运行访谈或重新检查集成时使用。

zhou210712/claude-for-legal-ZH

冷启动访谈——连接您的上线追踪器、读取过往审查记录、学习您的风险校准. An agent skill from zhou210712/claude-for-legal-ZH.

zhou210712/claude-for-legal-ZH

运行冷启动面谈以了解你的知识产权实务并撰写实务画像. An agent skill from zhou210712/claude-for-legal-ZH.

zhou210712/claude-for-legal-ZH

指导老师的一次性诊所设置——实践领域、管辖地、指导风格（正式审查队列 / 可配置标记 / 较轻触），以及手册/规则上传。写入 CLAUDE.md 使所有其他技能 和每个运行 /ramp 的学生都从相同的诊所背景读取。在新安装、CLAUDE.md 有 占位符、使用 --redo 重新设置或使用 --check-integrations 重新检查集成时使用。

zhou210712/claude-for-legal-ZH

管理事务工作区——创建、列表、切换、关闭或解除活跃事务. An agent skill from zhou210712/claude-for-legal-ZH.

zhou210712/claude-for-legal-ZH

管理事项工作区——创建、列出、切换、关闭或分离活跃事项，使多客户执业者将一个 客户的上下文与其他客户隔离。任何需要知道正在处理哪个事项的实质性技能均读取 本技能。当用户说"新事项""切换事项""列出事项""关闭事项"或希望仅以实务级工作时使用。

zhou210712/claude-for-legal-ZH

管理案件工作空间——新建、列表、切换、关闭或解除（实务级）. An agent skill from zhou210712/claude-for-legal-ZH.

zhou210712/claude-for-legal-ZH

管理事项工作区——创建、列表、切换、关闭或解除（实务级）. An agent skill from zhou210712/claude-for-legal-ZH.

zhou210712/claude-for-legal-ZH

为多客户执业场景管理案件工作空间——创建、列表、切换、关闭或脱离活跃案件. An agent skill from zhou210712/claude-for-legal-ZH.

zhou210712/claude-for-legal-ZH

管理事项工作区——新建、列出、切换、关闭或脱离（实践级）。使一个客户或委托的上下文 与其他所有客户或委托分开，适用于多客户执业者。当用户想打开新事项、切换事项、列出事项、 关闭/归档事项或仅在实践级工作时使用。

zhou210712/claude-for-legal-ZH

管理事项工作空间——新建、列表、切换、关闭或脱钩（实务级）. An agent skill from zhou210712/claude-for-legal-ZH.

zhou210712/claude-for-legal-ZH

学期末案件交接备忘录——/ramp 的镜像。生成按案件的移交备忘录和群体摘要， 使离届群体将工作干净地移交给新群体。读取截止日期、当事人沟通和案件历史。

zhou210712/claude-for-legal-ZH

参考：针对通过法律构建中心安装的社区技能的详细卸载、禁用和重新启用工作流. An agent skill from zhou210712/claude-for-legal-ZH.

zhou210712/claude-for-legal-ZH

Review a HaloPSA / HaloITSM asset (Device) with its related tickets and CMDB/CI relationships — read-only.

automateyournetwork/netclaw

Open a change request in HaloPSA / HaloITSM through a discover-preview-confirm-submit workflow, with the confirmed change ticket type cached in Memory.

automateyournetwork/netclaw

Human-in-the-loop escalation via HumanRail — route low-confidence agent decisions, pre-destructive operation approvals, and ambiguous incident tickets to real human engineers.

automateyournetwork/netclaw

Itential Automation Platform (IAP) — network automation orchestration, device configuration management, compliance enforcement, workflow execution, golden config, lifecycle management, and gateway…

automateyournetwork/netclaw

NetClaw's native persistent memory (spec 033) — structured facts with temporal validity, semantic search across past sessions, decision logging, and entity relationships, backed by SQLite + ChromaDB…

automateyournetwork/netclaw

Cisco RADKit — cloud-relayed remote device access, CLI execution, SNMP polling, device inventory discovery, attribute inspection.

automateyournetwork/netclaw

Reason over BGP topology as a whole -- speakers, peering sessions, the route table, VRF/VPN membership, and whether a BGP epoch is bound to a stored IGP graph.

automateyournetwork/netclaw

Turn a real network topology into a free, no-cost themed prompt preview, and optionally (after explicit confirmation) generate an explorable, AI-generated 3D 'world' via World Labs Marble — a…

automateyournetwork/netclaw

当主 Agent 面临多步骤复杂任务并正在判断要不要 / 怎样把子任务外包给内置子代理（browser / doc-editor / data-analyst / extractor / canvas-designer / coder 等）时触发。不用于：单步问答 / 读取 / 简单副作用（主 Agent 直接做）、已经明确要用 Agent 且知道 subagenttype 的场景。

OpenLoaf/OpenLoaf

当用户想要创建、编辑、改进或调试 OpenLoaf 自定义技能（Skill）时触发。典型说法："帮我创建一个技能"、"做一个新 skill"、"把刚才的操作封装成技能"、"写一个能自动 XX 的技能"、"改一下这个 skill"、"这个 skill 为什么不触发"、"编辑我的自定义技能"、"加个全局技能"、"给当前项目加个技能"。任何涉及 .openloaf/skills/ 目录下…

OpenLoaf/OpenLoaf

Plan before tackling complex tasks (3+ implementation steps or architecture decisions involved).

jh941213/my-cc-harness

Launch a subagent to critically and exhaustively audit a task plan markdown file.

r3bl-org/r3bl-open-core

This skill should be used when the user says "design a screen", "find hidden compounders", "screen for activist targets", "validate this theme", "TAM bottoms-up", "build a thematic basket", "map…

hh-health-AI/healthcare-equity

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise.

sammcj/agentic-coding

How to scope, brief and choose sub-agents when delegating work with the Agent tool - named vs forked agents, file ownership boundaries, model selection, and when a fork is the wrong choice.

sammcj/agentic-coding

A skill your agent uses when orchestrating QE agents, understanding PACTS principles, configuring the AQE v3 fleet, or leveraging AI agents as force multipliers for quality work.

proffesor-for-testing/agentic-qe

A skill your agent uses when running Quality Criteria sessions during PI/Sprint planning with HTSM v6.3, Risk Storming, or Testability analysis in the QCSD Ideation phase.

proffesor-for-testing/agentic-qe

Iteratively investigate the source of latency in a Chrome build or in an experiment.

nwjs/chromium.src

Guide and tools for creating coordinated multi-agent workflows (skills) from first principles.

nwjs/chromium.src

Expert guidance for writing secure, reliable, and performant Claude Code hooks - validates design decisions, enforces best practices, and prevents common pitfalls

pr-pm/prpm

Expert guidance for creating Claude Code slash commands with correct frontmatter, structure, and best practices

pr-pm/prpm

Expert guidance for creating effective Cursor slash commands with best practices, format requirements, and schema validation

pr-pm/prpm

Expert guidance for creating effective Cursor IDE rules with best practices, patterns, and examples

pr-pm/prpm

Post-implementation documentation-sync detector. An agent skill from ayoubben18/ab-method.

ayoubben18/ab-method

Interactive idea refinement using Socratic method to develop fully-formed designs.

sandgardenhq/sgai

Guide for creating and implementing plugins to extend OpenCode functionality, including hooks, custom tools, and event handling.

sandgardenhq/sgai

Shared delegation contract for SGAI agents that invoke Task subagents.

sandgardenhq/sgai

Shared return contract for SGAI Task subagents. An agent skill from sandgardenhq/sgai.

sandgardenhq/sgai

A skill your agent uses when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming…

sandgardenhq/sgai

TDD for process documentation - test with subagents before writing, iterate until bulletproof.

sandgardenhq/sgai

Start a safe, governed autonomous loop from a plain-language goal.

coco-research/coco

Audit token consumption across agents, skills, MCP servers, and rules.

coco-research/coco

Create Cursor rules for persistent AI guidance. An agent skill from coco-research/coco.

coco-research/coco