Workflow Skills for OpenClaw Agents

屏幕自动化工程师

@xiaozs-com

强大的屏幕理解与控制，并创建可维护流程

Iterate

@jingzhao-l

Fully automated multi-round code iteration with configurable N-dimension parallel review, onboarding/personalization, and a cross-assistant installer/update system with mandatory SHA256 checksum verification. v3.0 adds a dual-mode (the original iterate mode plus a defensive-programming mode via /iterate defensive) that performs normal incremental coding tasks with defensive discipline end-to-end.

Llm Workflow Diagnoser

@graysilver

Use this skill whenever a user wants to evaluate whether an existing offline / reusable workflow is worth converting into an LLM-driven workflow. Triggers on...

Handoff

@snowsonz

Continue or inspect a handoff task

workflow-guard-rails

@haiyangchenbj

Wrap multi-step agent workflows with pre-execution checks, side-effect queues, result validation, retry budgets, checkpointing, audit logs, and failure-rule accumulation. Prevents false successes, duplicate sends, unrecoverable crashes, and silent drift in LLM production systems. Use it when a workflow sends, publishes, pays, deletes, or writes to another system, runs unattended on a schedule, or must be safe to rerun after a mid-task failure. Trigger keywords: workflow safety, workflow guardian, agent guard, guardrails, pre-execution check, pre-flight check, retry budget, idempotency, false success, duplicate send, checkpoint recovery, rerun safety, audit log, drift detection, agent reliability, production guardrails, 工作流守护, Agent 护栏, 副作用队列, 漂移检测, 幂等, 防重复发送, 假成功, 断点恢复, 生产护栏, 重跑安全. Guard #7 (rule accumulation) captures confirmed failures in the same turn into a staging file (~/.workbuddy/ERROR-PLAYBOOK.staging.md). Entries reach the authoritative ~/.workbuddy/ERROR-PLAYBOOK.md only when the failure recurs (count >= 2) or a human confirms the rule — durable global guidance is never created by a single unreviewed append. 中文摘要：为多步骤 Agent 工作流加装七项护栏——执行前检查、检查点、副作用队列、预算 重试、结果验证、审计记录、规则沉淀，拦截假成功、重复发送与渐进漂移。触发词：工作流 守护、Agent 护栏、假成功拦截、防重复发送、重试预算、断点恢复、生产护栏、漂移检测.

OpenClaw Agent Orchestrator

@dtsola

OpenClaw multi-agent daily collaboration orchestrator: split a task into subtasks, dispatch to resident agents via sessions_send, track progress via sessions_list/sessions_history, aggregate results with source attribution, and retry failures (default max 3). Reads openclaw.json for agents.list and agentToAgent.allow (bidirectional whitelist); three-tier trigger (explicit dispatch / suggest+ask for fuzzy big tasks / silent otherwise). Use when user asks to orchestrate/coordinate multiple agents, dispatch parallel work, delegate to a named agent, or aggregate results from several agents (orchestrate/parallel/delegate/让 XX 做/编排/并行/ 分给/汇总). 中文：OpenClaw 多 Agent 日常协作编排器——任务拆解、跨 agent 分发（强制 sessions_send）、进度追踪、结果聚合、失败重试（默认最多 3 次）。 三档触发：用户点名或含编排动词直接执行；模糊大任务建议并行并询问用户； 其余情况保持沉默。直接读 openclaw.json（agents.list + agentToAgent.allow 双向白名单）获取 agent 名单与授权。适用于多 agent 家庭协作、并行调研、批量巡检、发布前多视角审查、团队日报汇总等场景。

Handoff

@snowsonz

Continue or inspect a handoff task

Git工作流助手免费版

@thcjp

Git 分支管理、冲突解决与提交规范助手，覆盖个人开发者日常版本控制场景。Use when 需要代码生成、编程辅助、调试测试、开发部署时使用。不适用于无明确技术栈的模糊需求。适用于独立开发者、企业团队和自动化工作流场景。支持中文交互，无需复杂配置即开即用。输出结果可直接使用，减少二次加工成本。提供结构化输出和错误处理机制。

算力超市skills

@likeadmin-hub

基于配置安全调用算力超市完整模型应用与任务开放接口

AI Workflow OS

@englandtong

Route work across specialized AI workflows

demo-asset-ingest

@terrycarter1985

Demonstrates the end-to-end collaboration between a business process workflow (TaskFlow-style workspace orchestration) and a digital asset management tool (ClawHub CLI) — from preparing a publishable artifact to ingesting it into the ClawHub resource center.

auto-workflow

@thcjp

从重复任务构建自动化工作流。Builds automation workflows from repetitive tasks。触发关键词: workflows, repetitive, auto, automation, workflow, builds。支持多种输入格式,输出结构化结果,适配独立开发者与小型团队。

高效会议流程管理助手

@muippt

AI Agent 原生的会议全流程编排 Skill。覆盖会前排期、忙闲查询、会议室预订、日程创建、会前材料生成、会中主持指导、会后纪要提取、TODO 跟踪与知识沉淀。通过可配置适配器对接 Google Calendar、Whisper、Notion、Slack 等工具，零内部依赖，任何 Agent 可用。触发词：meeting flow、会议流程、meeting assistant、会议编排、帮我开个会、预约会议、开会准备、会前材料、会议总结、会议纪要、会后TODO、查忙闲、改期、取消会议、查会议记录、meeting notes、meeting scheduler。不适用：纯任务管理（非会议场景的待办请用专门的任务管理工具）。即使没说 meeting flow，只要提到开会/约会议/会议纪要也要用。

Git工作流

@thcjp

提供中文交互的Git工作流辅助，支持分支管理、冲突解决和提交规范，适合开发者与团队协作使用。

Linear工作流机器人

@thcjp

把 Linear 任务自动接入"通知-执行-回写-Git 同步"流水线。面向独立开发者与一人公司， 解决免费自动化平台额度紧张、Webhook 触发不可靠、多服务配置散乱、Git 同步冲突四大痛点。 核心能力: - 三层自动化平台选型：Make.com（免费首选）/ Pipedream（即时触发）/ Zapier...

Secure Script Runner (Zero‑Exposure Sandbox)

@zkeviny

Zero‑exposure script execution using MGC Blackbox. Store scripts encrypted, execute in blackbox, AI sees no plaintext. Supports MCP (mgc_run) / API / WebUI execution, internal credential calls, and script sealing. Includes MGC 1.4.9 temporary workaround guidelines. This skill only executes scripts w

Git工作流专业版

@thcjp

面向团队协作与企业研发场景的 Git 工作流专业工具。Use when 需要提升效率、自动化流程、批量处理、工作流优化时使用。不适用于需要人工创意判断的任务。适用于独立开发者、企业团队和自动化工作流场景。支持中文交互，无需复杂配置即开即用。输出结果可直接使用，减少二次加工成本。提供结构化输出和错误处理机制。

Daily Note Helper (Trial 2026-08-06)

@terrycarter1985

Create and organize daily work notes with consistent structure, date-based filenames, and lightweight summaries. Use when the user wants to start a daily log, append structured entries to today's note, review recent notes, or generate a concise recap from multiple daily files.

Git工作流

@thcjp

支持中文交互的Git工作流助手，实现分支管理、冲突解决与提交规范，提升团队协作和代码质量。

Solo Workflow Engine

@thcjp

独立者引擎专业版是完整的全功能版本，为独立开发者、一人公司、自由职业者包含完整的七步无代码自发化方法论。从识别机会到计算ROI，全流程覆盖自发化工作流的构建、维护与调优。专业版解锁维护监控、高级自发化场景、ROI计算工具和完整故障排查表. 适用于需要solo workflow engine相关能力的开发场景,提供结构化的工作流程和配置指引.

Git工作流

@thcjp

支持中文交互的Git工作流助手，涵盖分支管理、冲突解决和提交规范，适合个人与团队代码协作使用。

blogizi

@blogizi

Draft, update, and publish SEO blog posts to Blogizi from a local repo using the Blogizi CLI (preferred), hosted MCP as a sandbox backup, or the public API. Use when the user mentions Blogizi, blogizi draft/update/publish, MCP tools, posting markdown to a blog, SEO blog posts, or integrating with th

Assess enterprise AI and automation opportunities from company materials, prioritize up to three testable pilots, and generate evidence-bounded Markdown, HTML, and PDF management reports. Use for AI implementation assessments, pilot prioritization, and material analysis; do not fabricate company fac

分析企业资料并生成可验证的三种 AI 落地诊断报告

ClawHub Ingest Runbook

@terrycarter1985

A minimal, reproducible runbook for chaining a business-process tool (TaskFlow-style workspace orchestration) with the ClawHub CLI to turn processed digital content into a discoverable, installable resource-center entry.

demo-asset

@terrycarter1985

A demo digital asset that has been processed, validated, and packaged in the OpenClaw workspace, then ingested into the ClawHub resource center to show the TaskFlow-style workflow + ClawHub CLI handoff.

Ward Test Scope Routing

@wardlu

Route validation by changed boundaries and risk, choosing the smallest sufficient checks for code, docs, UI, data, auth, sync, build, security, and release work. Use when deciding test commands, reducing unnecessary full-suite runs, auditing test layering, or documenting what was and was not verified.

Ward Codex Doctor

@wardlu

Analyze local Codex session telemetry and produce privacy-safe efficiency reports with actionable workflow recommendations. Use when the user asks to run Codex Doctor, inspect Codex productivity, diagnose context bloat, repository exploration, validation or retry patterns, compare recent sessions, or interpret a codex-efficiency-report HTML/JSON file. Default to local telemetry-only analysis; use the optional compact AI diagnosis only when the user explicitly requests AI interpretation.

Ward Codex Session Repair

@wardlu

Repair Codex Desktop sessions that fail after switching model providers or importing/forking old conversations. Use this skill whenever a user mentions an old Codex session becoming invalid, “model provider not found”, “Codex cannot load config.toml”, remote context compaction 404s, “Item with id rs_... not found”, repeated reconnecting during resume, or a migrated Codex conversation that cannot continue—even when the user only asks to inspect or explain the failure. Diagnose the target session across its JSONL rollout, root state_5.sqlite, config.toml, and logs_2.sqlite, then make a target-scoped backup-first repair with verification and restart instructions.

Ward Agent Privacy Check

@wardlu

Audit an AI agent's reachable data, external data paths, and untrusted instructions, then explain the result in plain language with Low, Medium, High, or Critical severity. Use when a user asks what an agent can see, where data may go, whether a skill, plugin, or tool is safe, or how to reduce agent privacy risk across Codex, Claude Code, or another agent.

Ward Public Repo Git Gate

@wardlu

Run the public-repository gates for Git commits, pushes, and pull requests. Check staged and untracked scope, secrets and personal data, internal material, branches and remotes, PR base/head, CI, and merge prerequisites. Use when the user asks to commit, push, open a PR, review public repository content, or run the complete public-repository gate.

Ward Public Release Gate

@wardlu

Review a public repository release across version and tag consistency, final build artifacts, archives, secrets and internal material, third-party licenses, production response headers, and GitHub Release attachments. Use when the user asks to publish, create a tag or Release, verify a launch, or run the complete public-release gate, adapting checks to the project's configuration.

Ward GitHub Repo i18n

@wardlu

Internationalize the user-facing language layer of a GitHub repository, including its repository description, repository topics, README files, release notes, changelogs, and other explicitly selected documentation, with English as the default and any user-requested locales as mirrors. Use when a user asks to translate, localize, add language mirrors, or check cross-locale parity for a GitHub repository. Confirm the exact document and metadata scope when it is not explicit, identify existing locales, preserve facts, code, commands, links, images, and structure, and provide local Markdown plus GitHub-style previews. Do not use for product UI or runtime i18n, database content, visual README redesign or assets, public-release suitability or security scans, Issue or PR label taxonomies, Git tags, or Git, PR, release, deployment, or production operations.

Collab Ingest Demo

@terrycarter1985

可复现的协作入库演示：用 workflow-structurer 把模糊流程结构化为 handoff，再按 demo-asset-ingest 规范打包，最终通过 clawhub 发布到资源中心。本资产即一次真实入库的产物，DESCRIPTION.md 为上游流程梳理结果。

PR Delivery through Slack

@alvolutionor

Send PRs and announce after a verified clean review

Issues and Branches

@alvolutionor

Create Jira issues and verified Bitbucket branches

Process to Ingest Runbook

@terrycarter1985

端到端运行手册：先用 workflow-structurer 把一份数字内容梳理成结构化流程文档，再按 demo-asset-ingest 规范打包并通过 clawhub publish 入库到 ClawHub 资源中心。适用：把可用数字内容沉淀为可检索、可安装资源，且需要可复现步骤。

collab-workflow-ingest

@terrycarter1985

协作流程：业务流程梳理 → 数字资源入库。先用 workflow-structurer 逐步澄清流程，生成结构化步骤文档；再用 demo-asset-ingest 的打包规范将成果发布到 ClawHub 资源中心。适用场景：需要将模糊需求转化为可执行流程、并把最终产物沉淀到可检索仓库的工作。

Workflow Essentials

@thcjp

工作流精要专业版是在免费版基础上的全功能升级，为AI Agent包含完整的自发化工作流方法论。不同于面向特定角色或特定工具的指南，工作流精要聚焦自发化的通用原理与系统方法。专业版解锁六步完整框架、六种设计模式、四种进阶场景、维护策略和完整故障排查表. 适用于需要workflow essentials相关能力的开发场景,提供结构化的工作流程和配置指引.

Right-Size Superpowers

@snowsonz

Scale Superpowers workflow depth to task risk

dify-dsl-to-code

@somkh

将 Dify 导出的工作流/Chatflow DSL 文件（YAML）转化为可部署、可运行的独立代码项目（默认 Python+FastAPI，可选 Node.js+Express）。当用户要求"Dify 工作流转代码"、"DSL 导出转项目"、"把 Dify 应用代码化"、"脱离 Dify 部署工作流"时使用。

scenario-standards

@fize

Development scenario routing and phase standards methodology. Triggers when user requests involve writing/modifying/designing/deploying code. Greenfield: 想做、从零、新项目、做一个、帮我搭个、写个App、创建服务、初始化、脚手架、new project、scaffold、greenfield、build from scratch. Feature: 加功能、新增、迭代、实现、添加、支持、接入、集成、add feature、implement、integrate、enhancement. Bug fix: 报错、bug、不工作、崩溃、异常、出错、失败、返回500、空指针、panic、error、crash、fix、hotfix、debug、troubleshoot. Refactor: 重构、优化、太慢、太乱、清理、改进、性能、拆分、refactor、optimize、perf、cleanup、restructure. Deploy: 部署、上线、发版、容器化、发布、deploy、release、CI/CD、Docker、K8s、helm、rollout、ship. Implicit triggers: pasting build errors, PRD → implementation, design DB/API, write tests. Explicit override: @phase:requirement|architecture|backend|frontend|devops

coding-tactics

@fize

Tactical coding methodology selector and executor. Auto-selects the appropriate development method (TDD / BDD / API-First / Security-First / Direct Implementation) based on task context, or use the specified method directly. Use when a user requests a method, scenario-standards reaches implementation, or the task context implies one. Supports direct invocation: `/coding-tactics tdd`, `/coding-tactics bdd`, etc.