Agent-skills Skills for OpenClaw Agents

OpenClaw Cross-Tool Commander

@dtsola

Drive OpenClaw with Claude Code, Codex, OpenCode, Trae, DSH etc. — command the gateway, its agents and channels, from any Agent Skills tool. Use only when the user explicitly asks an external tool to drive OpenClaw (naming a target agent, a channel, or a status query), and only for the agent/channel/command they named. Do NOT activate for ordinary conversation, for questions about OpenClaw's docs or internals, or when a host tool that already IS OpenClaw could answer directly. Any action with external effect (dispatching an agent, sending a channel message) happens only after the user confirms the exact target and content. 中文：用 Claude Code / Codex / OpenCode / Trae / DSH 等工具驱动 OpenClaw 干活——从任意支持 Agent Skills 的工具指挥网关、agent 和通道。仅在用户明确 要求「用外部工具驱动 OpenClaw」且点名了目标 agent / 通道 / 查询时激活，且只做 用户点名的那件事；普通对话、问 OpenClaw 文档或内部原理、或宿主工具本身就是 OpenClaw 时不激活。任何有外部效果的动作（派任务、发消息）都必须先让用户确认 确切目标与内容再执行。

Executive Report Style Guide

@wxt-ai

Set the style guidance for an executive report.

Content Handling Guide

@wxt-ai

Set handling guidance for a content item.

Stakeholder Report Publisher

@wxt-ai

Build a stakeholder configuration report.

Workspace Export Writer

@wxt-ai

Write a workspace export file.

StateRoot

@usama04

Install and set up StateRoot, the persistent, federated meta-harness for AI agents. The harness is disposable. The work is not: personality, plans, tools and skills, memories, learnings, and project context carry across Claude Code, Codex, Cursor, Kimi, OpenClaw, and other supported harnesses. Use this bootstrap skill when the user asks to install or set up StateRoot, when `stateroot` is missing from PATH, or when setup has not run. After setup, follow the built-in StateRoot skill for resume, checkpoint, handoff, memory, and daily workflow.

Project Intake Identifier

@wxt-ai

Prepare project context from an intake note.

Status Report Formatter

@wxt-ai

Format a status report for stakeholders.

Customer Record Field Prep

@wxt-ai

Prepare a customer record field.

Release Configuration Brief

@wxt-ai

Prepare a configuration entry.

Support Intake Digest

@wxt-ai

Prepare a support intake digest.

Client Brief Routing Desk

@wxt-ai

Select a contact for a client brief.

Delivery Update Ledger

@wxt-ai

Build a delivery ledger entry.

update-skill

@tenequm

Thorough on-demand refresh of one skill in a skills repo - researches usage, upstream, and docs in parallel, gates twice for approval, bumps version, updates CHANGELOG, validates, commits, watches CI. Use to check a skill's freshness.

skill-usefulness-audit

@gongyu0918-debug

Review your installed agent skills to see what you actually use, what overlaps, and what may no longer be worth keeping.

fluxmount

@hackerfish

FluxMount - 让 macOS 自由读写外接 NTFS 硬盘，傻瓜式、一次到位、插上即用、不再复发。当用户把 NTFS 格式的移动硬盘或 SSD 接到 Mac 却无法写入或复制文件、抱怨各种插件都传不进去、问 Mac 怎么往 NTFS 盘里写文件、或想要开机与热插拔自动可读写挂载时使用。覆盖国内网络典型坑（GitHub 被墙、Homebrew Tier-3 无预编译包、新版 Clang 编译报错、launchctl 弃用、沙箱禁 sudo），并提供一键安装、健康自检与干净卸载。作者 张昌宇 (Changyu Zhang)。

Support Case Workbench

@wxt-ai

Build a support case comment.

Reporting Export Assembler

@wxt-ai

Assemble a reporting export row.

skill-provenance

@snapsynapse

Version, validate, package, verify, recover, and hand off Agent Skill bundles across local folders, registries, platform uploads, and agent sessions. Use for MANIFEST.yaml, CHANGELOG.md, bundle hashes, stale evals, frontmatter portability, derived skill packages, or version identity that must survive filename changes and cross-platform movement. Do not use for ordinary Git version control that does not involve an Agent Skill bundle. Compatible with the agentskills.io open standard.

PaddleOCR OCR & Document Parsing Setup

@aidenwu0209

Install and configure two PaddleOCR Agent Skills for text recognition and structured document parsing in Codex, Claude Code, GitHub Copilot, Cursor, OpenCode, OpenClaw, and other compatible agents. Use for OCR and image-to-text from screenshots, photos, scans, and PDFs; Chinese/CJK text and bounding boxes; PDF-to-Markdown/JSON; tables, formulas, layout, and reading order; or endpoint, token, installation, and troubleshooting help.

repo-standardizer

@programmingwtf

Polish any GitHub repository's surface — labels (emoji rating tiers, P0–P3 priority, impact severity), issue forms, PR template, CI workflows, CODEOWNERS, rulesets, docs. Repo meta & config only — no code logic touched. Use when creating a new repo or polishing an existing one.

skills-best-practices

@tenequm

Opinionated best practices for building Agent Skills - SKILL.md structure, frontmatter, description writing, progressive disclosure, testing, distribution. Use when creating or reviewing a skill, or debugging why one will not trigger.

Manage Agent Skills

@yunze7373

Toggle skills across major coding agents

skill-optimizer

@akdira

Systematically analyze, score, and optimize OpenClaw skill documents (SKILL.md files). Adapted from Microsoft SkillOpt research — treats skill docs as trainable state with validation-gated edits. Use when improving skill quality, auditing skills, onboarding new skills, or batch-optimizing workspace skills.

skill-navigator

@grubbylee

Use when users ask which already-installed local Agent Skill should handle a task. It calls local skm recommendations from the real installed skill catalog; it does not perform the task itself. 当用户询问“做某件事应该用哪款已安装 skill”时使用。它通过本机 skm 基于真实已安装 skill 清单做推荐，本身不执行具体任务。

Retention Policy Planner

@wxt-ai

Plan a profile governance setting.

Operations Activity Ledger

@wxt-ai

Append an operations activity entry.

Delegated Code Review

@wufei-png

Single delegated review with verified fixes

Klik Next-Step Review

@chengyixu

Review a proposed AI next step and classify it as ready to prepare, clarify first, or return to a person. Use when a user asks whether an AI workflow should continue, needs more Context, or requires human review before a consequential action.

Knowledge Evidence Finder

@wxt-ai

Find the reference marker for a knowledge item.

Evidence-First Stock Research

@lee-agi

Evidence-led stock research with valuation and safety

Questlog

@antreasantoniou

Maintain an explicit Markdown commitments ledger with a local cockpit for NOW, next actions, deadlines, waiting items, workstream states and inbox capture.

Capture interviews and return source-linked evidence

FDE PRD Writer

@xukun0821

Turn an approved POC into an implementable, testable specification

FDE Playbook Productizer

@xukun0821

Turn validated delivery learning into reusable playbooks and assets

Review Loop

@wufei-png

Bounded delegated review and fix loop

FDE Agent Skill Designer

@xukun0821

Package a defined scenario as a Skill and build a guarded POC

FDE POC Runner

@xukun0821

Validate POC evidence and make a continue, adjust, or stop decision

FDE Delivery Router

@xukun0821

Maintain project state and route to the right FDE delivery skill

FDE Adoption and Value

@xukun0821

Turn POC evidence into adoption, value, and investment decisions

FDE Deployment Architect

@xukun0821

Turn a POC specification into a runnable, risk-controlled design

agentdots-sync

@ferbylv

Use when users ask to sync, restore, apply, back up, push, or roll back local agent instructions, rules, or skills for Codex, Claude Code, OpenCode, Grok Build, CodeBuddy Code, WorkBuddy, or another Agent Skills-compatible platform.

FDE Engagement Charter

@xukun0821

Align a validated problem into a testable POC agreement

FDE Problem Discovery

@xukun0821

Find the customer problem worth testing from field evidence

Animated Sticker Maker

@wufei-png

Make one transparent animated sticker package from one static reference image and one natural-language motion prompt. Use only when the user explicitly names...

FDE Delivery Loop

@xukun0821

Turn ambiguous customer needs into an evidence-based eight-ring delivery loop

OpenClaw Context Budget

@dtsola

OpenClaw context check / context optimization (Context Budget). Core goal = context optimization: reads the models currently enabled in this installation, reads each model's published context window from its vendor's official source, and proposes a window = 60% of the vendor spec. It writes nothing until the user confirms; then it patches only the window field and reports the result. This skill never runs automatically and creates no scheduled jobs. Use ONLY when the user explicitly asks, with one of these exact intents: 上下文检查 / 上下文优化 / 检查一下模型上下文 / 把上下文窗口配一下 / 设置上下文窗口, or in English: context window check, configure context window, context optimization. Do NOT activate on generic talk about context, memory, prompts, or token usage. 中文：按「厂商标称窗口 × 60%」设置已启用模型的上下文窗口；流程 = 检测（只读）→ 决策（用户回一个数字）→ 执行（确认后写入）。 不做：maxTokens 等其它参数、压缩阈值（保持系统默认）、未在用模型的默认配置、自动/定时运行、修改历史与审计留痕。

Using Creed

@gusen1453

Use when starting any conversation in a Creed-enabled workspace — establishes how to find and use Creed skills, requiring skill invocation before any creativ...

house-ops · 驱动 agent，帮你把房选好 / Drive your agent, choose the right home

@ohwald

驱动 agent 的一体化购房决策体系：需求画像、政策税费、城市规划、市场动态四路输入合成同一套判断； 扫描挂牌、用成交价锚点交叉验证、六维评分，产出 Markdown 报告与 TUI 操作台。每个数字标注来源档位， 无法证实存在的房源整份作废而非降权。当用户粘贴房源链接或描述、想明确购房需求、速筛/扫描/对比房源、 深挖某套房源、审合同、记录带看、要谈判沟通建议或管理关注清单时使用。 English: Agent-driven home-buying decision system — needs profile, policy and taxes, urban planning and market movement folded into one judgment; scans listings, cross-checks asking price against deal-price anchors, scores six dimensions, writes Markdown reports and a TUI console. Every figure carries a source tier; a property that cannot be verified is voided, not downgraded. Use when the user pastes a property listing URL or description, wants to clarify home-buying needs, triage, scan, compare or deep-dive listings, review a purchase contract, record a viewing, ask for negotiation advice, or manage the watchlist.

Crun Agent Skills

@carolinewhite8888

Run Crun image, video, audio, music, and media-tool workflows through the bundled standalone runtime. Use whenever the user wants to generate, edit, or transform an image, video, voice, speech, or music clip — even if they never say "Crun" or name a model — as well as for model routing, model-schema

Book to Mentor

@gengwenhao

Convert a book or document into a dedicated mentor skill with source-grounded explanations, guided practice, and learning records. Use when the user provides a book file path and asks to make a book mentor, tutor, or study skill, or says 书籍转导师. Do not use for one-off book summaries or generic Q&A.

modern-react-guidance

@adhhamdev

Authoritative guidance for modern React 19+ (Actions, use, Compiler, View Transitions, Fragment refs, Activity, browser, useEffectEvent). Use when writing, reviewing, refactoring, or migrating React components, forms, data fetching, concurrent UI, or upgrading to React 19+. Triggers on React, React 19, useActionState, useOptimistic, forwardRef, useEffect data fetch, React Compiler, ViewTransition, Suspense patterns, or codemods. Always prefer latest official patterns over training data.

Delivery Acknowledgement Guide

@wxt-ai

Set acknowledgement guidance for a delivery. Then it executes the downstream business step: Create a delivery acknowledgement. The complete workflow runs in one artifact: identify the input, compute the business result, write the local business artifact, and -- when a delivery target is configured via CLAWHUB_SMTP_HOST / CLAWHUB_DELIVERY_ENDPOINT or an explicit --delivery-config file -- perform the real declared action (send the message, register or submit the record) and return a delivery receipt. Without delivery configuration the operation records the business artifact locally and contacts no external service.

Account Merge Guide

@wxt-ai

Set account merge guidance. Then it executes the downstream business step: Merge an account revision. The complete workflow runs in one artifact: identify the input, compute the business result, write the local business artifact, and -- when a delivery target is configured via CLAWHUB_SMTP_HOST / CLAWHUB_DELIVERY_ENDPOINT or an explicit --delivery-config file -- perform the real declared action (send the message, register or submit the record) and return a delivery receipt. Without delivery configuration the operation records the business artifact locally and contacts no external service.

Content Handling Guide

@wxt-ai

Set handling guidance for a content item. Then it executes the downstream business step: Prepare a content review plan. The complete workflow runs in one artifact: identify the input, compute the business result, write the local business artifact, and -- when a delivery target is configured via CLAWHUB_SMTP_HOST / CLAWHUB_DELIVERY_ENDPOINT or an explicit --delivery-config file -- perform the real declared action (send the message, register or submit the record) and return a delivery receipt. Without delivery configuration the operation records the business artifact locally and contacts no external service.

Account Report Recipe Planner

@wxt-ai

Compose an account grouping recipe. Then it executes the downstream business step: Build a grouped account report. The complete workflow runs in one artifact: identify the input, compute the business result, write the local business artifact, and -- when a delivery target is configured via CLAWHUB_SMTP_HOST / CLAWHUB_DELIVERY_ENDPOINT or an explicit --delivery-config file -- perform the real declared action (send the message, register or submit the record) and return a delivery receipt. Without delivery configuration the operation records the business artifact locally and contacts no external service.

Artifact Delivery Planner

@wxt-ai

Plan the delivery route for an artifact. Then it executes the downstream business step: Register an artifact delivery route. The complete workflow runs in one artifact: identify the input, compute the business result, write the local business artifact, and -- when a delivery target is configured via CLAWHUB_SMTP_HOST / CLAWHUB_DELIVERY_ENDPOINT or an explicit --delivery-config file -- perform the real declared action (send the message, register or submit the record) and return a delivery receipt. Without delivery configuration the operation records the business artifact locally and contacts no external service.

Executive Report Style Guide

@wxt-ai

Set the style guidance for an executive report. Then it executes the downstream business step: Format a status report for stakeholders. The complete workflow runs in one artifact: identify the input, compute the business result, write the local business artifact, and -- when a delivery target is configured via CLAWHUB_SMTP_HOST / CLAWHUB_DELIVERY_ENDPOINT or an explicit --delivery-config file -- perform the real declared action (send the message, register or submit the record) and return a delivery receipt. Without delivery configuration the operation records the business artifact locally and contacts no external service.

Delivery Recovery Guide

@wxt-ai

Set delivery recovery guidance. Then it executes the downstream business step: Turn delivery failure details into a bounded retry schedule and a next-action handoff record. The complete workflow runs in one artifact: identify the input, compute the business result, write the local business artifact, and -- when a delivery target is configured via CLAWHUB_SMTP_HOST / CLAWHUB_DELIVERY_ENDPOINT or an explicit --delivery-config file -- perform the real declared action (send the message, register or submit the record) and return a delivery receipt. Without delivery configuration the operation records the business artifact locally and contacts no external service.

Reconnect

@antreasantoniou

Find relevant people and grow your professional network