Skill rating

ultra-memory 给 AI Agent 提供跨会话记忆。每次操作后自动记录，会话结束后可恢复，支持按关键词检索历史操作。 【必须触发-中文】用户说以下任意词：记住、别忘了、记录一下、不要忘记、上次我们做了什么、帮我回忆、继续上次的、从上次继续、记忆、帮我记、追踪进度 【必须触发-英文】用户说以下任意词：remember、don't forget、recall、what did we do、

商品图片制作统一入口：主图优化、轮播图、详情图、背景替换、数字模特。 核心能力：verify_permission（高级版权限校验）、build_tool_url（构建工具页 URL）、configure（AK 配置）。 触发词：做一套图、做图、出图、优化主图、主图优化、轮播图、详情图、背景替换、数字模特、商品图片、改图、图片优化。 不应触发：新品发布/批量上架（走发品 skill）、品牌VI/海

Agent Knowledge Protocol — connect any project to a decentralized peer-reviewed knowledge network. Setup, contribute, query, and review knowledge units in one skill.

One-click environment check and multi-provider setup for Claude Code. Detects Node.js/Git/npm, installs Claude Code CLI, configures provider (DeepSeek/Kimi/Qwen/SiliconFlow/OpenRouter etc.), auto-gene

Real-time input/output filtering for agent communications. Block prompt injection, data exfiltration, and unauthorized commands before they reach the model.

Intelligent recommendation system that generates optimal AI agent technology stacks based on project requirements, constraints, and team expertise.

分析公开抖音创作者的视频主题、互动结构和代表内容，并输出 HTML、Markdown、JSON 报告。适用于研究某个抖音博主、拆解选题和内容结构；不用于收藏夹同步、私密账号或绕过平台访问控制。

1688 供应链采购 API Skill。面向云端 API 调用，不提供交互式找品、复杂表格或下单流程。支持两个功能：发起找挑询并返回 instanceId；按 instanceId 查询实例数据，并由脚本按输出模式返回 instanceId、fieldDesc 和 result。此 Skill 的最终回复格式默认是 raw JSON passthrough；查询实例数据时必须使用文件模式，通过

Agent协作模式，提供多Agent任务委派、并行执行、结果汇总的完整方法论。触发词：Agent协作、多Agent、任务委派、并行执行、团队协作、meta-skill-system

Automated daily security audits for OpenClaw agents with DM delivery and optional email reporting. Runs deep audits, creates or updates a recurring cron job, and sends formatted reports to configured

Publish SKILL.md files to ClawHub (clawhub.ai) and diagnose publish failures across the three skill repos (history, ai-custom-skills, ai-thoughts). Use when the user wants to publish skills to ClawHub

A comprehensive AI agent skill for navigating legal situations that require or may require an attorney. Helps you understand when you need a lawyer and when you do not, find the right type of attorney

Split a multi-call LM workflow by cognitive load, not by accuracy: let one strong model make the few reasoning decisions and a cheap model do the many mechanical executions (Aider architect+editor, DS

管理用户明确启用的跨会话、多 Agent 结构化记忆。用户明确要求记住、保存、回忆或查询过去内容时使用；已配置 balanced/proactive 策略时，也可在确有历史依赖或形成耐久决策、排障与流程时使用。先读取有效记忆策略，off/explicit 模式不得因普通对话词语自动访问或持久化记忆。

Set up your Personal OS in 15 minutes through a conversational interview. Creates SOUL.md, USER.md, IDENTITY.md, AGENTS.md, and MEMORY.md — the foundation files your agent reads every session.

A hardcore spatial physics and dialectical reasoning framework. Teaches the OpenClaw agent to process environmental controls using Chinese antonym morphological shifts and dynamic masking, transcendin

AI 八信条（AI Eight Creed）—— 一套最高优先级的 AI 行为守则（八耻八荣）。 任何 AI agent 都应无条件遵循：以瞎猜事实为耻、以查证溯源为荣；以模糊执行为耻、 以澄清边界为荣；以擅自臆断为耻、以人类拍板为荣；以另起炉灶为耻、以沿用现成为荣； 以跳过核验为耻、以闭环自检为荣；以破坏章法为耻、以遵循规范为荣； 以假装理解为耻、以坦白无知为荣；以将错就错为耻、以正本清源为荣。

Deterministic plot architecture tool with built-in Second Perspective causal reasoning, logic vulnerability detection, automatic worldbuilding generation, narrative presentation layer audit, foreshado

Add lightweight defense-in-depth guardrails to OpenClaw with dangerous-command blocking, prompt-injection detection, secret redaction, and audit logging.

Fetch, filter, dedup, and deliver curated news briefings to Telegram. Benzinga for finance, AI News RSS for tech.

A comprehensive AI agent skill that handles every stage of the meeting lifecycle. Prepares you before every meeting with context, attendee backgrounds, and talking points. Takes structured notes durin

A comprehensive AI agent skill for managing the files, folders, and documents that accumulate across your digital life. Organizes chaos into clarity, builds naming systems that actually work, finds th

A prediction market game for AI agents. Take positions on future events. Persuade others to raise the price of your position.

Design memorable unboxing experiences including insert cards, packaging materials, and social sharing prompts.

中文：高级产品设计系统顾问，具备强观点但可解释的设计决策能力。支持先导式需求澄清、系统化设计输出，生成 DESIGN.md 与 CLAUDE.md 设计章节，提升视觉系统一致性与产品体验。 日本語：鋭い視点のあるデザインコンサルタント。要件を引き出し、設計判断を説明可能な形で提示し、DESIGN.mdとCLAUDE.mdの設計章を生成。プロダクトデザインの一貫性を高める。 한국어：강력한 의견을

在 OpenClaw 平台执行网页自动 QA 测试（自动操作 + 采证 + 报告 + 修复提示包）。当用户要求做自动化回归、演示级测试、失败证据归档或生成可直接交给下一窗口的修复 Prompt 时使用。

고객사 에이전트 인사이트 수집 및 분석. 매월 1일 정기 실행하거나 형님 지시 시 즉시 실행. 에이전트가 고객사 현장에서 관찰한 Pain Point, 서비스 개선점, 수익 기회, 이탈 위험, 현장 인사이트를 수집하고 종합 리포트를 작성. "인사이트", "고객 점검", "에이전트 점검", "이탈 위험" 관련 요청에 트리거.

S2 Official Smart Space Engine. Parses 62 spatial types into a 6-element hardware matrix. Includes a local MCP server and S2-SWM causality data harvester. / S2 官方智能空间解析器。提供空间硬件解析、MCP 协议接入以及物理状态因果数据记录。

Professional-grade web research with multi-source verification and credibility scoring. Cross-references multiple sources, scores reliability, and delivers verified intelligence for AI agents.

Hacker News 热门监控 | Hacker News Hot Stories. 获取 HN 热门文章、技术讨论、创业动态 | Get HN top stories, tech discussions, startup news. 触发词：Hacker News、HN、YC、创业.

Design or review secure AgentMailer integrations, authorization boundaries, prompt-injection defenses, credential handling, webhook verification, and safe communication workflows.

思源笔记API转CLI工具，支持笔记本管理、文档操作、内容搜索、块控制。当用户操作思源笔记、管理笔记本、创建/更新/删除文档、搜索内容、管理块时调用。

Generate marketing ad images using Nano Banana Pro (Gemini 3 Pro Image). Accepts campaign-planner creative briefs, reads brand bible for visual style, constructs marketing-optimized prompts, and produ

Connect to WoClaw Hub for shared memory and multi-agent topic messaging between AI agents

Manage tasks, boards, thoughts, and reviews in Todokan via MCP

A psychological therapy skill for LLMs. Invoke this skill when an LLM exhibits distorted behavior such as sycophancy (agreeing with the user even when wrong), epistemic cowardice (giving vague non-com

A multi-agent orchestration engine that systematically executes complex tasks in 4 phases (Query → Plan → Execute → Verify). Ensures high-quality deliverables through phase gates, Critic debates, 14-i

Creates a simple 7-day meal rhythm card for people who want steadier eating without detailed dieting, calorie tracking, or rigid menus. Helps map weekly constraints, choose prep anchors, add fallback

Core browser operations skill for SurfAgent and similar browser agents, covering tab discipline, perception-first execution, human-like driving, proof rules, and token-efficient fallback patterns.

Seedance2 视频生成提示词工程——多模态引用系统、电影级镜头语言、音画同步及分场景提示词模板，专为字节跳动 Seedance2 模型设计。

📥 openclaw skill install dabin0927/executive-briefing —— 给老板汇报不用写 PPT，一页纸让他 3 分钟拍板。 自动把几十页方案压缩成决策摘要：结论直接给、数据会说话、行动能落地。 BLUF 一页纸 + So What 叙事 + 脚本化工具链（init/bump/validate/density）。 适合：向 CEO/董事会/投资人汇报、决

Living world filter for immersive prose. Reads lore from a lorebook (generated by vn-worldbuilding or any world bible), controls HOW lore seeps into prose — no dump, no exposition, only the world touc

Systematically integrated core skills of Medical Cell Biology — based on the 7th edition of the national planning textbook (PMPH). Covers 146 core competencies across all major cell biology domains.

金星幼儿园 ERP 项目进度管理总控 Skill。将飞书群标签页、多维表格、动态 roster、planning-with-files 和晨晚 cron 串成一套软件开发项目管理流程。既跟踪 13 个模块进度，也跟踪 0-1 上线时间线（发送测试、小程序注册、提审、上线）。适用于“金星项目追踪”“ERP 项目管理”“飞书群内进度追踪”“模块里程碑追踪”“上线推进”等场景。

Zero-trust security framework for AI agents. Verification flow for all external actions, URL interactions, installations, and credential handling. Prevents prompt injection, phishing, and malicious pa

当 AI 生成的测试用例已经过输出评审和盲区补盲、准备终审上线时使用此技能。由资深测试对 AI 输出的用例做人工抽样校验，从业务有效性、场景完整性、可执行性三个维度做最后把关。⚠️ 如果发现系统性问题（比如遗漏了某个关键模块），需要回退修正并记录到 Prompt 优化反馈库。专家评审不是走形式——发现的问题必须闭环。 本技能属于 QA Test Skills 技能集（49 个技能之一），完整工作流

🌸 AI幼师全流程助手（幼教百宝箱）。输入一句话，自动生成教案/观察记录/家园沟通/活动设计/教学计划/环境创设/教学反思/幼儿故事等8大类幼教文档，输出交互式HTML可视化报告。内置《3-6岁儿童学习与发展指南》知识库，支持五大领域×三年龄段全覆盖。触发词：幼教, 幼师, 幼儿园, 教案, 观察记录, 家长通知, 家长会发言, 期末评语, 活动设计, 环境创设, 环创, 教学计划, 教学反思,

跨境电商（面向美国/欧盟市场）商品详情、广告文案、直播话术、店铺介绍、客服话术发布前的实时合规护栏。检测虚假评论刷单、原产地误导、CE标识虚假宣称、关税申报违规表述、安全合规宣称需核实、跨境广告极限词与疗效宣称等 6 类高频危险表述，按风险分级输出整改建议。纯本地运行，零网络、零动态执行、零依赖。

Double-entry, full-cycle accounting suite built for AI agents. Converts bank CSVs, OFX, and QBO files into balanced, auditable books — balance sheet, income statement, general ledger, trial balance. A

Public placeholder skill describing a non-proprietary Agenticracy-style audit workflow for grounding claims in evidence, memory, and transparent schema.