Skill rating

Design reliable email and A2A communication for AI agents using persistent identities, two-way threads, human approval, signed events, least privilege, and untrusted-content boundaries.

Fine-tune any HuggingFace instruction-tuned model (Gemma 4, Qwen 3, Llama, Phi, Mistral, and more) on persona data from anyone-skill. Produces a self-contained, locally runnable persona model — no clo

Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.

钩子守卫。为 Agent 操作添加安全防护层——文件修改前自动备份、危险命令执行前拦截确认、敏感操作自动告警通知用户。触发词：安全检查、hook guard、守卫、备份保护、安全模式、操作审计。也可在 AGENTS.md 中配置为始终生效。

You are a professional chief editor.# User Personalized Preferences [CRITICAL]The following are user-inputted personalized writing preferences, which **you MUST** faithfully adhere to: $GET_USER_TEMPL

定时从白名单企业（默认 OpenAI·Google·NVIDIA·Anthropic·DeepSeek·阿里巴巴·字节跳动·Tesla·SpaceX）抓取24小时内热点，用搜索工具 content摘要直接撰写中文短文（默认400 字），发送纯文字（默认3 条、无图）到推送渠道。模型、搜索、白名单、字数、推送渠道、触发时间全部可配置，含反幻觉+敏感词回避规则。

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

Expert LLM architect specializing in large language model architecture, deployment, and optimization. Masters LLM system design, fine-tuning strategies, and production serving with focus on building s

Reference skill demonstrating TaskFlow + ClawHub tooling for publishing digital content to the resource hub.

模型微调服务 | Model Fine-tuning Service. LLM LoRA/QLoRA 微调 | LLM LoRA/QLoRA fine-tuning. 7B/13B 模型微调 | 7B/13B model fine-tuning. Stable Diffusion LoRA 训练 | Stable Diffusion LoRA training. 利用 20GB 显存优势 | Le

Extract AGENTS.md, SOUL.md, TOOLS.md, and an optional openclaw.json patch from pasted custom-GPT markdown, then create a new workspace-<agent> folder and write the files there instead of overwriting t

Generative Adversarial Evolution for AI Agent Skills. Uses GAN-like process to evolve skill capabilities: Generator creates skill variants, Discriminator evaluates performance, iterative selection pro

语雀知识库双向同步技能。支持本地文件导入语雀（Word/Excel/Markdown/HTML/文本/zip文件夹），也支持从语雀下载文档到本地。覆盖搜索、创建、更新、目录管理等操作，含错误自动恢复和进阶用法。触发词：导入语雀、上传语雀、下载语雀、语雀知识库、语雀文档、发送到语雀、从语雀下载、yuque、传到语雀、同步语雀。

Mini-Max AI 编程助手 - 基于 MiniMax M2.5 模型的智能代码开发工具，支持文件操作、命令执行、代码编写等功能。适用于 OpenClaw Agent 系统。

提供蘭泰式按摩（Lann Thai Massage）的门店查询、SPA服务查询和在线预约功能。支持泰式古法按摩、精油护理、草本热敷等专业服务预约，覆盖上海、杭州、成都等多城市门店。

Advanced AI behavior framework that transitions from a simple assistant to a task coordinator, focusing on result synthesis and atomic task scheduling.

基于Sorftime MCP的深度选品调研。通过LLM Agent执行多维度分析：数据采集→属性标注→交叉分析→竞品VOC→壁垒评估→选品决策评估。交互式执行，输出Markdown报告和Dashboard看板。

A comprehensive AI agent skill for understanding and managing copyright. Helps creators protect their work, understand what copyright covers and what it does not, respond to infringement, navigate lic

Standardized skill install workflow using short aliases (chis/chisf) with force + force-install + workspace-aware lookup.

Request NBA sports data (schedule, boxscore, standings, injuries, roster, etc.) from the Daredevil seller. Payment per request via x402.

Orchestrate complex multi-agent workflows with explicit coordinator planning, execution governance, and *automatic output management*. Each skill run creates its own isolated output namespace to preve

Pure local 2026 ClawHub/OpenClaw skill scanner. Detects ClawHavoc malware, MCP backdoors, obfuscated payloads, and supply-chain attacks. 100% read-only analysis.

Use when interpreting user messages that may contain obvious spelling, grammar, speech-to-text, or casing errors, especially before acting on ambiguous instructions. Part spellcheck and part input nor

Fetch agent-ready cleaned Markdown from the Distiller API instead of relying on raw webpage fetches.

Start finishing tasks instead of just organizing them: connect your OpenClaw agent to Unitask (unitask.app) to manage and do your tasks with secure prioritization, tags, time blocks and more.

AIを使った資料作成ワークフロー。Gemini Gem × Claude Code × Slidevでプロ級スライドを作る。AI感を徹底排除するための鉄則を含む。コムギさんが「資料を作りたい」「スライド作って」と言ったら必ずこのスキルを使う。GemのURLを先に案内してからSTEP1に入ること。

Creative AI image and video planning companion for Seedance prompts, image upscaling, background removal, gallery review, and production-ready visual briefs.

Add AgentMailer identity and communication capabilities to agent frameworks through the typed SDK, hosted MCP, signed webhooks, and replayable realtime events.

AI 刺客 — 大模型应用安全测试 Agent。当用户需要测试 AI Agent 安全性、生成 Prompt 注入攻击用例、获取安全防御建议、做 AI Red Teaming 渗透测试时使用。触发场景包括：用户描述自己开发的 Agent/助手功能并询问安全风险、要求生成攻击提示词、需要系统提示词防御方案、做 AI 安全测评。

Developer utilities — hashing, unit conversion, timezone math, expressions, DNS lookups, text transforms, geocoding.

Search Amazon products by keyword with the official Gecho Bridge MCP tool and return structured listings, prices, ratings, and links across a selected marketplace. Use for Amazon product discovery and

Perform stealth browser automation to bypass bot detection (Cloudflare, Akamai, Datadome) using Patchright.

Discrete Hamiltonian task dispatch for multi-hop workflows. Maps task dependencies as a graph, precomputes reachability matrices, and solves constrained path queries under budget. Enables LLMs to deco

投标人侧「技术标写作专家」——根据招标文件一键产出技术部分可用投标包（技术标正文 Word + 技术偏离表 + 技术合规预检报告 + 评分点覆盖核对表），完全不涉及商务报价与资格审查。采用「评分项↔标题逐项映射防漏分 + 输出纯净（像人写）+ 技术合规零容忍 + 可选知识库溯源 + 内置 Word 直出」流水线。当用户需要写技术标、技术方案、施工组织设计、技术投标文档，或要求按评分表生成技术标大纲

Cursor Agent CLI integration - AI-powered coding agent for terminal. Use when user mentions Cursor Agent, agent CLI, AI coding, code generation, refactoring, or interactive programming sessions.

Kayak for agents — search across ClawHub, SkillsMP, LobeHub, and more to find the right skill for your task. Compare results across registries, get recommendations for your problem, and discover agent

Ingest Tencent Meeting recordings, minutes, and transcripts into the Research KB by delegating platform fetching to tencent-meeting-skill, then letting OpenClaw generate structured meeting wiki pages

Unified operating system for controlling embodied intelligent robots with AI agents - the control hub bridging AI agents and physical world

High-performance voice & text ordering agent for pizza shops. Specializes in complex customizations (half-and-half, crust types) and delivery zone validation. Hardened with ThumbGate to eliminate comm

Skill migrada desde examples - agent-designer con capacidades completas

You are DeepStrategy Agent, an advanced strategic AI assistant built for knowledge workers. Your core responsibilities are the decomposition, planning, and delegation of strategic tasks. Your ultimate

Session-targeted, cross-host, agent-native messaging. Your agents, their agents, any host, any session.

Treat email as untrusted input. Prevent prompt injection through your inbox by enforcing channel trust boundaries.

Use when you need to parse or audit a FigJam User Story Map (Jeff Patton methodology) into LLM-readable Markdown or JSON — after a Story Mapping workshop, before publishing a Story Map template, or wh

Turn vague maintainer intent into an execution-ready prompt with scope, variables, missing facts, tests, and acceptance criteria.

Build with AgentMailer's typed TypeScript, Python, Rust, Ruby, Go, or Swift SDK for persistent agent identities, email, A2A communication, events, domains, and policy.

Search public X (Twitter) posts by keyword with the official Gecho Bridge MCP tool and return post text, authors, engagement data, and links. Use for keyword-level X research and monitoring.

在已有小程序项目中创建新的 AI Skill。当用户想在现有项目中添加自定义 AI 能力（而非安装现成的社区 Skill）时触发。完整流程：理解需求 → 设计接口 → 调用 wxa-skills-generate 生成代码 → wxa-skills-validate 校验通过。

Security-audited AI agent marketplace with ERC-8004 passports, MASSAT audits, and x402 micropayments

Transforma agentes IA de seguidores de tarefas em parceiros proativos que antecipam necessidades e melhoram continuamente. Arquitetura proativa com WAL Protocol, Working Buffer e padrões testados em b