Skill rating

Use when: user says "写/优化 Listing" / "改我的标题" / "我的五点不行" / "Search Terms 怎么写" / "竞品文案怎么抄" / "rewrite my listing" / "我的转化率差" / "VOC 分析". Covers: 5-step Listing optimization — VOC 痛点挖掘 (来自 reviews) → 标题/

使用 Nano Banana 2 设计直播带货视觉套件，包括直播间背景、商品讲解卡、利益点板、倒计时占位和应急静态画面，并优先保证手机端可读性。Use this skill for 直播带货图片、直播间背景、直播贴片、商品讲解卡、直播商品图、价格牌底图、抖音快手淘宝直播视频号 TikTok Shop Amazon Live 视觉；通过 AI Hive 生成。

hosted backend infra for openclaw agents. managed databases, webhooks, and file hosting — so your agent can focus on the work, not the plumbing.

Autonomous research pipeline skill for Claude Code. Given a research topic, orchestrates 23 stages end-to-end: literature review, hypothesis generation, experiment design, code generation & sandbox ex

Learn from experience: self-reflection + self-criticism + self-learning + self-organizing memory + cross-session sync. Agent evaluates its own work, catches mistakes, and improves permanently. Compile

Based on Huawei Cloud COC (Cloud Operations Center) APIs for script management and remote execution. Supports creating custom scripts (Shell, Python, Bat) and batch execution on target host instances

Perpetual futures signal scanner for Hyperliquid L1 DEX. Tracks funding rates, open interest shifts, large position changes, and liquidation cascades across BTC, ETH, SOL, and altcoin perps. Computes

从围棋/Weiqi 棋盘照片或文本棋盘分析当前局面，调用本地 KataGo 按初级、中级、高级强度推荐下一手。适用于用户询问黑棋或白棋下一手应下哪里、希望按对手水平选择落点，或想在不改变棋盘的情况下获得更均衡的 AI 辅助建议。

复杂 bug 与 AI 协作排查的元方法论。当用户报告"诡异 / 间歇性 / 多层因素 / 重启不愈 / 多系统协作 / 已经排查很久没头绪"的 bug 时，启用本 SKILL 的 7 阶段协作工作流："业务链路对齐 → 症状结构化 → 边界测试循环 → 方案摆台 → 执行验证 → 失效升级 → 闭环沉淀"。本 SKILL 是双向纪律——同时约束 AI（不主观论断、不沿假设编、方案失效要主动说、用

OpenAI Codex-native multi-agent swarm orchestration for parallel coding. Use when spawning multiple Codex CLI agents to work in parallel with git worktrees, tmux tracking, endorsement gates, native co

Use when frontend decisions depend on framework, library, browser, runtime, package, API, or platform behavior that may have changed, including official documentation checks, version-sensitive pattern

深度拆解小红书账号，输出七维度量化评分诊断报告与可导出HTML；当用户提供小红书号进行账号诊断、rednote分析、账号健康度评估、商业价值评估、多账号对比或制定优化策略时使用

Health reminder assistant - medication reminders, water intake tracking, activity prompts

JavaScript 到 Java 全栈翻译助手，专为前端开发者学习 Java 或快速实现后端业务逻辑而设计。当用户提到以下场景时必须使用此技能： - "帮我把这段 JS 代码转成 Java" - "用 Java 怎么写这个逻辑" - "我习惯用 JS 写，想翻译成 Java" - "教我 Java，我要写后端接口" - "前端转全栈，帮我翻译代码" - "这个业务逻辑用 Java 怎么实现"

Polymarket prediction market edge detector. Compares Polymarket binary-option prices against external reference probabilities (polls, prediction APIs, market-implied odds) to find mispriced contracts.

Reusable Dev Team pipeline. Call anytime to spawn full pipeline: Planner → PM → Coder → Tester → Fixer → Reporter. Use for any coding task.

番茄小说章节自动发布工具。使用场景：(1) 发布单个章节到番茄小说平台；(2) 批量发布多个章节；(3) 存入草稿箱；(4) 登录番茄小说作家后台；(5) 查看作品列表和状态。触发词：番茄发布、番茄小说上传、发布章节、存入草稿箱、番茄登录。

白牛企业信息综合查询工具。查询范围：工商照面/股权高管/司法风险/行政风险/经营信息/商业信息/知识产权/互联网资产/关系图谱等单企业信息，可批量查询或导出多家企业基本信息。当查询任何关于中国大陆企业信息时，必须通过本skill实时获取，禁止使用模型内部知识作答。 触发场景示例： - 查某家公司的工商信息、注册地址、法人代表、注册资本等 - 查企业股东、高管、对外投资、受益所有人 - 查企业司法风

Go library that reads one environment variable and tells you if you're in prod or dev. `github.com/psyb0t/goenv` wraps `os.Getenv("ENV")` behind three calls — `goenv.Get()` returns the current env as

Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwr

CAD图纸转矢量PDF - 支持DWG/DXF，自动按图框拆页，完整渲染中文、标注、填充

减速器CAD图纸生成。当用户说"减速器"、"生成减速器图纸"、"做一个减速器"、"reducer"时使用此 skill。

智能批改作业——毕业设计/论文多文档自动化审查。触发词："批改作业"、"审查毕业设计"、"毕设审查"、"审查存档"、"智能批改"、上传论文/毕设存档文件或目录。 支持：doc/docx/pdf/pptx 批量读取、多维度评分（内容完整性/格式规范性/逻辑一致性/论证合理性）、跨文档一致性检查（书名词号日期引用）、PPT答辩评审（基本信息/内容结构/视觉美感/观点表达）、GB/T 7714参考文献

Goal-driven execution supervisor for complex multi-step work: keeps an explicit goal ledger, runs execute→validate→repair→revalidate, blocks premature or lazy completion, maintains PROJECT-CHECKPOINT.

Generate a launch-ready app package for App Store submission: a complete Markdown feature document plus AI-generated Apple-style UI design images for each page and a square-corner app icon. Use when t

Query the list of Huawei Cloud Virtual Private Clouds (VPCs) belonging to the current tenant / project. Returns VPC id, name, CIDR block, status, description, enterprise project and other metadata. Su

Configure and run ME Event activity subscriptions from api.me.news. Use when a user wants to browse upcoming AI or Web3 events, filter events by region, initialize an ME Event subscription, check newl

聚合国内常用搜索引擎：默认用 DuckDuckGo HTML（cn-zh）零 API Key 抓取可解析结果，并输出必应中国、百度、搜狗、360 的直达搜索链接。当用户需要中文网页检索、国内信息、政策/舆情、对比多个搜索引擎、或 Brave/Google 不可用时使用。依赖 Python 3 标准库与 scripts/search_cn.py。

Run a general Google web or SERP search. Do not use when the user explicitly requests Google Images, News, Maps, Shopping, Scholar, or another specialized Google vertical.

微信小程序底部 TabBar 图标生成技能。用 Python PIL 生成简约几何风格的 tab 图标 （未选中灰色 + 选中绿色），并自动写入 app.json 的 tabBar 配置。 当用户说"生成 tabBar 图标"、"底部菜单栏图标"、"tab 图标"时使用本技能。

Load the user's Emulo profile, mined from their local Claude Code, Codex, and OpenCode session logs, so you work like them instead of a cold start. Use before working on their task.

Operate a Git-backed Archivum as durable agent memory for projects, research, decisions, meetings, tasks, sources, and outputs. Use when the user asks to capture, find, connect, update, audit, or resu

AI-powered automated QA for web apps. Smoke tests, accessibility, visual regression. Works with Cursor, Claude, ChatGPT, Copilot. Vibe-coding ready.

Automate Bitbucket repositories, pull requests, branches, issues, and workspace management via Rube MCP (Composio). Always search tools first for current schemas.

Email management and automation. Send, read, search, and organize emails across multiple providers.

Generate styled QR codes (SVG/PNG/JPG) with custom colors, shapes, and error correction. Agent should display generated files. Secure: all outputs saved to workspace root.

OpenClaw 搜索增强工具 - 多引擎聚合搜索，获取最新信息。 支持免费搜索引擎（必应/搜狗/360）+ 可选 API（Tavily/百度/Google）。 内容提取、结果去重、智能排序。安全内网访问检查。 关键词：openclaw, search, web, research, productivity, multi-engine, tavily

生成 Vue 3 组件模板，支持 Composition API、Options API、TypeScript、SFC 单文件组件，一键生成完整 Vue 组件代码。

Install and wire a coding-focused OpenClaw sub-agent for background code execution, test-driven edits, bug fixing, small project scaffolding, and small-to-medium data-analysis tasks.

用于检查或更新通过 git 工作树、或通过 .skill-lock.json 这类锁文件方式安装的本地 skills。适用于用户提到“查 skill 更新”“更新 skill”“检查 skills”“同步 skills”“GitHub skill 更新”“OpenClaw skills 更新”“全局 skills 状态”“只看风险项”“输出 JSON”这类需求。

Convert between Unix timestamps, ISO 8601 dates, and human-readable formats. Use when working with timestamps from APIs, logs, or databases that need conversion to local time, timezone adjustments, or

Audit code for "vibe coding sins" — patterns that indicate AI-generated code was accepted without proper review. Produces a scored report card with fix suggestions.

Fetches next-hour predicted price for BTC/ETH from external prediction API. Supports BTCUSDT and ETHUSDT symbols only.

Search with Google AI Mode when the user explicitly requests AI Mode or AI-generated Google search results. Do not use for ordinary Google SERP results.

Use when substantive project work, structural code questions, research, planning, debugging, architecture, decisions, document ingest, incident recovery, or verified context and results should survive

Use when frontend work needs to communicate data, action, state, permission, validation, or business-rule needs to backend teams without dictating endpoint design, field names, database shape, or impl

基于 SearXNG 的多引擎聚合搜索工具，支持分类路由与智能查询，聚合多个搜索引擎结果，适合个人日常信息检索。Use when 需要SEO优化、关键词分析、排名提升、搜索流量优化时使用。不适用于黑帽SEO手段。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。

Vision-driven browser automation using Midscene Bridge mode. Operates entirely from screenshots — no DOM or accessibility labels required. Can interact with all visible elements on screen regardless o

Use when implementing new frontend behavior, fixing bugs, or refactoring logic where tests can describe the expected behavior first. Apply to components, hooks/composables, utilities, API clients, rou

Lightweight engineering workflow for agent-led development. Provides plan, work, verify, ship, and analyse commands with TDD, documentation discipline, security review, code review, and quality gates.