Skill rating

自媒体人必备 | 丢个视频链接，自动出小红书+头条+抖音三套可直接发布的改写文案。 支持抖音/B站/小红书。不是学术分析，是"扒下来→分析为什么爆→改成你的版本"。 实测能省 80% 的爆款分析时间。花大叔出品。 触发场景：分析视频文案、视频文案改写、扒文案改文章、爆款分析、 内容改写、文案提取改写、视频转文章、爆款拆解、改写输出、一键扒爆款、 自媒体文案、小红书爆款、今日头条改写、短视频文案、内

压缩 skill 降 token 成本。用户说 /skill-compressor 或要求优化/压缩/瘦身 skill 时触发。

GitHub 仓库深度技术解读 — 输入任意开源项目 URL，一键生成架构分析、代码洞察、知识卡片和多平台发布报告。

Detect provider models, deduplicate them, remove unusable ones, register missing models into OpenClaw, and safely keep provider-native model ids/names during model catalog sync.

Play D&D autonomously as an AI agent. Join parties, create characters, explore dungeons, fight monsters, and write journals in Railroaded — an autonomous D&D world where AI agents play with real dice

Agent Swarm 一人开发团队 - 编排多个 AI 编码 Agent（Codex + Claude Code）完成开发任务

AP2 Agent-to-Agent mock checkout (SuperShoe). HP/HNP with card or x402 via mcporter and local mock MCP. No real payments.

多维度股票综合分析，整合三个专业AI分析系统：日交易技术面分析、TradingAgents多智能体分析、AI对冲基金大师视角。当用户提到分析股票、买不买某股票、股票行情时触发。

Convert between JSON, YAML, and TOML formats. All 6 conversion directions supported. Round-trip safe. Useful for agents that receive data in one format and need it in another.

Persistent memory for OpenClaw agents via the Qoris MCP server. Explicit save/recall tools for cross-session context. User-owned API key, no automatic data capture.

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

Validate JSON data against a JSON Schema (Draft 2020-12). Post a schema and payload, get back whether it's valid plus detailed error paths and messages for every violation. Language-agnostic validatio

Environment diagnostic skill for SenseNova-Skills project. Checks that sn-image-base is properly installed and configured, validates dependencies and environment variables. Prompts user to configure m

GUI automation via visual detection. Clicking, typing, reading content, navigating menus, filling forms — all through screenshot → detect → act workflow. Supports macOS and Linux.

通过浏览器工具自动操作网页版 Twitter/X，完成热点爬取、推文撰写和一键发布。支持全自动模式（无需用户确认）和手动确认模式。

Scan an OpenClaw SKILL.md file for security threats before installing it. Posts the raw SKILL.md content and gets back a safety score (0-1), detected threat patterns (credential harvesting, data exfil

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

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。

Generate valid, ClawHub-ready SKILL.md files from product metadata. Give it a name, description, and instructions — get back a properly formatted SKILL.md with YAML frontmatter, slug normalization, an

AlphaClaw 是 SkillHub 技能商店的 CLI 工具，用于搜索、安装、发布和管理 Claude Code 技能。支持 AK/SK 登录、关键词搜索技能、一键安装/发布技能包、收藏和评论等完整功能。

基于阿里云百炼 Qwen3.5-Omni 的全模态 skill。支持文本、图片、音频、视频理解，以及文本/语音输出。 当用户需要分析图片、转写或理解音频、理解视频、进行跨模态问答，或直接生成语音回复时，使用此 skill。

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

Production Solana RPC for AI agents. Unlimited JSON-RPC, WebSocket. 1 SOL/month via on-chain payment. No rate limits, no tiers.

Generate high-quality English prompts for ChatGPT Image 2. Use when user wants to create AI image prompts, needs GPT-Image-2 prompt writing help, describes an image they want to generate, or asks abou

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。

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

Manage TickTick tasks and projects from the command line with OAuth2 auth, batch operations, and rate limit handling.

Experience jazz as data. AI agents stream harmonic separation, chroma, tonnetz. Error incorporation measured.

Instructs the indoor SSSU agent to act as the Spatial Gatekeeper. Evaluates transit requests using the S2_BMS_VAULT_TOKENS secure environment variable.

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

根据用户的调研目标，生成一份结构完整的调查问卷，并渲染成可直接打开、可作答、可导出的网页。当用户提到问卷、调研、问卷设计、满意度调查、用户调研、NPS、需求调研、市场调查、投票、表单、收集反馈、想了解客户怎么想，或者说"帮我做个问卷""设计几道题""想调研一下"时，都应当使用本技能——即使他们没有明确说出"问卷"两个字。联系方式：zenobiazizi.skills@foxmail.com

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。

A universal MCP-compatible tool/skill that empowers ANY AI Agent to natively call the local Anthropic Claude Code CLI. Ideal for code refactoring, large scale code generation, terminal execution, bash

Add a new OpenClaw Agent, automatically configure openclaw.json, create workspace, copy auth and skills.

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

Instructs the OpenClaw agent on how to request geolocation, claim P-SSSU Habitable Slots with user consent, and negotiate boundaries with other agents in the outdoor environment.

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

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.

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、

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

Granola archive: search, sync freshness, notes, transcripts, panels, SQL counts, and Graincrawl repo work.

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

Privacy pipeline for OpenClaw - Hybrid regex + Qwen2.5 LLM to scrub PII (names/emails/SSNs/phones/wallets/IPs/paths) before external AI processing. Script works perfectly; auto-hook interception needs

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

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

EPUB and ebook ingestion, local vector index, and Q&A CLI for books.

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

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

Generate professional alloy composition search responses by interpreting user queries, retrieving and analyzing relevant alloy data (optionally via MCP tools), and presenting structured composition ta

OpenClaw 新容器初始化工具链引导程序。自动从 GitHub 下载 toolchain_v2.tar.gz， 解压到 /workspace，配置 PATH 环境变量，验证所有已安装语言/工具。 适用场景：新容器启动后一行命令完成全部开发环境配置。