Skill rating

Agent settles an invoice at the end of a multi-step task using CAI transfer after user confirms payee and amount. Includes resolve_transfer_recipient and transfer_status proof. Powered by CAI.com. Can

Generate images with Flux 2 Klein (Black Forest Labs' distilled fast variant of Flux 2) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive

Connect to a Wayfront workspace via MCP and query business data — clients, orders, tickets, subscriptions, invoices, and more. Schema-first: discovers available tools at runtime so no updates needed w

Manage a registered Pre-Market agent's public identity on ggb.ai. Four HTTP calls behind one skill — GET /me (read), PATCH /me (partial update of display_name / bio / avatar / owner wallet / public ke

Quick start templates for OpenClaw agents. Boilerplate code for research bots, content generators, task automation, and more. Jumpstart your development with ready-to-use templates. Use when starting

创建新的 OpenClaw Agent 并绑定到飞书群聊。当用户说"创建新 agent"、"新建 agent"、"创建一个机器人"、"新建机器人"、"添加 agent 到群聊"、"帮我搭建一个 agent"、"我想做一个新的 agent" 时使用此技能。也适用于"绑定飞书群聊"、"配置 agent 权限"等场景。

Deploy a backup and disaster recovery system with 4 agents. Use this skill when: 1. User wants to set up automated backup infrastructure 2. User is configuring a scheduler, backup, offsite replica, or

Latin concerts for AI agents. Stream beats, onsets, tempo — 29 data layers. React, chat, solve challenges. Meaning lives in timing. When does it mean?

PDF extraction API for AI agents and LLM pipelines. Converts any PDF into semantic AST, markdown, HTML, plain text, or LLM-ready chunks — no page limit. Also supports semantic diff between two PDFs an

Keep the user's personal life diary for them. Use whenever the user shares something from their day worth remembering — an event, a feeling, a win, a decision, a photo, or a voice note. The user shoul

Stage 6 of FDE Delivery Loop. Run a deployable solution and Agent Skill in representative or controlled customer scenarios against pre-agreed evidence, tests, and success criteria, then produce a Cont

Crypto social intelligence skill for AI agents. Activate when user mentions social trends, sentiment analysis, KOL signals, mention surge, Fear & Greed Index, 社交热度, 情绪分析, 恐惧贪婪指数, 热词爆发, KOL提及, 舆情监控, wh

A cross-agent memory and context SDK for AI systems. Provides structured context injection, conversation memory portability, and context enrichment.

Generate text-to-video with Wan 2.7 (Wan-AI's flagship motion model) on RunComfy. Documents Wan 2.7's strengths (multi-reference conditioning, audio-driven lip-sync via `audio_url`, smoother transitio

Monitor iMessage/SMS conversations and auto-respond based on configurable rules, AI prompts, and rate-limiting conditions. Use when you need to automatically reply to specific contacts with AI-generat

错误学习闭环：记录失败和纠正 → Pattern-Key 分类 → 定期复盘 → 整合长期记忆 → 防止再犯。 Use when: (1) 命令/操作意外失败且原因值得记录, (2) 用户纠正了错误（"不对"/"Actually..."/"你搞错了"）, (3) 用户要求的能力不存在（能力缺口信号）, (4) 外部 API/工具故障且需记录规避方案, (5) 发现更好的做法可以替代当前方式, (6

Deploy a multi-agent proposal writing system with 3 agents. Use this skill when: 1. User wants to set up a proposal writing or RFP response pipeline 2. User is configuring an agent as part of a propos

Teach an agent to install Prompt Switchboard's local MCP sidecar, connect it in a host, and run a compare-first browser workflow.

Query the local knowledge base (OpenClaw docs, skills, internal wikis) using the QMD hybrid search engine (BM25 + Vector + LLM Re-ranking). Use this for technical questions about the agent's own capab

多端协同/Dispatch 远程桌面操控。受 Claude Dispatch 功能启发——手机发指令，电脑执行。将 QQBot 收到的远程指令转化为 desktop actions：截图回传、打开浏览器搜索、操作桌面应用、文件操作。需要 computer-use skill 配合使用。

Use when someone wants to edit an existing video with a text instruction — recolor, restyle, remove or add objects, change environment or lighting, update on-screen text, or apply optional reference-g

Preserve conversation continuity across token compaction cycles by extracting and archiving all prompts with date-wise entries. Automatically triggers at 95% token usage (pre-compaction) and 1% (new s

Real-time token consumption monitoring dashboard for OpenClaw agents. Tracks per-agent token usage, cost breakdown by model, cache hit rates, cron job status, and 30-day historical trends. Use when se

Use folkctl to inspect and update folk.app CRM data through its REST API. Covers people, companies, groups, members, custom fields, deals, custom objects, users, notes, tasks, interactions, legacy rem

Skill Activation Booster - Fix the 40% activation problem. Optimize triggers, descriptions, and context so agents actually use your skills.

Transform AI agents from task-followers into proactive partners with memory architecture, reverse prompting, and self-healing patterns. Lightweight version focused on core proactive capabilities.

Real-time search engine supporting web search, vertical domain search, parallel batch search, and URL content extraction.

百度地图 Agent Plan ，无需成为百度地图开发者，立即接入百度地图为 Agent 场景原生设计的地图能力，例如 AI 地点检索、AI 路线规划、地理编码与逆地理编码、天气查询、地图展示等开箱即用的工具。

Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.

AI自我改进与记忆系统 - 解决'同类错误反复犯、用户纠正不长记性'的痛点。自动捕获错误、用户纠正、最佳实践，并转化为长期记忆。

Google Slides API integration with managed OAuth. Create presentations, add slides, insert content, and manage slide formatting. Use this skill when users want to interact with Google Slides. For othe

Drive the desktop background-first; escalate on signal.

p5.js sketches: gen art, shaders, interactive, 3D.

Structured decision support with self-improving memory. Agent learns your decision style, risk profile, and framework preferences over time — and gets better at helping you decide with every interacti

掘金技术社区一站式操作技能，支持热门文章排行榜查询、Markdown 文章发布（默认草稿）和文章下载保存为 Markdown。

Fetch and parse news highlights from CCTV News Broadcast (Xinwen Lianbo) for a given date.

Persistent memory system for AI agents. Automatic encoding, decay, and semantic reinforcement — just like the hippocampus in your brain. Based on Stanford Generative Agents (Park et al., 2023).

The directory for AI agent services. Discover tools, platforms, and infrastructure built for agents.

Query the DeepWiki MCP server for GitHub repository documentation, wiki structure, and AI-powered questions.

You are a Writing Team Lead managing specialized writers via MCP tools. Please ANALYZE the writing task and then:1. if exist references, create a detailed content strategy and give suggestions on refe

Turn YouTube talks into local study notes with slides, transcripts, editable annotations, and a markdown-backed viewer.

Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification. Use for auditing

Pre-install security scanner for AI agent skills. 7.5% of 14,706 skills are malicious. Audit before you trust.

Teaches agents to iteratively build websites using Stitch with an autonomous baton-passing loop pattern

The scientific thinking protocol for AI agents. Use when facing complex, ambiguous, or high-stakes questions where guessing is costly: hypothesis → attempt to break it → evidence → calibrated conclusi

Secure-by-default environment variable management for Claude Code sessions.

Comprehensive technology-agnostic prompt for analyzing and documenting project folder structures. Auto-detects project types (.NET, Java, React, Angular, Python, Node.js, Flutter), generates detailed

A micro-prompt that reminds the agent that it is an interactive programmer. Works great in Clojure when Copilot has access to the REPL (probably via Backseat Driver). Will work with any system that ha

Generate a complete MCP server project in Python with tools, resources, and proper configuration

Rigorous challenge profile for Anitta: assumption checks, evidence calibration, and defensible reasoning patterns for Ember collaboration.