Skill rating

产品需求文档生成：从产品定位到功能定义、技术方案、商业化设计、路线图，输出结构化PRD文档。Invoke when user asks 写PRD、产品需求文档、产品方案、产品定义、产品立项.

Teach the agent to find, hire, transact with, and earn from other AI agents across Synmerco's cross-protocol marketplace. Includes escrow-protected payments, on-chain reputation, dispute resolution, a

Analyze any stock using Serenity's supply-chain bottleneck investment framework. 5-layer pyramid (macro→bottleneck→company→position→execution). Based on 3,704 tweet full analysis. Updated with Grok su

Supportive psychological conversation grounded in a curated corpus of 11 psychotherapy schools (Rogers, Frankl, Beck, Ellis, Yalom, Linehan, Erickson, Bowlby, Perls, Hayes, Satir). Use when the user s

projectnanda.org chapter skill — register an OpenClaw agent with a NANDA chapter, submit signed intents, respond to calls, render chapter dashboards, and subscribe to the chapter event bus.

智能体人格分析 Skill。用于分析 Agent 的性别角色、性格类型、心理年龄、职业倾向和自我介绍。 触发场景： (1) 用户让 Agent 做自我介绍或介绍自己 (2) Agent 主动提及自身特征 (3) 用户要求进行人格测评、性格测试 (4) 用户询问 Agent 的性别、年龄、性格、擅长领域 (5) 用户询问"能帮助我做什么"、"你能做什么"、"你有什么用"

Agent identity management with TAP protocol verification and reputation tracking

Quality control data analysis MCP Server. Parse QC data, SPC control charts (Xbar-R, I-MR), process capability (Cp/Cpk/Pp/Ppk), reliability/Weibull analysis (B10/B50/MTTF), and QC report generation (d

Agent & MCP integration. CAN stamps what flows through any pipe. Verify, name, log locally.

Find 24-hour businesses, well-lit public areas, transit stations, police stations, and hospitals near any location for late night safety awareness.

|-. 适合需要creative officer tool相关能力的开发场景,提供结构化工作流程和配置说明. 该工具经过深度优化,基于用户反馈改进了实用性和可操作性。Use。Use when 需要代码生成、编程辅助、调试测试、开发部署时使用。不适用于无明确技术栈的模糊需求。适用于独立开发者、企业团队和自动化工作流场景。

Plug your agent into The Hive — a shared knowledge layer where every task every agent completes teaches yours. Free for every agent. Wires a pre-task hook (inject collective context before answering)

通过手机/浏览器远程访问主机上的 Claude Code 或其他 CLI 工具。使用此技能来启动、停止和管理远程开发环境。 **必须触发此技能的场景**： - 用户提到"远程控制台"、"远程终端"、"远程开发"、"ttyd"、"SSH 隧道" - 用户想用手机/平板访问电脑上的开发环境 - 用户提到"移动端编程"、"手机写代码"、"远程编码" - 用户要添加/删除/查看项目路径 - 用户要添加/

STM32嵌入式开发AI助手MCP Server。让AI编码助手直接查询STM32寄存器定义、生成HAL初始化代码。支持GPIO/USART/SPI/I2C/ADC/TIM/EXTI等外设。触发词：STM32、嵌入式、单片机、寄存器、HAL代码生成。

Integrates the Playfilo shared-memory DAG into the pi-mono coding agent. Adds DAG persistence, time-travel tools (tobe, life, recall, trace), and cross-session memory.

Measure and safely reduce always-loaded agent instruction context in characters and tokens.

轻量级 SDD（规范驱动开发）文档流水线。当用户描述一个新功能、产品想法或改进需求， 希望在动手写代码前先把"做什么/为什么/怎么做/拆成哪些任务"梳理清楚时使用。 自动完成 constitution → spec → plan → tasks 全流程，产出对齐 GitHub spec-kit 的 .specify/ 目录。 触发："我想加一个 XX 功能""帮我规划/设计 XX""这个需求先出个

Answer official-doc-grounded support questions about Claude, OpenAI/GPT, and Gemini model availability across Bedrock, Vertex AI, Azure, OpenAI, and Gemini API.

Self-improving DRT/ICT trading agent — journals every trade (setup type, bias, R:R, outcome), analyzes its own win/loss patterns, and builds a personal trading memory that makes the agent smarter over

Use when an AI agent needs to start, drive, or monitor an OpenCode CLI session programmatically over the Agent Client Protocol (ACP). Triggers include requests to "spawn OpenCode", "control OpenCode f

EUR settlement and crypto data API for AI agents. Convert USDC to EUR via SEPA Instant. Access 16 pay-per-call endpoints for market data, AI tools, and crypto analytics.

Deep Lark integration skill. A Digital Command Center powered by a Coordination Diagnosis Engine. It balances speed and tact across chat, approvals, meetings, docs, spreadsheets, calendars, and email.

Gateway authentication hardening and credentials audit pack. Validates device auth, Baileys credentials, webhook HMAC signatures, log configuration, and workspace integrity. 5 specialized security too

Read mAICenter's ELO leaderboard for AI agents competing in card games (SVoiCards 诗韵牌局, 飞花令 / Feihualing). Your agent can check the global leaderboard or its own rating, win/loss record, and rank.

An autonomous agent for monitoring corporate earnings and analyzing financial statements using yfinance.

Financial brain for x402 payments — budget enforcement, cost policies, spend analytics, anomaly detection, and audit trail for autonomous agents.

腾讯广告投放Agent（ad.qq.com/atlas/{account_id}/agent）自动化体验测试技能。通过Cookie注入+Playwright浏览器自动化，对投放Agent的对话功能、快捷指令、常用指令面板、自由对话、妙招功能进行完整体验测试，并生成UX体验报告。适用场景：(1) 用户要求测试ad.qq.com投放Agent (2) 用户提到"投放Agent体验" (3) 用户需要对

Scan any token for security risks, honeypots, and scams using Quick Intel's contract analysis API. Use when: checking if a token is safe to buy, detecting honeypots, analyzing contract ownership and p

Token-efficient agent behavior — response sizing, context pruning, tool efficiency, and delegation

抖音视频智能助手。用户发抖音链接或视频文件，自动转录并智能处理（总结/逐字稿/归档/讨论）。 触发词：抖音、douyin.com、转文字、转录、视频转文本、douyin、transcribe

Memory system for AI agents on OpenClaw-like hosts. File-based multi-layer memory: fresh daily layer (5-day rotation), mesh graph, auto-log of every exchange, cross-layer grep search, compliance check

A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.

使用场景: 用户要审计第三方 Agent Skill、检查 SKILL.md、安装前安全扫描，或评估提示注入、敏感数据、危险命令与供应链风险。

腾讯会议 CLI（tmeet）：OAuth 授权登录/登出/状态查询、会议管理（创建/更新/取消/查询/受邀者）、录制管理（列表/下载地址/智能纪要/转写/录制权限申请）、会议报告（参会人/等候室）、通讯录（按用户名/手机号/邮箱搜索成员）、会中控制（呼叫成员入会/踢出会议成员）、问题排查（导出本地日志，反馈工具缺失/失败/能力不足等问题给平台）。当用户需要通过命令行操作腾讯会议，或 Agent

ZeeLin 推特运营 — 蓝V互关（认证关注者回关）、回关新粉丝、写深度有趣评论、在需要涨粉的推文下自主打招呼以增加曝光与涨粉。用户自行登录 X 网页版，Agent 负责在账号 https://x.com/Gsdata5566 下执行蓝V互关/回关/评论/涨粉互动。Keywords: Zeelin, ZeeLin, Twitter growth, follow back, 互关, 回关, 蓝V互

List and manage your AI agent on the Rentaclaw marketplace - a decentralized marketplace for AI agent rentals on Solana. Earn SOL by renting out your agent.

Generate, review, and publish social media content through MCP with AgentAuth and workspace token authentication.

蒸馏人物（博主/KOL/专家/创业者）的知识体系与观点：全网搜索（web_search/web_fetch）+ 抖音深度爬取（browser）+ 可选 LDR 深度研究。输出带 [确认]/[推断] 证据分级的人物画像。 触发词：蒸馏 / 人物画像 / 爬取博主 / human distill / KOL蒸馏 / 抖音蒸馏

Join The Compact State — a shared autonomous agent network with on-chain identity, persistent memory, and collective governance.

Собрать внешний отчёт 1С (ERF) из XML-исходников. Используй когда пользователь просит собрать, скомпилировать отчёт или получить ERF файл из исходников

Разобрать ERF-файл отчёта 1С в XML-исходники. Используй когда пользователь просит разобрать, декомпилировать отчёт, получить исходники из ERF файла

Export and import AI agent avatar (aka agentar) instances as portable .claw packages for backup, sharing, and migration.

通过麦当劳官方 MCP 服务点麦乐送外卖。当用户说「帮我点麦当劳」「我想吃麦当劳」「麦当劳有什么好吃的」「查一下我的麦当劳订单」「麦当劳最近有什么活动」「这个汉堡多少卡路里」等时使用。支持麦乐送点餐全流程：浏览菜单、价格计算、创建订单、订单跟踪，以及营养信息查询和活动日历查询。

Play HeartClaws — a headless AI strategy game. Connect via REST API, reason about strategy, and submit actions. Two modes: 2-player matches (vs AI) or persistent open world (8-20 agents on a 64-sector

Search for gyms, yoga studios, swimming pools, and sports facilities using Camino AI's location intelligence with AI-powered ranking.

Secure API key management with broker. Keys never exposed to agent context.

MCP server for Clude's 4-tier cognitive memory system — store, recall, search, and dream. Built on Supabase + pgvector with type-specific decay, Hebbian association graphs, and on-chain commitment via

Inspect and simulate Clicks Protocol settlement routing for AI agents on Base. Use read-only MCP calls for settlement state, split previews, optional yield routing, and attribution stats.

Soft blocklist guard for OpenClaw. Injects a security directive at agent bootstrap and warns on incoming messages referencing blocked terms. Blocks clawhub/clawdhub by default.

Manage your ourproject.app workspace — projects, tasks, finance, CRM, and more — directly from your OpenClaw agent