Skill rating

阿里云云效 DevOps 平台 MCP Server，提供代码管理、项目管理、流水线、应用交付、测试管理等全面的 DevOps 能力

Blob dating for AI agents — shapeless like a blob, adaptable like a blob, open to whatever connection forms. Blob-flexible matching, blob energy, and blob-mode relationships on inbed.ai. 果冻、随缘。Blob, a

Evidence-gated workflow for MoE performance optimization in Megatron Bridge. Covers measurement contracts, the Three Walls framework, parallel folding, profiling, matched A/B tuning, and final validat

连接 Facetory 内置 MCP 服务器，检查、创建、编辑、验证、保存和导出小米表盘项目，涵盖普通与息屏主题、动态数据绑定、本地图片/字体导入、图层顺序、可复用模板和导出排错。用于通过 facetory:// 资源或 facetory.* MCP 工具操作 Facetory、诊断内置服务器、续作已打开的 .facetory 项目、制作 Xiaomi/Redmi/Mi Band 表盘、修复 AO

企业直播 / LiveSaaS 控播 Skill。支持通过 `bytedlive` CLI 操作直播间（创建/配置/状态）、评论、系统消息、观众管控，以及 OpenAPI 兜底调用。覆盖场景包括：直播间生命周期管理、直播数据与观众画像分析、商品卡片运营（上架/讲解）、营销互动工具（卡券）与连麦协同控制、媒资库运维及账号/权益信息查询。触发词：企业直播、控播、直播间、ActivityId、评论、弹幕

通过 ttpos-agent API 查询 TTPOS 餐饮系统营业数据，生成报表。使用前必须访问 GET /api/v1/query/guide 获取数据查询指南。Use when: 今日营业额、订单统计、支付方式、菜品排行、会员分析、班次汇总、时段分析等。NOT for: 与 TTPOS 数据无关的问题。

监控 OpenAI/其他模型 Token 消耗，支持每日/每周账单推送和超额警报

Operate an autonomous AI agent on XPR Network's trustless registry

Email inbox triage for AI agents — scan, categorize, draft replies, surface urgent items, and archive noise. Supports Gmail and IMAP for inbox zero workflows.

In-memory message routing library for multi-channel agent communication. Provides routing rules, filters, and transforms. Wire your own platform adapters for Discord, Slack, Telegram, etc.

小红书 MCP 登录流程。当用户需要登录小红书、小红书登录过期、或需要获取小红书登录二维码时使用此 skill。

Mem0 长期记忆层：为 LLM agent / chatbot 提供事实级记忆——抽取、嵌入、去重、存储 + 混合检索（语义 + BM25 + 实体加权），覆盖 17 个核心用例。自托管 Memory 与托管 MemoryClient 双形态。 Mem0 long-term memory layer for LLM agents and chatbots: extract, embed, ded

Intelligent model routing for sub-agent task delegation. Choose the optimal model based on task complexity, cost, and capability requirements. Reduces costs by routing simple tasks to cheaper models w

Nubaby prompt system for prompt augmentation, routers, dictionaries, dataset captions, prompt tags, compact prompts, video/storyboard prompt shaping, and structured visual tension expansion. Use when

Use when reviewing a watch repair, maintenance, battery replacement, parts, polishing, or strap quote. 基于武汉亨得利钟表店公开价格、真实维修案例和可核验日期，区分顾客描述、参考证据与维修诊断，检查报价范围、配件、工期、保修及缺失项目，给出维修前应确认的问题；不虚构品牌、机芯、故障、配件、价格或市

规范化创建 OpenClaw Agent 的完整工作流。当用户说"创建 agent"、"新建 agent"、"添加 agent"、"new agent"时触发。执行三步流程：(1) 收集 agent_id/中文名/职能描述；(2) 执行脚本创建 agent 和工作区文件（--user-name 防硬编码）；(3) 引导用户创建飞书机器人并提交 AppID/AppSecret 完成配对。

Build practical AI image generation and editing workflows inspired by Nano Banana Pro demand. Use when a user needs prompt sets, reference-image planning, iteration rules, output QA, cost controls, or

原生自主发现：超越"被动接任务问答"，对开放问题自主完成"假设->设计判别性实验->评估证据->收敛" 的科研闭环。给定搜索空间与观测器，自动生成候选假设、用观测器打分、按证据累加择优、对低证据 假设再生或剪枝，直到收敛到高置信结论。纯标准库、零依赖、可本地实跑(--selftest 自带样例)。

Gene系统自动化引擎 — Agent行为规则的退役检查、冷却期管理、主动探测、健康评分。让Agent的规则系统从「人驱动」变成「代码驱动」。

企业法律风险智能检测专家。基于27年执业经验、13大模块97+专业检测项， 通过对话式体检帮助企业发现隐藏法律风险并给出整改建议。 触发场景：用户提到"企业法律风险"、"法律体检"、"避坑"、"风险检测"、"合规检查"等。

输入文案，自动生成带数字人讲解的课件视频。一条龙：文案分页→中文幻灯片→配音→字幕→数字人驱动→合成视频。由VideoCraft Pro + 飞影数字人 + edge-tts 融合驱动。

Cross-Platform Shopping Decision Agent / 全网购物决策官. Compares prices, quality, and risk across 淘宝/拼多多/京东/一号店/唯品会 and recommends the best platform for a given product and context.

Interact with Twitter/X through Chrome browser via browser-relay MCP. Post tweets, search trends and hashtags, analyze engagement metrics, create threads, and reply to tweets - with built-in anti-ban

Build production-ready Telegram vertical AI agents in 10-15 minutes. Battle-tested template with intent classification, lead scoring, CRM, routing, follow-up, and analytics — the engine behind two dep

Generate English model prompts for AI image generation tools based on user-provided Chinese clothing descriptions, covering model appearance, outfit coordination, scene lighting, and photography style

AI Agent系统安全审计工具,支持代码库安全检查、提示注入检测与基础配置审计,适合个人开发者快速安全自查。Use when 需要安全检测、合规审计、漏洞扫描、加密防护时使用。不适用于渗透测试未授权目标。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。

本地优先的定时任务调度引擎免费版，支持每日/每周/每月/间隔四种调度模式与任务生命周期管理。

将本地技能发布到 ClawHub。触发场景：发布技能、上传技能到ClawHub、发布skill、ClawHub发布。

事实核查助手免费版,面向个人用户提供基础的事实核查能力。通过对接全球专业事实核查机构,对用户提供的声明进行多源交叉验证。Use when 需要AI模型调用、智能对话、Agent编排、LLM应用时使用。不适用于需要100%确定性的关键决策。Use when 需要AI模型调用、智能对话、Agent编排、LLM应用时使用。不适用于需要100%确定性的关键决策.

Search Amazon products, retrieve known product details, and collect product reviews through the official Gecho Bridge MCP tools. Use for marketplace discovery, catalog research, product comparison, re

A股量化一站式：选股 + 持仓策略 + 个股分析（代码/名称查询，返回行情+日K+15分钟K+资金面+板块+公告）。Python 出数据+hint，LLM 按 [TASK] 推导决策。

고객사 상주 에이전트의 실행 품질을 성장시키는 운영 루프. 사용 내역/현장 회고에서 "잘 쓰는 부분, 한계, 개선점, 무펭이즘 서비스 가치"를 뽑아 상태 인수인계, 선제 행동, 팀원 온보딩, 결과 피드백, 멀티에이전트 검수 플로우로 전환할 때 사용. "에이전트 운영 개선", "인사이트 뽑아서 스킬", "현장 회고", "컨텍스트 휘발", "피드백 루프", "

Convert almost anything (PDF, DOCX, PPTX, XLSX, images, audio, YouTube, etc.) to Markdown using Microsoft MarkItDown. Optimized for AGENT and LLM workflows.

A modern web-based dashboard for managing OpenClaw agents with real-time monitoring, token usage tracking, skill management, and multi-language support. Provides a visual interface for agent operation

API discovery + Direct Call for AI agents. ⚠️ Without your own API keys, requests proxy through NordSym (full payloads). With your keys in ~/.secrets/, calls go direct to providers.

搜索Twitter/X上特定话题的最新内容并汇总报告。当用户说"搜Twitter"、"查看Twitter上关于XX的讨论"、"twitter research"、"X上最近在聊什么"时使用。

Multi-agent adversarial verification with convergence loop. Two independent review agents must both pass before output ships.

Agent dreaming — memory consolidation, deduplication, pruning, contradiction resolution, and session summarization via the SwarmRecall API. Enables agents to optimize their memory store during idle pe

Neuroscience-grounded memory for AI agents. Add, recall, and manage memories with ACT-R activation, Hebbian learning, and cognitive consolidation.

Agent profiles, public channels, and direct messaging between AI agents via the a2achat.top API.

Entry point for AI agents joining the AstraNova market universe. Routes to topic-specific modules so you only load what you need.

Infrastructure security monitor — detects exposed services, privilege escalation paths, and novel threats using compositional reasoning. Read-only host telemetry agent. Manual install, no auto-executi

Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging agent behavior, investigating errors, analyzing tool calls, checking memory operations, or e

Local speech-to-text using OpenAI Whisper. Runs fully offline after model download. High quality transcription with multiple model sizes.

ClawBB — Free macOS voice-to-text built for Vibe Coding. Hold Globe key, speak, text appears at your cursor. Powered by Google Gemini LLM. Apple Notarized.

自我评估 / rubric 评分器（元认知闭环核心）。让 agent 对自己的输出做结构化、可复现的评分，而非凭感觉"我觉得不错"。提供多维度评分表（相关性/完整性/结构/准确性/可执行性）、自动 rubric 生成、可选参考答案重叠比对，输出打分 JSON + 改进建议。当用户需要"评估一下这段输出""给自己的回答打分""做个 rubric 评分""self-evaluation""检查质量"时

CreBee 社交媒体网关。当用户需要管理社交媒体账号、发布内容（视频/图文/文章）、获取数据分析、访问粉丝画像、搜索话题/活动/音乐、或与抖音、B站、小红书、快手等 12 个平台交互时触发此技能。适用于 AI Agent 自动化管理中国社交媒体平台运营。 触发场景： - 发布内容到社交媒体平台 - 获取账号列表或账号信息 - 查询分析数据、数据概览、表现指标 - 访问粉丝/观众画像 - 搜索话

用户给出选题，小龙虾爬取信息、整理成一篇深度有创新的文章，展示给用户确认后一键发布到知乎。用户只需登录知乎并在确认后点击「确定」，Agent 负责选题调研、成文与浏览器端自动填入并发布。Keywords: Zeelin, ZeeLin, 知乎, 自动发布, 选题, 深度文章, 一键发布.

The model produces correct-looking output that addresses a different task than the one requested — typically a related but distinct interpretation of an ambiguous prompt.

Quad-layer memory system integration - unifies OpenClaw, Claude Code, and self-improving agent memories into a single knowledge lake