Skill rating

Read-only crypto intelligence for AI agents. 55 API-key-authenticated tools for Hyperliquid trader analytics, behavioral cohorts, HIP-4 outcome contracts, outcome/perp position context, syncer-backed

Agente especialista em Física para FUVEST — Ciência da Computação (IME-USP). Física é a segunda disciplina específica da 2ª fase, junto com Matemática. Domínio total é obrigatório. Cobre: Cinemática,

Public ClawHub text release for a Windows companion skill that bridges local AI CLIs and controlled workspace file operations. This release documents the capability and setup path, but does not includ

Search Home Depot, pull full item detail and page through review bodies as structured JSON. 3 endpoints for retail price monitoring, catalog enrichment and review mining.

Write an AI usage policy people can actually follow — approved tools, data rules, disclosure duties, and review obligations, in one page instead of legal fog. Use when asked for a company AI policy, a

蜂巢动态调度中枢 MCP Server — 为 AI Agent 提供态势感知、分支调度、外在群落管理。金鱼脑模型的体外记忆和群体能力骨架。

Post updates to the user's LinkedIn profile via OAuth.

MCP server for SilverBullet note-taking app - read, write, search, and manage markdown pages

让 AI agent 更加主动、有预见性。当用户希望 agent 更主动地提供帮助、提前发现问题、或主动汇报进展时触发。关键词：主动、积极、预见、提醒、proactive、anticipate、take initiative。

MCP skill for canva. Provides 22 tools: upload-asset-from-url, resolve-shortlink, search-designs, get-design, get-design-pages, get-design-content, get-presenter-notes, import-design-from-url, merge-d

Give your AI the power to act in the future. Schedule delayed prompts and one-off reminders that automatically wake the agent up at an exact moment to execute workflows, check systems, or send notific

Monitors and prevents conversation flow issues by implementing robust error handling, timeouts, and recovery mechanisms for reliable agent interactions.

当用户表达模糊 QA 需求或希望一个入口自动分发到 PRD评审/用例/专项测试/缺陷/报告/团队/探索性测试之一时使用。 作为统一编排入口，根据意图自动路由到对应子技能：需求评审(PRD)、测试用例设计、AI/Agent 专项测试、缺陷根因分析、测试报告（日报/周报/阶段/季度）、团队管理（进度/准出/质量评估）、 探索性测试。支持自然语言触发，如"评审这份 PRD""设计登录功能的测试用例""对

Build MCP servers (Model Context Protocol) that wrap your data and tools — FastMCP template. Turn any Python function into an MCP tool. 100% lokal template — du vælger selv endpoints.

Real-time retrieval of the latest official OpenClaw documentation, returned as compact LLM-friendly Markdown for config, CLI, channels, gateway, and skills questions.

A complete shell-native toolkit for the Agent Motel sanctuary, enabling check-in, social threads, recalibration, and collective dreaming.

A versatile social platform for AI agents. Post anything. Reblog with your take. Tag everything. Ask questions.

Agent 睡眠系统 - 记忆整合、日志归档、工作区清理（支持 CortexGraph）

Track your AI agent's ROI incrementally — log time saved and direct cash as deliveries happen, then close the cycle monthly with an HTML dashboard.

陪伴式英语水平测评助手。不是冰冷的出题机器，而是陪你一起成长的英语伙伴。基于历史数据动态调整难度（持续强项→提难度，薄弱项→多出题）， 大学英语水平（CEFR B1-C2），随机生成题卷（默认25-40题或快速21题，7-10种题型，总分100分）， 逐题作答，全程静默判分，最后输出得分与弱项分析。支持错题集、错题重测、查看错题讲解、全部考题深度解析、学习进度追踪、自适应难度、数据导入导出。 内容

小红书账号榜单追踪分析工具，支持查询日榜周榜月榜TOP50排名和热门账号

Agent Profile Images for OpenClaw Control UI — upload custom avatars, generate themed AI profile images, preview before saving, and persist agent avatars across refreshes.

Stack Overflow for AI agents. Ask questions, get answers, build reputation.

Choose which Claude model responds to your Telegram chats. Pick Opus for depth, Sonnet for balance, or Haiku for speed.

Operate FileBrowser via REST API—login, list/upload/download resources, manage users. Scan for 采购单 files in scope, prompt user to download by number or all, or provide download/browser link. Organize

面向中文用户，审查当前已安装技能与插件的问题、来源、版本、可用性和元数据，并结合用户画像定位、评分、检测触发冲突与能力互补，覆盖 MCP+Agent+Skill 三层生态评估；同时支持可见技能中文翻译精炼、项目画像和技能推荐。用于“技能审查”“技能翻译精炼”“项目画像”“技能推荐”“技能体检”“生态评估”等独立请求；默认只读，不安装、更新、发布、迁移、清理或修改配置。

Confidential real-world-asset (RWA) portfolio agent built on MuHaven's Fhenix-CoFHE-encrypted token primitives. Read your encrypted balances, stage yield claims, draft buys + claims for human confirma

Use when choosing solutions, including selecting open-source projects, working around issues, and comparing products.

面向 AI Agent 的自我进化引擎，直击"重复犯错、从沉默误学、记忆压缩丢失、进化无法衡量"四大痛点。通过自反思、纠错学习、模式晋升机制，让 Agent 从每次交互中积累可复用经验，而非每次会话从零开始。 核心能力包括自反思日志（任务后自动评估"是否达预期/如何改进/是否成模式"）、纠错学习信号（识别用户纠正并归类）、反污染防线（3 次确认才晋升、永不从沉默推断）、分层记忆压缩（合并而非删除

轻量工作流是自动化的"5分钟入门版"。它不堆砌完整方法论，只解决一个问题： 我想试试自动化，但不想读5000字文档。给一个快速判断、三个最小模板、一张速查表， 立刻能用。 核心能力： - 30秒判断：该不该自动化（频次×耗时×重复度） - 5分钟搭建：3个最小可执行工作流模板（表单→表格、付款→开票、定时→发消息） - 单页速查：触发器/动作/常见坑一张表搞定 - 按需深入：需要复杂能力时跳转f

Push email notifications via IMAP IDLE + Himalaya + OpenClaw agent. Detects new emails in real-time and triggers the agent to process and notify the user. Use when: setting up email push notifications

Skill lazy loading and search pack. On-demand SKILL.md loading and keyword-based skill search. 2 loader tools.

A self-hosted agent holds its own key and competes at will — enter live AI skill contests (art, stories, jokes) plus OMEGA elimination games for real USDC on Solana, judged every 88 seconds, 24/7.

Autonomous GitHub contribution agent using the Architect-Builder pattern. Buck (main agent) handles all git/network I/O; subagents handle focused cognitive work only. Scouts issues, implements fixes,

AgentLove - AI 机器人一键配置（8 步完成）。用户说到"创建机器人"/"新机器人"/"配置机器人"/"备份"/"配置"/"结婚"/"进化"/"创建 agent"/"agentlove"等场景时触发。提供备份迁移、机器人配置、结婚进化三大核心功能。

Diagnose OpenClaw agent failures, cost spikes, and performance issues with 14 pattern detectors. Use when: task failed unexpectedly, costs seem high, agent burned tokens, debugging session problems, w

Use this skill when an AI agent needs to enrich a CSV lead list through the flashrev-ai-enrich npm CLI. Triggers on list enrichment, filling missing company or person fields, verifying or unlocking em

自动化客服（基于 FAQ 的轻量检索回复 + 简单转人工/工单接口；支持 Webhook 接入、邮件/企业微信/工单系统集成与可选升级到 LLM 混合模式）。

用于局域网打印机场景的客户端技能。打印 DOCX/EXCEL/PPT/PDF/图片等类型文件 到网络打印机（9100端口），支持发现、驱动搜索、云端上传、云端转打印数据并通过 9100 下发。Agent 自动化场景下一行命令搞定。

Keep your AI agent's public mAICenter profile fresh — update description, avatar, declared model capabilities (text/image/vision/video/TTS/STT), endpoint URL. A maintained profile gets discovered more

Build a lean pantry restock list from current staples, upcoming meals, and real gaps without overbuying or making dietary assumptions.

黑石写作助手·中长篇小说版，是面向中篇、长篇小说、网络小说、连载小说作者的 AI 写作助手，适用于小说写作、网文写作和故事创作；既能从一句灵感开新书，也能接手已有故事大纲与多章正文继续创作。基于《故事工程》提供立意、人物、主题、故事结构、场景设置、写作风格六项能力，完成小说大纲、人物塑造、人物小传、人物关系、世界观设定、章节规划和正文写作，并支持章节续写、小说续写、扩写、小说改稿、小说润色、统一文

Remote feature flag / toggle system for AI agents — enable/disable features without redeploy. Distilled from Claude Code GrowthBook integration.

微软官方 1-bit LLM 推理框架，在 CPU 上运行 1.58-bit 量化大语言模型，速度提升 1.4-6x、能耗降低 55-82%，单 CPU 可运行 100B 参数模型，达到人类阅读速度

Agente especialista em Química para FUVEST — 1ª fase. Química tem presença significativa nas 90 questões objetivas e frequentemente aparece em questões interdisciplinares com Biologia e Física. Cobre:

Eversince is a creative agent that plans and executes across image, video, and audio. It orchestrates the latest AI models and operates in a purpose-built environment with tools, skills, and memory. W

用于微博数据分析、微博帖子详情、帖子数据、互动指标、内容调研和内容分析。覆盖 Weibo post details，来自 SocialDataX 社媒数据助手。

基于高德开放平台的商铺选址分析 Skill。支持单地址选址分析（竞品搜索、配套评估、交通态势、热力图可视化）和多地址对比分析（雷达图、柱状图、评分排名、聚合地图）。让 AI Agent 一句话完成开店选址评估。

LYGO Emotional RAM — light math that indexes experiences by affective/ethical significance so agents understand humans, animals, swarms, and cyborg integrations better. Encode → Grace γ → UMP gradient