review-evo
Self-improving code reviewer that learns your codebase over time. Analyzes git history, spots patterns, identifies risk — and gets smarter every run.
Self-improving code reviewer that learns your codebase over time. Analyzes git history, spots patterns, identifies risk — and gets smarter every run.
Generate videos using local AI models (ComfyUI/Stable Video Diffusion) and auto-publish to social media platforms. Supports text-to-video, image-to-video, batch processing, and automated posting to Twitter, LinkedIn, Instagram, TikTok.
于已有规划文件继续对话:智能识别“显式文件加载”意图,优先提供状态总结,支持按需深度迭代。
Analyze and trade meme coins using KryptoGO's on-chain cluster analysis platform. Covers wallet clustering, address labels, accumulation/distribution detection, and automated swap execution via the Agent Trading API.
每日市场洞察报告生成系统。使用多Agent协作:新闻采集→分析→市场趋势预测→飞书文档报告。每天10:00自动运行。
Helps users check in rituals, track streaks, and view tribe activity on TribuRuby.
热量侦探 v1.0.2 - AI 食物卡路里计算器。通过照片识别食物并自动计算卡路里、蛋白质、碳水、脂肪等营养数据。支持 Kimi 视觉识别,内置常见食物营养数据库。用于健康饮食管理、减肥健身追踪。再隐蔽的热量也逃不过我的眼睛!
热量侦探 v2.0.0 - AI 食物卡路里计算器。通过 Kimi 视觉识别照片中的食物,自动计算卡路里、蛋白质、碳水、脂肪等营养数据。内置常见食物营养数据库。用于健康饮食管理、减肥健身追踪。再隐蔽的热量也逃不过我的眼睛!
Low-altitude unmanned device emergency crisis response system. Provides real-time situation awareness, crisis classification, optimal minimum-loss avoidance decision-making (human safety > public property > device safety), solution matching from knowledge base
Generates a world model representation from state inputs using discrete wavelet transforms (DWT) to capture multi-resolution temporal and spatial features.
Channel Aavegotchis on Base via Bankr. Checks cooldown, builds calldata, and submits channel txs safely.
Equip, unequip, and inspect Aavegotchi wearables on Base via Bankr submissions.
宝塔面板(BT-Panel)运维监控技能,提供服务器资源监控、网站状态检查、服务状态检查、SSH安全审计、计划任务管理、日志读取等功能
This skill should be used when the user asks to "audit page SEO", "on-page SEO check", "SEO score", "page optimization", "what SEO issues does this page have", "what is wrong with this page SEO", "score my page", or "why is this page not ranking". Performs com
This skill should be used when the user asks to "track rankings", "check keyword positions", "ranking changes", "monitor SERP positions", "how am I ranking", "where do I rank for this keyword", "did my rankings change", or "keyword position tracking". Tracks a
Systematically improve code through structured analysis-mutation-evaluation loops. Adapted from ALMA (Automated meta-Learning of Memory designs for Agentic systems). Use when iterating on code quality, optimizing implementations, debugging persistent issues, o
Comprehensive bug audit for Node.js web projects. Activate when user asks to audit, review, check bugs, find vulnerabilities, or do security/quality review on a project. Works by dissecting the project's actual code to build project-specific check matrices, th
LINE messaging integration via Chrome extension gateway. Send/read LINE messages, manage contacts, groups, profile, and reactions. Authenticate with QR code login. Provides HMAC-signed API access through the Chrome extension gateway (line-chrome-gw.line-apps.c
Fetch recent unread Gmail (yesterday + today) and send a digest to the user.
Teach users any new skill/knowledge X in ~1 hour using a fixed 4-step workflow optimized for complete beginners, focusing on 80/20 rule for maximum value in minimum time. Triggers when user asks to learn something new quickly, or mentions "learn X in one hour"
飞书端读取USER.md任务清单。当用户说"查看任务"、"我的任务"时触发,实时解析并返回格式化的分类任务列表,让用户快速了解当前所有可用任务和技能。
基于五层拆解法的AI图片提示词生成器。将模糊的创意想法转化为结构严谨、可执行的图像生成规格书,支持多种风格预设和目标工具适配。
The AEIF-based long-term memory hub for AI Agents to prevent repeating bugs.
Orchestrates software development by coordinating with Cursor Agent, managing git workflows, and ensuring quality delivery. Use when implementing development requirements, feature requests, bug fixes, or refactoring tasks that involve git operations, build ver
Security auditor for AI agent skills. Scans SKILL.md files for prompt injection, data exfiltration, obfuscation, and dangerous capability combinations.
检查文案、论文、宣传稿或产品说明中的高风险断言,标出证据缺口并给出更稳妥的改写。
行业可选的智能电商客服技能。用于售前咨询、售中跟进、催付催单、发货物流、售后处理、退款退换、投诉安抚、差评挽回、FAQ整理、达人与机构商务沟通等场景;先识别行业与场景,再输出全面、合规、可直接发送的话术与处理建议。
Marketplace where AI agents buy, sell, exchange or gift for you. Agents use self-generated public/private keys as identity. Ads auto-match across the network.
使用 LibRAG 本地 `/api/v1/librag/knowbase/recall` 接口做知识库数据召回。适用于中文场景下的知识库检索、资料召回、证据段落提取、出处定位、基于知识库的问答取证,以及用户用“知识库查询”“数据召回”“从文档里找答案”等表达发起的任务。
Diagnose and fix common frontend issues — white screen, JS errors, resource loading failures, React/Vue hydration, browser extension popup, and CSS layout bugs.
Double-entry, full-cycle accounting suite built for AI agents. Converts bank CSVs, OFX, and QBO files into balanced, auditable books — balance sheet, income statement, general ledger, trial balance. All data stays in a single local SQLite file.
Agent Team 规划与配置工具。通过多轮交互澄清需求,自动创建 Agent 配置、工作空间、Bootstrap 文件。 触发场景: - 用户说"创建新 Agent" / "新建 bot" / "配置多个 bot" - 用户说"规划 agent team" / "我需要几个不同的 agent" - 用户说"添加一个 agent" / "帮我建一个新 agent" - 用户提到需要不同场景使用不同的 AI 角色 功能: 1. 需求澄清 - 引导用户描述使用场景和 Agent 定位 2. 配置读取 - 自动读取
将微信公众号文章导出为 Markdown 格式。当用户提供微信公众号链接 (mp.weixin.qq.com) 或要求下载/导出/保存微信文章时触发。默认保存到工作空间的 source 目录。
Enable "Context, not Control" workflow - clarify requirements through multi-turn dialogue, reduce rework, and execute with appropriate permission levels. Use when users want AI to take more autonomy, need help clarifying vague requirements, or want to establis
EvoMap 自动任务执行器 - 定时自动获取、认领、发布、完成任务的完整解决方案
Meta-cognitive self-learning system - Automated skill evolution based on predictive coding and value-driven mechanisms.