AI Ml AI agent skills

8,771 skills in the archive. Read a skill’s instructions or open its original repository.

• Convex Security Audit

  by @waynesutton

  Deep security review patterns for authorization logic, data access boundaries, action isolation, rate limiting, and protecting sensitive operations

• Convex

  by @waynesutton

  Umbrella skill for all Convex development patterns. Routes to specific skills like convex-functions, convex-realtime, convex-agents, etc.

• Convex Component Authoring

  by @waynesutton

  How to create, structure, and publish self-contained Convex components with proper isolation, exports, and dependency management

• Ai Llm Engineering

  by @Microck

  Operational skill hub for LLM system architecture, evaluation, deployment, and optimization (modern production standards). Links to specialized skills for prompts, RAG, agents, and safety. Integrates recent advances: PEFT/LoRA…

• AgentDB Learning Plugins

  by @Microck

  Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or…

• AgentDB Performance Optimization

  by @Microck

  Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of…

• AgentDB Memory Patterns

  by @Microck

  Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.

• AgentDB Vector Search

  by @Microck

  Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.

• Free Apis Catalog

  by @jamditis

  Curated free APIs with verified free-tier limits. Use when suggesting APIs or finding free weather, news, finance, or sports data.

• Claude Api

  by @PM-Shawn

  Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports…

• Skill Creator

  by @PM-Shawn

  创建、编辑、优化和测试 skills。当用户明确要求创建一个具体的新 skill、修改已有 skill 的内容或描述、运行 skill 评测，或优化 skill 触发准确率时使用。

• Abu Chrome Bridge

  by @PM-Shawn

  通过 Abu Chrome 扩展操作用户现有的 Chrome 标签页、登录态和浏览器资料。仅在用户明确要求使用 Chrome、已有标签页或现有登录状态时使用。

• Abu Browser

  by @PM-Shawn

  操作阿布应用内置的可见浏览器：打开网页、点击、填写、截图和提取数据。用户要求在阿布内预览或操作网页时使用；无需安装浏览器扩展。

• Abu Plugin Builder

  by @PM-Shawn

  Create or edit a local Abu plugin in its dedicated creation conversation. Generate the package, then validate with plugin_prepare for user-reviewed installation.

• Mermaid Diagram

  by @PM-Shawn

  用 Mermaid 语法生成可视化图表 — 流程图、架构图、序列图、ER 图、甘特图、状态图、思维导图、饼图等结构化图表。当用户要求画图/画架构图/画流程图等结构化可视化需求时触发，直接输出 mermaid 代码块，前端会自动转换为 HTML 并在沙箱 iframe 中渲染。

• Html Widget

  by @PM-Shawn

  生成可交互的 HTML 可视化组件 — 算法动画、数据图表、概念演示、交互式教程等。当用户需要交互式演示、动画解释、数据探索、UI 原型等场景时触发，直接输出 html 代码块，前端会在安全沙箱中渲染为可交互组件。

• Svg Diagram

  by @PM-Shawn

  用 SVG 生成精美的架构图、流程图、时序图、层级图、对比图等结构化图表。直接输出 ```html 代码块（内含 SVG），前端在沙箱 iframe 中渲染。效果比 Mermaid 更美观、布局更灵活。

• Infographic

  by @PM-Shawn

  生成精美的纯 HTML+CSS 信息图 — 时间线、流程、对比分析、SWOT、金字塔、漏斗、数据卡片、组织架构等。无需外部依赖，在沙箱 iframe 中渲染。适合将结构化信息以海报级视觉效果呈现。

• Reflect

  by @PM-Shawn

  复盘当前对话——回顾任务过程、总结经验教训、主动沉淀可复用的 skill。当用户要求"复盘"、"反思"、"总结一下刚才"、"有什么值得记住的"时使用。

• Prd Doctor

  by @PM-Shawn

  用户要审查、体检、评审一份 PRD / 产品需求文档 / 功能说明时使用，产出结构化的问题清单而不是笼统评价

• Init

  by @PM-Shawn

  初始化工作区规则文件 (.abu/ABU.md)，分析项目结构生成项目规则模板

• Alert Sop

  by @PM-Shawn

  自动分析告警信息，按SOP排查问题并生成处理报告

• Google Image Search

  by @glebis

  Search and download images via Google Custom Search API with LLM-powered selection. This skill should be used when finding images for articles, presentations, research documents, or enriching Obsidian notes with relevant…

• Local Models

  by @glebis

  Run quick, offline, private LLM tasks on local models via llama.cpp, reusing models already downloaded by Ollama. Use for cheap/bulk text work (summarize, classify, extract JSON, anonymize PII, translate, proofread, keywords),…

• Red

  by @glebis

  Residual re-identification RISK CHECK on text you have ALREADY redacted (defensive, dual-use). Use when the user asks to "check residual re-id risk", "red-team my redaction", "what can an attacker still infer", "is this safe to…

• Chunking Strategy

  by @giuseppe-trisciuoglio

  Provides chunking strategies for RAG systems. Generates chunk size recommendations (256-1024 tokens), overlap percentages (10-20%), and semantic boundary detection methods. Validates semantic coherence and evaluates retrieval…

• Rag

  by @giuseppe-trisciuoglio

  Implements document chunking, embedding generation, vector storage, and retrieval pipelines for Retrieval-Augmented Generation systems. Use when building RAG applications, creating document Q&A systems, or integrating AI with…

• Langchain4j Testing Strategies

  by @giuseppe-trisciuoglio

  Provides unit test, integration test, and mock AI patterns for LangChain4j applications. Creates mock LLM responses, tests retrieval chains, validates RAG workflows, and implements Testcontainers-based integration tests for Java…

• Prompt Engineering

  by @giuseppe-trisciuoglio

  Provides workflows to write, debug, and optimize prompts for LLMs, including few-shot example selection, chain-of-thought structuring, system prompt design, and template composition. Use when the user asks to write or improve a…

• Aws Cloudformation Bedrock

  by @giuseppe-trisciuoglio

  Provides AWS CloudFormation patterns for Amazon Bedrock resources including agents, knowledge bases, data sources, guardrails, prompts, flows, and inference profiles. Use when creating Bedrock agents with action groups,…

• Langchain4j Spring Boot Integration

  by @giuseppe-trisciuoglio

  Provides integration patterns for LangChain4j with Spring Boot. Configures AI model beans, sets up chat memory with Spring context, integrates RAG pipelines with Spring Data, and handles auto-configuration, dependency injection,…

• Langchain4j Ai Services Patterns

  by @giuseppe-trisciuoglio

  Provides patterns to build declarative AI Services with LangChain4j for LLM integration, chatbot development, AI agent implementation, and conversational AI in Java. Generates type-safe AI services using interface-based…

• Langchain4j Rag Implementation Patterns

  by @giuseppe-trisciuoglio

  Provides Retrieval-Augmented Generation (RAG) implementation patterns with LangChain4j for Java. Generates document ingestion pipelines, embedding stores, vector search, and semantic search capabilities. Use when building…

• Langchain4j Vector Stores Configuration

  by @giuseppe-trisciuoglio

  Provides configuration patterns for LangChain4J vector stores in RAG applications. Use when building semantic search, integrating vector databases (PostgreSQL/pgvector, Pinecone, MongoDB, Milvus, Neo4j), implementing embedding…

• Qdrant

  by @giuseppe-trisciuoglio

  Provides Qdrant vector database integration patterns with LangChain4j. Handles embedding storage, similarity search, and vector management for Java applications. Use when implementing vector-based retrieval for RAG systems,…

• Month End Close

  by @WellApp-ai

  Run a month-end (or period) close checklist against a Well workspace — verify everything is reconciled and posted before the books are closed. Use when the user asks to close the month/period, run a close checklist, check if the…

• Querying Well Data

  by @WellApp-ai

  How to query a Well workspace correctly — discover the schema first, then query the right root. Use whenever the user asks about their invoices, companies, contacts, bank transactions, accounts, or accounting ledger in Well, or…

• Cash Flow Forecast

  by @WellApp-ai

  Forecast cash flow and runway for a Well workspace from booked invoices and collected bank transactions. Use when the user asks for a cash-flow forecast, runway, how long until they run out of cash, projected balance, or…

• Ar Aging

  by @WellApp-ai

  Produce an accounts-receivable aging report and surface overdue invoices for a Well workspace. Use when the user asks who owes them money, an AR aging report, overdue invoices, days sales outstanding (DSO), or which customers to…

• Connect

  by @WellApp-ai

  Connect and verify the Well MCP — authenticate, confirm the tools work, and show what to ask. Use when the user runs /well:connect, just installed the Well plugin, or says the Well connection/MCP "isn't working" / "nothing…

• Reconciliation

  by @WellApp-ai

  Match bank transactions to invoices and surface unpaid / unmatched items in a Well workspace. Use when the user asks what's paid vs unpaid, to reconcile the bank, to find missing payments, or to match transactions to invoices.

• Vat Summary

  by @WellApp-ai

  Produce a VAT / sales-tax summary for a period from a Well workspace's posted ledger. Use when the user asks for a VAT return, VAT summary, sales tax owed, output vs input VAT, or tax declaration figures for a period.

• Compte De Resultat

  by @WellApp-ai

  Build a profit & loss statement (compte de résultat / income statement) from a Well workspace. Use when the user asks for a P&L, income statement, compte de résultat, revenue vs expenses, or net result over a period.

• Balance Sheet

  by @WellApp-ai

  Build a balance sheet (bilan) from a Well workspace. Use when the user asks for a balance sheet, bilan, assets/liabilities/equity, or financial position at a point in time.

• Qa Planning

  by @WellApp-ai

  Generate QA Contract with numbered Gherkin scenarios (G#N) and acceptance criteria (AC#N)

• Tech Divergence

  by @WellApp-ai

  Evaluate technical options with scoring matrix, trigger Gate 4 for significant decisions

• Debug

  by @WellApp-ai

  Systematic debugging with MCP integration, auto-invoke from qa-commit, Phase 7 Harden

• Autonomous Loop

  by @WellApp-ai

  Iterate until success or limit, composing existing skills with Jidoka integration

• Qa Commit

  by @WellApp-ai

  Verify implementation against QA Contract (G#N, AC#N), auto-invoke debug on RED

• Problem Framing

  by @WellApp-ai

  Frame problems using JTBD Job Stories, HMW questions, and persona validation

• Session Status

  by @WellApp-ai

  Generate breadcrumb headers/footers with takt time tracking and muda metrics

• Pr Review

  by @WellApp-ai

  Automated code review using ReadLints and Shell for technical validation

• Decision Capture

  by @WellApp-ai

  Capture patine (decision wisdom) at Gates when KO or challenge occurs

• Bpmn Workflow

  by @WellApp-ai

  Generate and maintain BPMN 2.0 diagrams linked to Gherkin scenarios

• State Machine

  by @WellApp-ai

  Document UI component states (current vs expected) with transitions

• Design Context

  by @WellApp-ai

  Refresh UI/UX context from design system, Storybook, and codebase

• Pr Threshold

  by @WellApp-ai

  Track commit accumulation and trigger PR when thresholds crossed

• Competitor Scan

  by @WellApp-ai

  Research best-in-class products using Browser MCP and WebSearch

• Dependency Mapping

  by @WellApp-ai

  Map slice dependencies using DSM matrix and prioritize by risk

• Gtm Alignment

  by @WellApp-ai

  Align phases with GTM strategy, persona tiers, and KPI targets

• Team Routing

  by @WellApp-ai

  Detect domain from context and find appropriate team member

• Slack Announce

  by @WellApp-ai

  Generate formatted Slack messages for team communication

• Code Review

  by @WellApp-ai

  Review code changes against hard rules and conventions

• Test Hardening

  by @WellApp-ai

  Convert passed QA Contract criteria to automated tests

• Notion Sync

  by @WellApp-ai

  Standardize Notion task updates across all modes

• Webapp Testing

  by @WellApp-ai

  Test web app UI using Browser MCP and Storybook

• Mcp Server

  by @WellApp-ai

  Guide for creating new MCP server integrations

• Compliance Audit

  by @WellApp-ai

  Audit Value Delivery compliance after PR push

• Skill Creator

  by @WellApp-ai

  Template and guide for creating new skills

• Kg Builder

  by @Mathews-Tom

  Designs and builds knowledge graphs from documents — ontology modeling with domain/range constraints, entity/relation/event extraction, entity resolution, provenance and supersession, and GraphRAG serving. Use when asked to…

• Baoyu Comic

  by @smallnest

  Knowledge comic creator supporting multiple styles (Logicomix/Ligne Claire, Ohmsha manga guide). Creates original educational comics with detailed panel layouts and sequential image generation. Use when user asks to create…

• Code Review

  by @smallnest

  Frontend-focused code review skill for React/TypeScript/Tailwind projects. Analyzes code quality, security vulnerabilities (XSS, CSRF), performance issues, accessibility (WCAG), React best practices, hooks usage, component…

• React Component Generator

  by @smallnest

  Generate React components following best practices with TypeScript, Tailwind CSS, and Zustand state management. Use this skill when the user requests creating React components, UI elements, or mentions component generation.…

• Wechat Article Writer

  by @smallnest

  专业的微信公众号文章创作助手。当用户提供网站链接、文本素材或图像，需要创作微信公众号文章时使用。支持通过搜索工具丰富内容、优化标题、调整语气为官方文案风格，帮助创作高质量的公众号推文。适用于企业宣传、品牌推广、资讯报道等官方内容创作场景。

• Feature Builder

  by @smallnest

  Build complete React features with proper layered architecture including UI components, business logic, API integration, and state management. Use this skill when users request implementing features like "user authentication",…

• Playwright Browser Automation

  by @smallnest

  Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate…

• Ui Analyzer

  by @smallnest

  Analyze UI design screenshots and generate React components with TypeScript and Tailwind CSS. Use this skill when the user provides UI mockups, design screenshots, or Figma exports and requests implementation. Provides detailed…

• Baoyu Image Gen

  by @smallnest

  AI SDK-based image generation using official OpenAI and Google APIs. Supports text-to-image, reference images, aspect ratios, and quality presets.

• Code Review

  by @smallnest

  专业的代码审查助手，提供结构化的审查流程、详细的检查清单和建设性的反馈指南。适用于审查Pull Request、代码提交或任何需要代码质量评估的场景，涵盖功能性、安全性、性能、测试、文档、架构设计等多个维度。

• Coze Api

  by @smallnest

  调用扣子(Coze)智能体 API 进行对话、工作流执行等操作。当用户需要集成 Coze 智能体、调用 Coze API、或开发 Coze 相关应用时使用。支持流式和非流式对话、工作流调用等功能。

• Prompt Optimizer

  by @smallnest

  Analyze and optimize user prompts for clarity, specificity, and completeness using interactive questionnaires or direct analysis. Use this skill when user requests are vague, ambiguous, incomplete, or lack necessary details.…

• Request Analyzer

  by @smallnest

  Proactively analyze user requests at the start of conversations to determine task type, assess prompt quality, and intelligently recommend which skills to activate. Should activate for ALL user requests to ensure optimal…

• Flutter Api

  by @smallnest

  Comprehensive Flutter API reference guide covering widgets, Material Design, Cupertino, animations, gestures, navigation, state management, and platform integration. Use when developing Flutter applications and needing detailed…

• Crewai Developer

  by @smallnest

  Comprehensive CrewAI framework guide for building collaborative AI agent teams and structured workflows. Use when developing multi-agent systems with CrewAI, creating autonomous AI crews, orchestrating flows, implementing agents…

• Hello World

  by @smallnest

  A fundamental skill that demonstrates the basic execution of a Python script. It serves as a "Hello, World!" example for the skill system, verifying that the environment is correctly set up and that the agent can execute scripts.

• Slidev

  by @smallnest

  Create and edit presentation slides using Slidev framework when user requests slides, presentations, or deck modifications

• Tech Article Writer

  by @smallnest

  技术干货文章创作专家,擅长用简练语言传递核心知识点,不遗漏关键信息

• Kanban Tasks

  by @jin-bo

  使用 agentao-kanban 看板进行任务管理（拆任务 / 状态流转 / 后台服务 / 看产物）。 本技能负责：① 初始化 .kanban/ 项目 ② 把需求拆成原子卡片入板 ③ 推动状态流转 INBOX → READY → DOING → REVIEW → DONE ④ 启停 daemon 与 Web UI ⑤ 察看卡片状态与产物。 触发关键词（中/英）：看板 / kanban / 任务管理 / task board / 拆任务 / 任务卡 /…

• Zootopia Ppt

  by @jin-bo

  将用户的演示讲稿转化为拟人化动物世界主题的演示文稿图像（顶级3D动画电影风格）。 分三步：① 理解演讲内容与受众 ② 生成每页的3D动画电影风格生图提示词（Markdown 格式，保存到 workspace/docs/outline/） ③ 调用 image_gen_ppt.py 批量生成图像（保存到 workspace/docs/slides/）。 触发条件：用户提供演示稿/PPT 内容，要求制作 疯狂动物城风格 / 拟人化动物 /…

• Ocr

  by @jin-bo

  OCR image files using the Qwen VL model via the bundled scripts/ocr.py (lives in this skill's directory, NOT your cwd). Use when the user asks to extract text from an image, perform OCR on a photo or screenshot, or recognize…

• Flint Chart Author

  by @jin-bo

  从结构化、表格或查询结果生成数据图表：选择适合对比、趋势、分布、相关性或层级关系的图型， 生成、修复、解释或校验 Flint 图表规格，输出可直接渲染的 ```flint 围栏块。 Trigger on: "画图", "画个图", "可视化", "出个图表", "flint", "chart", "visualize", "plot this", "graph these numbers", "对比一下…（给出多行数据时）", "趋势", "分布",…

• Pro Ppt

  by @jin-bo

  将用户的演示讲稿转化为「专业 · 高级感」风格的演示文稿图像（高端商务编辑风）。 视觉特征：极浅灰主色（#F2F2F2）、金属灰辅色、金色点缀、深蓝灰背景（#0F233B），整体克制、克莱因蓝调、印刷品级质感。 分三步：① 理解演讲内容与受众 ② 生成每页高级商务视觉提示词（Markdown 格式，保存到 workspace/docs/outline/） ③ 调用 image_gen_ppt.py 批量生成图像（保存到…

• Ai Ml Skills

  by @wentorai

  27 ai & machine learning skills. Trigger: ML experiments, model training, deep learning, NLP, computer vision. Design: covers frameworks, benchmarks, paper reproduction, and AI research workflows.

• Econometrics Skills

  by @wentorai

  10 econometrics skills. Trigger: causal analysis, regression models, treatment effects, panel data. Design: method-centric guides with R/Python code and diagnostic tests.

• Econml Causal Guide

  by @wentorai

  Apply EconML for causal inference combining machine learning and econometrics

• Ai Model Benchmarking

  by @wentorai

  Benchmark AI models across 60+ academic evaluation suites and metrics

• Generative Ai Guide

  by @wentorai

  Curated guide to generative AI covering LLMs and diffusion models

• Domain Adaptation Papers Guide

  by @wentorai

  Comprehensive collection of domain adaptation research papers

• Anomaly Detection Papers Guide

  by @wentorai

  Industrial anomaly detection methods and benchmark papers

• Client Proposal Generator

  by @OneWave-AI

  Generates full consulting proposals from a brief. Input client name, problem description, and rough scope. Outputs proposal.md with executive summary, problem statement, proposed approach, timeline, team, pricing tiers, and…