全部能力

Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based…

Distill repeated work into Eve skillpacks by creating or updating skills with concise instructions and references. Use when a workflow repeats or knowledge…

Summarize documents, extract key points, and generate structured outlines

Build effective study habits with spaced repetition, active recall, and session tracking

Vercel Chat SDK expert guidance. Use when building multi-platform chat bots — Slack, Telegram, Microsoft Teams, Discord, Google Chat, GitHub, Linear — with a…

OpenDuck — open-source distributed DuckDB with differential storage, hybrid dual execution, and transparent remote database attach

Creates evidence-based learning plans that maximize long-term retention through spaced repetition, retrieval practice, interleaving, and elaboration. Guides…

Onboards users to MLflow by determining their use case (GenAI agents/apps or traditional ML/deep learning) and guiding them through relevant quickstart…

Vercel Runtime Cache API guidance — ephemeral per-region key-value cache with tag-based invalidation. Shared across Functions, Routing Middleware, and Builds.…

Project bootstrapping orchestrator for repos that depend on Vercel-linked resources (databases, auth, and managed integrations). Use when setting up or…

Routes Snowflake-related operations to Cortex Code CLI for specialized Snowflake expertise. Use when user asks about Snowflake databases, data warehouses, SQL…

Calculates targeted CRAP (Change Risk Anti-Patterns) scores for a named .NET method, class, or single source file. Use when the user explicitly asks to compute CRAP scores or assess risky untested code for a specific target, combining Cobertura coverage data with cyclomatic complexity analysis. DO NOT USE FOR: project-wide coverage analysis, coverage plateau or "stuck coverage" diagnosis, what's blocking coverage, or where to add tests across a project (use coverage-analysis); writing tests; running tests without CRAP context.

Extract text from PDFs for LLM consumption. Use when processing PDFs for RAG, document analysis, or text extraction. Supports API services (Mistral OCR) and…

Expert children's book writer creating delightful, engaging books for ages 2-9. Specializes in rhyming books, stories, songs with proper values, educational…

Next.js 16 Cache Components guidance — PPR, use cache directive, cacheLife, cacheTag, updateTag, and migration from unstable_cache. Use when implementing…

Vercel Marketplace expert guidance — discovering, installing, and building integrations, auto-provisioned environment variables, unified billing, and the…

Extracts key learnings from conversations, debugging sessions, and failed attempts. Use at session end or after solving complex problems to capture insights. Stores discoveries in memory (via amplihack.memory.discoveries), suggests PATTERNS.md updates, and recommends new agent creation. Ensures knowledge persists across sessions via Kuzu memory backend.

Choose and combine Eve storage primitives to give agents persistent memory — short-term workspace, medium-term attachments and threads, long-term org docs and…

Deep-dive analysis of GitHub projects. Use when the user mentions a GitHub repo/project name and wants to understand it — triggered by phrases like "帮我看看这个项目", "了解一下 XXX", "这个项目怎么样", "分析一下 repo", or any request to explore/evaluate a GitHub project. Covers architecture, community health, competitive landscape, and cross-platform knowledge sources.

Transform clichéd story elements by pushing along the emotional vector toward statistical edges. Use when first instincts are too predictable, when elements…