发现 Skills
为真实工作流程挑选经过整理的 Skill,连接、安装并开始使用。
hive
Complete workflow for building, implementing, and testing goal-driven agents. Orchestrates hive-* skills. Use when starting a new agent project, unsure which skill to use, or need end-to-end guidance.
jimmer-orm
Jimmer ORM development assistant that helps write entity mapping code and DSL query statements. Suitable for: (1) defining or modifying Jimmer entities (interfaces annotated with @Entity); (2) writing Jimmer DSL query code; (3) configuring entity associations (@ManyToOne, @OneToMany, @ManyToMany); (4) using dynamic predicates, dynamic table joins, or implicit subqueries; (5) editing Java/Kotlin files that contain Jimmer-related code.
moai-toolkit-codegen
AI-powered code generation toolkit (UV scripts migrated to builder-skill-uvscript)
mungers-lattice
Multidisciplinary analytical engine using Charlie Munger's latticework of mental models. Applies cross-disciplinary thinking (math, physics, biology, psychology, economics) to dissect life and business decisions. Use when user presents a decision problem, investment question, or complex analysis request requiring deep rational analysis.
n8n-mcp-tools-expert
Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns.
posthog-instrumentation
Automatically add PostHog analytics instrumentation to code. Triggers when user asks to add tracking, instrument events, add analytics, or implement feature flags in their codebase.
python
Python programming patterns and best practices
rendiv-video
Guidance for building programmatic videos with rendiv — a React/TypeScript framework for composing video scenes, animating with springs and interpolation, and rendering to MP4/WebM. Use when writing or modifying rendiv compositions, working with rendiv animation APIs, or setting up a rendiv project.
smartthings
Control a SmartThings hub and devices, and manage automations and scenes
sonos-control
Control Sonos speakers through MCP tools - search and play music, manage queue and playlists, adjust volume. Use when users request music playback, mention artists/songs/albums, want to control Sonos speakers, manage playlists, or ask about what's playing.
spec
Implement features using Spec Driven Development (SDD) workflow. Creates design and task documents with approval gates.
TDD Process
Strict test-driven development state machine with red-green-refactor cycles. Enforces test-first development, meaningful failures, minimum implementations, and full verification. Activates when user requests: "use a TDD approach", "start TDD", "test-drive this".
wordpress-router
Use when the user asks about WordPress codebases (plugins, themes, block themes, Gutenberg blocks, WordPress Core checkouts) and you need to quickly classify the repository and route it to the correct workflow or specialist (blocks, theme.json, REST API, WP-CLI, performance, security, testing, release packaging).
yt-dlp
Download videos and extract audio from various platforms using yt-dlp. Use when user provides a video URL, asks to download a video, or when conversation contains video links from YouTube, Twitter/X, Vimeo, TikTok, Instagram, etc.
zimage-skill
Generate images using ModelScope Z-Image-Turbo API. Use when user asks to generate, create, or make images, pictures, or illustrations.
institutional-ai-operating-principles
Operating principles that turn any AI assistant into an institutional agent instead of a chat toy. Enforces signal over noise, revenue over time savings, anti-sycophancy, skills-first reusability, and auditable output structure. Load at the start of any project, workspace, or conversation to make the AI behave the way top-performing companies (Ramp, Hebbia, and the 20% of firms capturing 75% of AI's economic gains per PwC) actually use AI. Synthesizes McKinsey's 12-theme AI Transformation Manifesto, George Sivulka's Seven Pillars of Institutional AI (a16z), Seb Goddijn's Ramp Glass harness playbook, and Anthropic's Agent Skills specification. Activate this skill on every session, for every task — drafting, research, design, code, analysis, strategy, automation, client work.
shopify-landing-page-builder
High-converting landing pages — campaign pages, collection pages, seasonal promos, A/B testing
stop-preview
Stop a running MkDocs preview server. Use when port 8000 is busy, when switching tasks, or after finishing documentation edits.
deck-tech-sharing
GitHub-dark theme + JetBrains Mono monospaced font with terminal-style code blocks; includes agenda and Q&A
deck-xhs-white
Pure white + top rainbow bar + gradient text + macaron-style soft cards + black-background pill
finance-report
Masthead + KPIs + Revenue/Burn chart + P&L table + Highlights + Outlook
invoice
Standard invoice: sender/recipient + line items + taxes + total + payment instructions
literature-review
Use when a hypothesis has been formulated and you need to gather existing knowledge before designing experiments. Systematic search of PubMed, bioRxiv, and relevant databases to identify prior work, known results, and knowledge gaps.
validate-urls
This skill should be used when the user asks to "validate external URLs", "check for link rot", "screenshot URLs", "archive external links", or wants to verify and document external web resources (http/https) referenced in the codebase. This is for external URLs only, not internal file paths.