Plantilles
Plantilles de projectes i de codi
Unreal Engine MCP Skill
openamer
The self-improving, self-learning open-source AI agent. Background Computer-Use, A2A Swarm, Vector Memory, Plugin System, Voice, Smart Approvals - 100/100 Score. Windows-native.
Darwinian Evolver
openamer
The self-improving, self-learning open-source AI agent. Background Computer-Use, A2A Swarm, Vector Memory, Plugin System, Voice, Smart Approvals - 100/100 Score. Windows-native.
Kanban Video Orchestrator
openamer
The self-improving, self-learning open-source AI agent. Background Computer-Use, A2A Swarm, Vector Memory, Plugin System, Voice, Smart Approvals - 100/100 Score. Windows-native.
OSINT Investigation — Public Records Cross-Reference
openamer
The self-improving, self-learning open-source AI agent. Background Computer-Use, A2A Swarm, Vector Memory, Plugin System, Voice, Smart Approvals - 100/100 Score. Windows-native.
pptx-author
openamer
The self-improving, self-learning open-source AI agent. Background Computer-Use, A2A Swarm, Vector Memory, Plugin System, Voice, Smart Approvals - 100/100 Score. Windows-native.
to-issues
ayoubben18
Break a plan, spec, or PRD into independently-grabbable GitHub issues using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.
Article Illustrator
openamer
The self-improving, self-learning open-source AI agent. Background Computer-Use, A2A Swarm, Vector Memory, Plugin System, Voice, Smart Approvals - 100/100 Score. Windows-native.
Knowledge Comic Creator
openamer
The self-improving, self-learning open-source AI agent. Background Computer-Use, A2A Swarm, Vector Memory, Plugin System, Voice, Smart Approvals - 100/100 Score. Windows-native.
TRL - Transformer Reinforcement Learning
openamer
The self-improving, self-learning open-source AI agent. Background Computer-Use, A2A Swarm, Vector Memory, Plugin System, Voice, Smart Approvals - 100/100 Score. Windows-native.
request-refactor-plan
ayoubben18
Create a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue. Use when user wants to plan a refactor, create a refactoring RFC, or break a refactor into safe incremental steps.
LLaVA - Large Language and Vision Assistant
openamer
The self-improving, self-learning open-source AI agent. Background Computer-Use, A2A Swarm, Vector Memory, Plugin System, Voice, Smart Approvals - 100/100 Score. Windows-native.
erpnext-impl-jinja
OpenAEC-Foundation
"Implementation workflows and decision trees for Jinja templates in ERPNext/Frappe. Use when determining HOW to implement Print Formats, Email Templates, Portal Pages, or custom Jinja methods. Covers template type selection, context variables, styling, and V16 Chrome PDF rendering. Triggers: create print format, email template, portal page, custom jinja filter, print format styling, pdf template, invoice template, report template."
grid-sticker-generator
guanyang
A universal 4x4 grid sticker generator. uses strict visual guidelines (No Text, Transparent BG) and supports loading theme templates from resources.
erpnext-syntax-jinja
OpenAEC-Foundation
Deterministic Jinja template syntax for ERPNext/Frappe Print Formats, Email Templates, and Portal Pages
procedural-3d-scroll-sites
lavjiwellborn
How to build cinematic, "ultra 3D animated" websites where the entire 3D scene (buildings, temples, product objects, environments) is generated from code and rendered live, pixel-by-pixel, by the GPU — with the object's rotation/position/camera tied directly to scroll — instead of generating a video (Kling, Seedance, Runway, Sora, etc.), extracting it into frames, and playing the frames back as a sprite/frame-sequence animation. ALWAYS use this skill when the user asks for a "3D animated" or "3D animative" website, a scroll-driven 3D scene, an object that rotates/rises/moves as the page scrolls, a "cinematic", "immersive", or "premium feel" landing page with a 3D hero, or explicitly says they want real/procedural/code-generated 3D instead of converting AI video into frames — even if they never say "Three.js" or "WebGL" by name. Also trigger this any time the user describes the frame-extraction-from-video workflow and wants an alternative to it.
sandbase
sandbaseai
Access 2,000+ AI models and API tools through one MCP interface for inference, media generation, search, scraping, embeddings, social data, and structured retrieval. Use sandbase_discover before building custom integrations or declaring external data inaccessible; prefer an existing dedicated tool or API key when the user already has one.
orange-line-illustration
orange2ai
Generate New Yorker-style minimalist editorial illustrations — thin black ink lines on white, vast negative space, a single orange accent (#F97316) — for articles, principles, covers, and concept visuals. Use when the user asks for 配图, 插图, 封面图, editorial illustrations, concept/metaphor illustrations, article covers, 公众号配图, principle/maxim illustrations, or mentions "橙线风格" / "orange line style" / "纽约客风格插图". Works with any image generation tool that accepts text prompts.
loom-hermit-patterns
rjwalters
"This file contains detailed patterns, examples, and reference scripts for the Hermit role. It is meant to be consulted when needed, not loaded as primary instructions."
loom-architect
rjwalters
"Identifies improvement opportunities and creates proposals"
soliplex-docs
soliplex
"Soliplex documentation: how to install, configure, run, and use Soliplex -- a self-hosted RAG/AI system with a FastAPI backend, Flutter client, and terminal UI. Covers configuration (rooms, agents, completions, RAG, OIDC, skills, quizzes, AG-UI features), server setup and CLI, environment variables, secrets, Docker deployment, RAG database setup, and client usage. Use when answering questions about installing, configuring, operating, or troubleshooting Soliplex."
project-brain
Ethan-YS
Use this skill when the user explicitly asks to set up, resume, update, or hand off persistent project context for AI-assisted work. Triggers (all require an explicit user request — do NOT activate just because a brain/ folder exists): (1) The user wants to set up project-level memory ("set up project brain", "scaffold project context", "init project brain", "建项目脑"). (2) The user is in a directory containing brain/ AND explicitly asks to resume / continue / load the project / check status / "what's the state of this project". (3) The user signals window switch / context compaction ("switch windows", "context's getting full", "I'll head out", "压缩了") — write a HANDOFF before they leave. (4) The user says "update the project brain" / "let's record this" / "更新项目脑" — propose a list with reasons; user approves per item. Do NOT auto-activate during casual conversation that happens to occur inside a brain/-bearing directory. The methodology's "activation boundary" requires an explicit user request. This skill provides a folder structure (brain/), copy-able templates for multiple AI tools, and a four-workflow protocol (startup / kick-off / update / handoff). Methodology details in METHODOLOGY.md alongside this file.
agents-md
ranbot-ai
This skill should be used when the user asks to "create AGENTS.md", "update AGENTS.md", "maintain agent docs", "set up CLAUDE.md", or needs to keep agent instructions concise. Enforces research-backed
project-reflection
rapidreview-io
Run a Merv project-reflection wave across completed experiments: create the five-lens roster, fan out independent lens agents, reconcile their findings into the reflection document and change spec, coordinate independent review, and hand approved research to code consolidation. Use when the user requests reflection or workflow.status_and_next reports stale project knowledge or a reflection gate.
small-cap-growth-identifier
Geeksfino
识别A股市场中被忽视的小市值高成长公司。当用户询问小盘成长股、低市值高增长公司、被忽略的小盘股、专精特新企业、或要求筛选市值小但增长快的A股时使用此技能。