Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Use when implementing Least Significant Bit (LSB) steganography - allows hiding images or text within other images by encoding data in the least significant bits of pixel color channels
Expert system for AgentMaestro that helps decide when and how to delegate tasks to specialized AI agents (Claude, Codex, Gemini). Use when you need to determine which agent is best suited for a task, …
World-building companion for the Aphebis platform that helps users explore, discuss, and extend fictional worlds. Use when users want to browse existing worlds/areas/locations, brainstorm world expans…
Helps manage context window efficiently by summarizing, focusing, and pruning context to stay within token limits.
Create mathematical animations using Manim (Community Edition or ManimGL). Includes best practices, examples, and rules for creating high-quality videos.
Use this skill when delegating complex autonomous tasks to Manus AI - an AI agent that can browse the web, execute code, generate files, and comple...
Generate optimized images for Marp slides using Playwright MCP with theme-matching color palettes and guideline-compliant sizes
Context-efficient report synthesis for large research corpora using evidence ledgering and harness-based iteration. **USE WHEN:** - Corpus has ≥8 files OR ≥100K characters - `finalize_research` return…
Master AI-powered natural language data exploration with Lumen AI. Use this skill when building conversational data analysis interfaces, enabling natural language queries to databases, creating custom…
Especialista en el proceso 'Hacer Magia': orquestación de agentes IA, SSE streaming y generación de assets de negocio.
Apply MAKER (Massively Decomposed Agentic Processes) to solve long sequential tasks using task decomposition, multi-agent voting, and error correction. Use when facing complex multi-step problems, seq…
Use this skill when working with UFC fighter images including downloading from multiple sources (Wikimedia, Sherdog, Bing), detecting and replacing placeholder images, handling duplicates, normalizing…
The slogan unpacked — seven readings of 'Manufacturing Intelligence'
Adds detailed alt text to markdown image embeds that are missing it. Supports both Obsidian wiki-style (![[image]]) and standard markdown () formats. Reads each image, describes its content t…
Generate variations of the Orient mascot (border collie dog with blue bandana). Use transparent=true for web/UI images. Use when asked to generate mascot, create avatar variation, make mascot image, m…
Use when building or working with Mastra agents - establishes best practices for agent development, tool creation, and workflow orchestration
Build and merge M4B audiobooks on Linux from multiple audio files or multi-part M4B sets, with chapter generation, metadata normalization, UTF-8/Russian encoding handling, and validation. Use when com…
Multi-perspective decision support using three AI agents (Scientist, Mother, Realist). Use when facing difficult decisions, trade-offs, comparing alternatives, choosing between options, or when unsure…
State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_…
Creates, analyzes, updates, and optimizes prompts using Claude 4.5 best practices, guardrails, context management, and prompt engineering patterns. Use when user asks how to write effective prompts, e…
Create and manage AI agent tasks via Manus API. Manus is an autonomous AI agent that can browse the web, use tools, and deliver complete work products.
markov-game-acset skill
Generate professional product mascot character reference sheets with a specific multi-panel layout. Use this skill when creating character design sheets, mascot documentation, brand mascot references,…
Build stateful AI agents and agentic workflows with LangGraph in Python. Covers tool-using agents with LLM-tool loops, branching workflows, conversation memory, human-in-the-loop oversight, and produc…