Agent Skills Hub

paper-figure

Generate publication-quality figures, charts, and LaTeX tables from experiment data for academic papers.

session-investigator

Analyze and debug fast-agent session histories, tool execution logs, and conversation timing to resolve performance bottlenecks, tool loops, and unexpected session terminations.

z-card-image

Automated text-to-image rendering engine for social media posts, article covers, and long-form threads. Supports X-style, WeChat, and poster templates with high-precision text formatting and highlights.

deep-reading-analyst

A comprehensive framework for deep analysis of articles, papers, and long-form content using 10+ thinking models like SCQA, First Principles, and Systems Thinking.

simplemem-skill

Persistent, semantic long-term memory for AI agents. Save, query, and retrieve cross-session dialogues, decisions, and multimodal context using semantic compression.

workflow-execute-plans

Execute implementation plans in small, verifiable batches with pause-for-feedback checkpoints to prevent drift and ensure code quality.

make-slide

Generate professional, single-file HTML presentations with speaker notes. Supports themes, layouts, and PPTX export for decks, talks, and pitches.

pixel-art

Generate bespoke pixel art SVG illustrations for your documentation, READMEs, and presentations. Perfect for character sprites, chat dialogue visualizations, and custom branding.

research-review

Get deep, critical, NeurIPS/ICML-style peer reviews of your research, paper drafts, and experimental setups using external LLMs via Codex MCP.

voice-extractor

Extract and document authentic writing voice from samples. Create comprehensive voice guides for AI training, ghostwriting, and brand consistency.

subagent-driven-development

Execute implementation plans using isolated subagents for each task, featuring a rigorous two-stage review process for spec compliance and code quality.

llmfit-advisor

Analyze local system hardware (RAM, CPU, GPU/VRAM) to receive expert recommendations for optimized local LLM models, quantization settings, and performance estimates.