Agent Skills Hub

getting-started-guide

A structured guide for novelists to navigate the seven-step writing process, from constitution and specification to planning, tasking, drafting, and quality analysis.

evolving-skill-creator

A framework for creating, iterating, and managing reusable evolving workflows that combine structured documentation with custom Python automation tools.

Extract structured data from unstructured files (PDF, PPTX, DOCX...)

Implement LlamaExtract for robust structured data extraction from PDF, DOCX, and PPTX files using Pydantic schemas.

moollm

A microworld operating system for LLM-based agent living memory, transforming filesystems into navigable rooms and code into habitable worlds.

drawnote-skill

An automated visual note and flowchart generator. Converts text or keywords into styled diagrams, mind maps, and handwritten notes exported as images without requiring file-reading permissions.

color-palette

Generate complete, accessible colour systems from a single hex. Includes 11-shade scales (50-950), semantic tokens, dark mode variants, and Tailwind v4 CSS output.

seedance-prompt-en

Expert prompt engineering for Jimeng Seedance 2.0. Generate high-quality multimodal video prompts using text, images, video references, and @ syntax for camera control, rhythm, and VFX.

k0ntext

RPI Plan Phase: Create chunk-based, dependency-aware implementation plans from research documents for structured, atomic development.

request-optimizer

An intelligent gateway that analyzes, scores, and routes user requests across 27 agents, 27 skills, and 14 MCPs to optimize Claude Code execution.

proofread

Automated, non-destructive proofreading for LaTeX and Quarto lecture files, generating quality reports for grammar, typos, and academic style.

evaluating-code-models

Evaluate code generation models using BigCode Evaluation Harness. Benchmarks include HumanEval, MBPP, and MultiPL-E with pass@k metrics for multi-language coding models.

clawhub-lovable

Accelerate clinical and healthcare app development in Lovable. Perfect for OpenClaw Clinical Hackathon participants building MVPs with PHI-safe patterns.