An agent skill that scans web projects for common AI-generated design patterns and suggests or applies fixes to remove them.

A taxonomy for open source cryptocurrency, blockchain, and decentralized ecosystems

Use when reviewing a PR, API, IPC channel, endpoint, parameter, type, config, or architectural extension point that adds or expands shared surface area, especially when consumers are absent, exports are unused or speculative, existing consumers are hack-heavy, forward compatibility is claimed, or multiple similar APIs may express one demand.

A local-first visual prompt archive with installable agent skills for generating art direction and retrieving traceable prompt-image references.

A Practical and Efficient NCBI Taxonomy Toolkit, also supports creating NCBI-style taxdump files for custom taxonomies like GTDB/ICTV

Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges

A universal, industry-neutral taxonomy of cognitive core skills (perception, memory, reasoning, planning, action, verification, learning, governance) for LLMs, SLMs, AI agents, and world models — with schemas, 159 skill cards, benchmarks, and CI.

LLM-powered toolkit for skill analysis, AI interviews, resume scoring, and job structuring. Automates professional skill taxonomy and interview processes with adaptive difficulty.

A collection of 9 markdown playbooks that package Shopify agency expertise—catalog cleanup, SEO metadata, structured data, redirects, and landing pages—as installable Claude Code agent skills.

Codex skill for curating GitHub starred repositories into safe, meaningful GitHub Stars Lists.

Draft and stress-test a VISION.md for a repository, then iterate with the author on an interactive review board until approved. Use on /vision or when asked to create or refine a project vision.

Search oip-visual-v2 for traceable prompt-image pairs and open local result galleries. Use when finding, inspecting, comparing, browsing, or copying real image-generation references or exact source prompts. After references are selected, adapt them into a derived bilingual prompt when requested; use img-gen-taste first when the visual direction is still unclear.