AI Agent Skills

Contribute Code Anonymously

When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change,"…

Multi-target output system — target abstraction, backend routing, content transforms for Codex CLI and future targets

Chrome and Firefox extension for Conventional Comments in GitHub UI.

Behavioral "black-box" testing for recommender systems

This skill should be used when writing documentation for codebases, including README files, architecture documentation, code comments, and API documentation. Use this sk…

Evidence-first debugging in 5 stages — REPRODUCE, EVIDENCE, DIAGNOSE, FIX, PROVE. Never touch code before the root cause is stated with evidence; fix the source, not the…

Scan the MRZ code of a passport and extract the firstname, lastname, passport number, nationality, date of birth, expiration date and personal numer.

🐟 Code and models for the NeurIPS 2023 paper "Generating Images with Multimodal Language Models".

Refresh a repo's documentation for a live production system — audit stale docs, rebuild a focused doc set with diagrams, update AI-agent knowledge bases, and improve cod…

Unified codebase manipulation, AI deployment, data analysis, and academic delivery engine. Absorbs 6 coding protocols + data-analysis + academic-delivery + spec-driven-d…

A non-destructive, decoupled analysis protocol for refactoring code. Generates a "Bill of Materials" report before any code is touched.

Automates the complex setup of parallel git worktrees for agentic swarms with dependency-aware wave execution.

Enforces strict, atomic commit hygiene. Splits large diffs into logical, revertible units.

Interrogates the user to build a complete design specification before writing any code. Prevents "vibe coding" failures.

Take full control of re-frame app