Agent skills for Codex CLI

Automates the generation of standardized source code documentation required for Chinese Software Copyright (Ruanzhu) applications.

Document toolkit (.docx). Create/edit documents, tracked changes, comments, formatting preservation, text extraction, for professional…

Use when `paper-review` has claims plus evidence gaps and needs the final referee-style report.

Implements type-safe Ruby 3.2 development patterns using RBS type definitions, Steep checking, and rigorous testing standards.

When to activate: Ruby performance, rack-mini-profiler, stackprof, fragment caching, Marshal serialization, GC tuning, memoization, Rails…

When to activate: Rails security, strong parameters, CSRF protect_from_forgery, SQL injection ActiveRecord, XSS raw html_safe, Rails…

Rapid Upper Limb Assessment (RULA) and Rapid Entire Body Assessment (REBA) skill for posture evaluation.

Run a standalone read-only rules compliance gate against changed files or a git ref.

Evaluate Claude Code rules in .claude/rules/.

Check code changes for .claude/rules/ compliance.

Authoring guide for Pega REST connector rules (Rule-Connect-REST) -- URL configuration, HTTP method stubs, request/response mapping…

Review UI code for Web Interface Guidelines compliance.

Run a single experiment iteration. Edit the target file, evaluate, keep or discard. Use when the user runs /ar:run or asks for one manual…

Evaluate learning progress, identify blockers, and adjust the learning plan

Generate comprehensive unit tests for Next.js 16 applications covering App Router, Server Components, Client Components, API routes, and…

Run a committed Java revision as a bounded disposable remote build for compilation, tests, analyzers, profiling, benchmarks, or toolchain…

Run reproducible DeepSWE coding-agent benchmark evaluations through OpenRouter and mini-swe-agent.

Deploy and run ML experiments on local or remote GPU servers.

Presents adaptive codebase challenge questions with multiple-choice and trace exercises.

Runs the golden re-baselining ritual — the one sanctioned way committed reference images are overwritten.

ALWAYS USE before running .NET tests or answering with a test command or flags.