Review current code changes for reuse, code quality, and efficiency, then fix issues directly. Use when the user asks for a cleanup pass on changed files, wants the current diff reviewed before finishing, or asks for duplication, maintainability, or performance issues in recent edits to be identified and cleaned up.
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a super review, deep code quality audit, or especially harsh maintainability review.
Use when the user says "yeet" or "/yeet" to quickly stage, review, commit, and push all changes with a provided message
My personal developer workflows, packaged for both Claude Code and Codex.
The root skills/ directory is the source of truth. The Claude Code and Codex
plugin metadata at the repo root expose those skills under the devflows
namespace.
/yeet "message" or /yeet to auto-generate.This repo can be installed directly with the Agent Skills CLI:
npx skills add GeorgeNance/agent-skills --list
npx skills add GeorgeNance/agent-skills -g -a codex --skill '*' -y
Use the GitHub source when you want tracked updates:
npx skills update -g -y
For local development, validate the checkout before publishing changes:
npx skills add . --list
devflows_code_simplifier at .codex/agents/devflows_code_simplifier.tomlThe cleanup workflow uses a project-scoped Codex custom agent plus the plugin skill.
Paste this into Claude Code:
Follow the setup instructions in this file exactly and complete the setup end to end:
https://raw.githubusercontent.com/GeorgeNance/agent-skills/refs/heads/master/instructions.md
Use the `Claude Code` section. Make sure you refresh the marketplace metadata before installing. When you're done, briefly confirm exactly what was installed.
Paste this into Codex:
Follow the setup instructions in this file exactly and complete the setup end to end:
https://raw.githubusercontent.com/GeorgeNance/agent-skills/refs/heads/master/instructions.md
Use the `Codex` section. If a command needs approval because it writes to my home directory, request approval and continue. When you're done, briefly confirm exactly what was installed.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub georgenance/agent-skills --plugin devflowsReliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Design fluency for frontend development. 1 skill with 23 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls