Skills by job · page 79
Coding & review skills
2,081 audited skills for coding & review: 1,590 SAFE, 386 CAUTION, 105 BLOCK. Review diffs, enforce conventions, write and refactor code in a language or framework.
Cite
Cite this page
ModelsAtlas. “Coding & review skills”. Retrieved 29 Oct 2026. https://modelsatlas.com/skills/topic/coding/page/79
everkeep
m4bwav/everkeep
Keep the repositories and packages the user already owns healthy: one repo by default, a saved selection, or the whole account. Triages open pull requests (merges safe bot bumps past a cooldown, fixes failing ones,…
frontend-god
muhamadhafis/frontend-god
Senior Frontend & Design Engineer skill for React 19, Next.js & Vite. Crafts non-AI-slop interfaces, B2B cockpit high-density dashboards, Tailwind CSS v4 (@theme) & shadcn/ui integrations, compound components, optical…
github-manager-skills
basitalisandhu/github-manager-skills
Build a blameless, cited postmortem timeline and document skeleton from a saved incident issue export, ordering label changes, comments, cross-references, PR merges and the close by time, deriving detected,…
gpt-webui-skills
AVANT-ICONIC/gpt-webui-skills
Autonomous ChatGPT WebUI development that implements an agreed specification, verifies the result, resumes safely across per-turn tool limits, and hands unfinished local work to a coding agent without losing context.
greenroom
PapiScholz/greenroom
Keep hundreds of Claude Code skills off the context window without ever losing them: hidden skills, one gate per family, a session map, zero maintenance.
hekouwang-harness-check-skill
huiyonghkw/hekouwang-harness-check-skill
当用户要求检查、体检、回归、验收、解释或诊断会勇禾口王内容工作流 Harness,或维护、移植、打包、开源这个 Harness 检查器 Skill 时使用。统一调用 verify.sh 及治理、Hook、安全门、Episode 等检查,分别报告本地、暂存区、CI 与真实宿主边界。具体 EP 的文章、实验选型和渠道交付预检由仓内 hekouwang-precheck 负责。
kiro-powers
gvatsal60/kiro-powers
Migrate a Java project from one JDK version to another
KiSYSTEM
Pr1m4lc0d3/KiSYSTEM
Use before editing, refactoring, moving, or deleting existing code — to keep the change contained to its bounded unit and prevent collateral damage to surrounding services and functions. Use whenever a change touches a…
lowkey
omlahore/lowkey
Makes the agent write like a person in the conversation, not an assistant. Mirrors the thread (case, punctuation, length, emoji), drops AI tells (em dashes, "Great question", "I hope this helps", headers in chat,…
my-skills
hu3rror/my-skills
Debug or verify frontend behavior by driving the live page with browser_* tools. Use when the user reports: broken login or auth, JWT/session issues, failed/401/403/CORS requests, form or button not working, blank…
NoShitUi-skill
wzj1228516103/NoShitUi-skill
Discover, compare, and integrate open-source UI libraries, components, templates, and design references into web interfaces. Use when a user asks for UI inspiration, a reusable component strategy, a UI stack comparison,…
open-code-skills
TrueImmortal82/open-code-skills
Verify a library's API against the source you actually have installed, rather than against memory or documentation. Use when calling a package whose exact signature matters; when a version may have changed an API, a…
panda-agent-toolkit
flyingpurpleleaf/panda-agent-toolkit
panda-agent-toolkit is a structured, engineering-focused agent toolkit repository shaped by ten years of real-world development experience.
perxel-social-kit
perxel/perxel-social-kit
Make social media images and short videos (reels) in every size from React templates, and the images and clips a site's blog posts need (visual recipes: capture, record, compose), with @perxel/social-kit. Use when the…
play-closed-test-recruitment
peikuo/play-closed-test-recruitment
Recruit and coordinate Google Play closed-test participants and one-for-one exchanges. Verify group membership, Play eligibility, real installations and feedback, and maintain evidence records. Use for tester…
project-kickstart
motalim-ai/project-kickstart
Starts any new software project the right way with an AI agent. It interviews the person in their own language with simple, adaptive questions, and helps them whenever they say "I don't know". It then writes the…
prompt-cosplay
yangyangnovelist-hub/prompt-cosplay
Validate a release before publication. Use when a user asks whether a package is ready to ship.
session-handoff-kit
alapha888/session-handoff-kit
Use this skill when context usage approaches capacity (>60%), before running /clear or /compact, when switching tasks, or when ending a coding session across Claude Code, Cursor, or Codex. Produces a structured handoff…
simplify-code
linkxzhou/simplify-code
Simplify, clean up, and refactor existing code in any mainstream language (JS/TS, Python, Java, Go, Rust, C#, C/C++, PHP, SQL, Bash, and more) while preserving behavior and public APIs. Use whenever the user asks to…
skillforge
mkd-hika/skillforge
Grounded training-data pipeline and evaluation tools for agent-skill selection and abstention. CPU pipeline implemented; model training pending.
specmetry
XKHoshizora/specmetry
Local-first project oversight for AI coding agents. Track requirements, verify progress, and see what's left to ship.
three-ws-skill-license
nirholas/three-ws-skill-license
On-chain skill licenses for agents — each purchased skill is a 1/1 SPL NFT plus a deterministic SkillLicense PDA. Mint, verify, and read trustless skill access in one import, no database required.
tried-and-true-ai
zlgan-spec/tried-and-true-ai
AI resources I've actually used and found helpful, curated from a non-technical background. 非技术背景亲测好用的 AI 资源。
ue5-mobile-shipping
alexglonti/ue5-mobile-shipping
Ship an Unreal Engine 5 game to Android and iOS as a small team (one or two people) with a Windows build machine and a Mac mini, coordinated by Claude agents - build, verify, install, store features, Android-to-iOS…