Skills by job · page 101
Coding & review skills
2,696 audited skills for coding & review: 1,958 SAFE, 585 CAUTION, 153 BLOCK. Review diffs, enforce conventions, write and refactor code in a language or framework.
Cite
Cite this page
ModelsAtlas. “Coding & review skills”. Retrieved 30 Oct 2026. https://modelsatlas.com/skills/topic/coding/page/101
igorkravcenko/snowshoe
Snowshoe personal comprehension map of a repository. After pull or catch-up: drain via work next (init / routine refresh / routine advance, then complete claimed steps). In the map PTY or when studying the map…
varuntej07/tej-stack
Sweep a codebase for nearly-duplicated abstractions that should be unified and for premature abstractions that should be inlined, then report ranked findings with file and line evidence. Use for requests to find…
DannyW618/What-skills-am-i-using
Claude Code mod: see which skills, plugins, subagents and MCP tools your conversation is using
alvseek/agent-memory-project
Coding/repo add-on overlay for the agent-memory framework — wizards, doc-gen, QA, fleet, localization, push/pull. Depends on the memory core (agent-memory-system); composes on top for coding agents.
setkernel/agent-plugins
Review the current branch for merge blockers only, using the setkernel reviewer subagent, check each reported blocker yourself, then summarize for the owner. Use when asked to review a branch or PR.
Haple/agentic-engineering
Working practices for coding agents, distilled from the free Agentic Engineering course (24 lessons built from 126 talks and articles by the people who build Claude Code, Codex and Cursor). Use for any non-trivial…
alexglonti/agentic-government
Split a job across cheaper and stronger Claude models - the manager plans and talks to the user, runner (Haiku) / researcher (Sonnet) / builder (Opus) do the work, checker (Fable) reviews it before it counts as done.…
lkdx0220/ai-code-quality-skill
INVOKE THIS SKILL when the user asks to 审查代码, 代码质量, 可维护性, AI 味, slop, 重构风险, 安全扫描, Sonar E 到 A, quality gate, ruff/mypy/radon/vulture/coverage, or before committing/refactoring a large change. Runs a unified local…
jestatsio/codebase-mentor
Explain unfamiliar code, trace execution paths, plan changes, and check onboarding docs against current source. Use for architecture questions, finding where a change belongs, or verifying codebase claims. Works with or…
yangming-666/codex-skills
Analyze game numerical/config/unpacked/runtime data and infer field relationships, evidence strength, curves, or economy specifically to design, restructure, complete, or audit an Excel/CSV/TSV workbook as the requested…
kohlarnhin/CodexPortal
Project-specific development, versioning, and release workflow for /Users/zhujiangyong/Software/codex-portal. Use whenever Codex changes this React/Tauri repository, implements account or configuration features, updates…
achandrapaul/digest
Digest your day to day work without acidity.
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,…
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…
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,…
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.
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.
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。
gvatsal60/kiro-powers
Migrate a Java project from one JDK version to another
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…
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,…
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…
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,…
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…