Coding & Dev Tools
Coding agent skills teach AI agents repeatable engineering workflows: reviewing pull requests, writing tests, refactoring safely, and enforcing house style. Install one SKILL.md and your agent applies the same checklist every time, whether you use Claude Code, Cursor, Codex, or another agent.
-
antreasantoniou Bundle Plus UltraRun a Byzantine 2+1 plan before consequential work and a fresh, plan-blind reality check afterward. Use when the user asks for Plus Ultra, maximum rigor, independent proposals, enforced verification, or help responding to a Plus Ultra hook gate. Claude Code can enforce the loop through the included hook adapter; on Codex and other hosts it is a convention unless separately wired and verified.
-
apparelhub-ai Bundle Apparelhub<!--
-
appraisily Bundle Design Mockup LoopUse for design-improvement workflows that turn live page screenshots into AI-generated GUI mockups. Trigger when the user asks to improve, redesign, critique, modernize, or mock up a web page using browser screenshots, visual analysis, and image generation; especially when they want a repeated loop of two desktop iterations and two mobile iterations mapped to the exact screenshot shape.
-
architect-sis Bundle Sis SkillS.I.S. - Sovereign Intelligence System
-
architektapx Bundle Hn BriefPersonalized Hacker News brief, ranked against a stored interest profile that learns from what gets opened. Use for "hn brief", "hacker news digest", "tech news for me", "what's on HN today", and for managing interests with add, forget, explore, or keep.
-
artur-antunes-1 Bundle 3dastraUse for visually directed 3D scenes or assets: concept art before modeling, reference-led refinement, and matching renders to a chosen image. Also applies to image-first Blender and real-time 3D workflows. Not for unrelated 2D UI work or purely technical 3D fixes.
-
ashoknaik009 Skill Project MemoryTicket-aware project memory for multi-developer teams. Tracks implemented features, detects duplicates before coding, maps features to files. Use when implementing tickets or checking existing work. Triggers: '/execute', '/init-memory', 'implement ticket', 'what features exist', 'has this been built'.
Audited -
avijit07x Skill Cdb ScanMap this codebase into project memory — a code graph of every symbol and how they connect, plus a written profile of stack, layout, conventions and workflows. Re-run any time to refresh both in place. Use when memory is newly installed on an existing project, or when the project has changed enough that the stored map is stale.
Audited -
avinashricky211 Skill WritUse this skill whenever writing or revising prose meant to read as natural human writing — essays, articles, blog posts, book chapters, emails, reports, LinkedIn posts, or any long-form text where the person wants it to not sound AI-generated. Also trigger if the user says things like 'make this sound more human', 'remove AI tells', 'don't write like AI', 'this sounds like ChatGPT', or references Wikipedia's Signs of AI Writing guide. Apply this skill's checklist as a final pass on any substantial written output before delivering it — not just when explicitly asked.
Audited -
ayden7399 Bundle No More FomoUse when user says 'fomo', 'digest', 'daily', 'AI news', 'today's papers', 'what's new in AI', 'catch up', or on a scheduled daily cron trigger.
-
ayueh0102 Bundle Luo Ming Color Science回答色彩科學/色度學問題時使用。涵蓋 CIE 色度學、XYZ 三刺激值、光源與色溫、色彩量測儀器與不確定度、色視覺與對立色理論、心理物理學實驗設計、色序系統(Munsell/NCS/Ostwald/DIN)、色差公式(CIELAB/CMC/CIE94/CIEDE2000)、影像色差與 S-CIELAB、同色異譜、色貌模型(CIECAM02/CAM16)、色適應變換(CAT02)、演色性(CRI/Rf/Rg)。觸發語如「色差公式」「CIEDE2000」「CIECAM02」「Munsell」「NCS」「色貌」「色適應」「演色性」「同色異譜」「亮度跟明度差在哪」「幫我複習色彩學」,或提到羅明(Ming Ronnier Luo)教授的色彩學課程。
-
azedl Skill Learn AnythingTailored learning coach for deeply learning a subject, skill, tool, or discipline. Use only when the user explicitly invokes `learn-anything` for guided learning.
Audited -
bakoware Bundle Claude Dependency MapperMap a project's dependency graph. Generates an Obsidian vault (obsidian-graph/) for human visualization and, for medium/large codebases, a compact PROJECT_MAP.md for token-efficient AI navigation. Decides the route by file count, wires up CLAUDE.md, adds .gitignore entries so the graphs are not committed, and installs a PostToolUse hook that auto-refreshes the graphs on source edits. Use when the user runs /claude-dependency-mapper or asks to set up / refresh the project dependency graph.
-
barinfo Bundle Camelot SkillCamelot: No-Mercy Code Review
-
barinfo Bundle Hyw何意味 — 当 AI 自己做出令人费解、无语或逆天的产物时,自动跳出冷静反问「何意味?」,摊开动机、逐条自省可疑点,然后把决策权完整交还给你。是 grilling 的反向调用(grilling 审你给的,HYW 审 AI 自己给的),与 NEVERMIND 互为梗系姊妹(无所谓 vs 这合理吗)。不审代码(那是 Camelot),不驱动递归(那是 Ouroboros)。用户可手动喊「何意味 / 和依未 / hyw / ? / ?」召唤它对最近一次输出执行三件事。
-
barinfo Bundle Nevermind用一张"尴尬黄豆追美元"(😅💵⚠️)的语气,把你今天烧掉的 AI token 结算成一笔"赛博功德",再云淡风轻地补一句 NEVERMIND。数只读 tokens.ci 能读到的本地 AI 客户端用量(强关联 tokens.ci,不另起本地假账);读不到则明说、走尴尬自报或纯梗收尾。输出俏皮、肉疼、又释然的播报。触发词:nevermind、赛博功德、今天烧了多少、token 结算、用了多少额度、AI 账单、钱又没了、功德结算。
-
beamuswayne Bundle Weirdo Tv神人TV (WeirdoTV) — 互联网神人人格蒸馏器。召唤泽连斯基、米莱、胡锡进、孙笑川、 川普、罗翔、马斯克等二十余位神人,模拟其极端言论风格,用于玩抽象的网民必备技能。 支持单人召唤、随机神人、神人辩论、神人点评、神人会议五种模式。 Use when asked to "召唤神人", "/weirdo-tv", "神人说", "让[人名]评价", or any request to channel internet legends, meme lords, or controversial figures.
-
beamuswayne Bundle Simp追爱军师 — 帮你用最纯情的话把心上人追到手 | Love Strategist — win over your crush with the most sincere words
-
tomevault-io Bundle Howells Arc Testing<tool_restrictions>
-
tomevault-io Bundle AmberAmber docs index. Use when building or porting Minecraft mods that use the Amber multiloader library (unified APIs for Fabric/Forge/NeoForge), or when you need quick links to Amber systems (registry, events, networking, commands, config). Use when this capability is needed.
-
tomevault-io Bundle Parsh FilesHow to use @parshjs/files for typed JSON file storage in a parsh CLI. Use when adding persistent config or state to a CLI (credentials, user prefs, cached state) — anything written as JSON on disk. Pairs with the parsh skill — read that first if you don't know how parsh CLIs are structured. Use when this capability is needed.
-
tomevault-io Bundle Indoor47 Memfun AskAsk
-
tomevault-io Bundle Indragiek Ghfs Ghfslat.md Authoring Guide
-
tomevault-io Bundle Barta DevelopmentIntegrate Barta package for sending SMS via Bangladeshi gateways. Use when this capability is needed.
-
tomevault-io Bundle Ivy Dotfiles UpdateUpdate: Morning Maintenance
-
tomevault-io Bundle Jkitchin Skillz TddTest-Driven Development (TDD) Skill
-
tomevault-io Bundle Jlevy Repren Repren<!-- DO NOT EDIT: Generated by tbd setup (format=f04).
-
tomevault-io Bundle ChatUse when starting a new project with llmring, building an application using LLMs, making basic chat completions, or sending messages to OpenAI, Anthropic, Google, or Ollama - covers lockfile creation (MANDATORY first step), semantic alias usage, unified interface for all providers with consistent message structure and response handling
-
tomevault-io Bundle DistillExtract an Allium specification from an existing codebase. Use when the user has existing code and wants to distil behaviour into a spec, reverse engineer a specification from implementation, generate a spec from code, turn implementation into a behavioural specification, or document what a codebase does in Allium terms. Use when this capability is needed.
-
tomevault-io Bundle Karanchawla Vvm VvmVVM Skill
-
tomevault-io Bundle Livewire DevelopmentVendor-overridden Livewire skill Use when this capability is needed.
-
tomevault-io Bundle Check CoverageEnsure comprehensive test coverage for a CLI handler. Use when adding a new command or auditing existing handler coverage. Use when this capability is needed.
-
tomevault-io Bundle Lestrrat Go Jwx Jwxjwx-companion-bulk
-
tomevault-io Bundle Learn Crossover当用户学习或接触一个新概念/新技术/新算法/新领域时使用(尤其感到陌生或有点难时)。用「跨界原则」拿用户已掌握的知识快速撬动新知识——指出他其实已经学过的同一个东西(换了名字)、结构同构的旧知识、能解释新知识的已有知识,并点出新概念体现的跨领域元知识模式。让「学新东西」变成「发现你已经会了一半」。触发场景:学 X、接触 X、这个好难、X 是什么、帮我理解 X。 Use when this capability is needed.
-
tomevault-io Bundle Self Motivation Corruption System系统性压力,机制驱动,持续输出 Use when this capability is needed.
-
tomevault-io Bundle JournalSupport reflection and journaling with prompts and structure. Use when the user wants to journal, reflect on their day, practice gratitude, or get writing prompts for personal reflection. Use when this capability is needed.
Frequently asked questions
What are Coding & Dev Tools agent skills?
Coding agent skills teach AI agents repeatable engineering workflows: reviewing pull requests, writing tests, refactoring safely, and enforcing house style. Install one SKILL.md and your agent applies the same checklist every time, whether you use Claude Code, Cursor, Codex, or another agent.
Which Coding & Dev Tools skills are most installed?
Popular Coding & Dev Tools skills on SkillMD right now include plus-ultra, apparelhub, design-mockup-loop. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Coding & Dev Tools skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.