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.
-
samber Bundle Developer TutorialWrites or audits a teaching tutorial for a developer product - one new concept per step, checkpoints the learner can verify and resume from, guidance that fades, troubleshooting hooks, and a demonstrable skill at the end. Use whenever the user mentions a tutorial, a build-along or hands-on guide, a "learn X by building Y" article, a workshop or lab handout, a developer course lesson, or says nobody finishes their tutorial - even if they just say "write a guide that teaches this". Do NOT use for a zero-to-first-success quickstart (samber/developer-relations-skills@developer-quickstart-guide) or a video script (samber/developer-relations-skills@technical-video-script).
-
samber Bundle Readme OptimizationAudits and rewrites a repository README so a developer who has never seen the project can tell what it is, why it beats the alternative, and run the first command inside a minute - every claim and the documented install verified against the source, the page ordered into a bail-fast funnel, badges that earn nothing pruned. Use whenever someone says "review my README", "my readme is bad", "write a README for this repo", "nobody understands what my project does", "repo first impression", "readme structure", "too many badges", or is preparing an open-source launch - even if they only call it the repo landing page. Not a profile README - use samber/developer-relations-skills@github-profile-optimization.
-
samber Bundle Developer Case StudyTurns a customer's real production deployment into a technical case study engineers believe - measured numbers tied to how they were measured, before-and-after architecture, published limitations, and cleared naming and quote approval. Use whenever the user mentions a customer case study, a technical case study, a developer adoption or success story, a reference customer, or wants to turn a user interview, migration or production rollout into published proof - even if they only say "a post about how Acme uses us". Do NOT use for a post about your own system - use samber/developer-relations-skills@engineering-blog-post; for your own project's ongoing progress use samber/developer-relations-skills@build-in-public.
-
samber Bundle Tech Press RelationsRuns press and light analyst relations for a developer-facing product - news qualification, the angle, a reporter-to-beat media map, the pitch, embargo and exclusive handling, the press page and briefing pack, and what coverage is honestly worth. Use whenever someone raises tech press relations, getting press coverage, pitching a journalist, a tech media pitch, building a media list, a press kit, an embargo briefing, announcing a funding round, a launch coverage plan, an analyst briefing, or "how do we get written about" - even if they only say they want to be in the news. Nothing to do with pull requests. Not the announcement post itself - use samber/developer-relations-skills@engineering-blog-post.
-
jawkx Skill Teach CodeTeach the user how a coding change works, then quiz them until they can explain and apply it. Use after implementing, debugging, reviewing, or discussing code when the user says "teach me," "quiz me," "grill me on this code," wants a walkthrough, or wants to learn alongside the work in the current session.
-
jawkx Skill Safe RebaseSafe git rebasing with backups and recovery. Use when Codex needs to rebase a branch, rewrite history, resolve rebase conflicts, or force-push after a rebase while preserving a rollback path (backup branch/tag or reflog).
-
jawkx Skill Gws DriveGoogle Drive: Manage files, folders, and shared drives.
-
jawkx Skill Better WritingCut AI tells from any writing. Must always apply.
-
jawkx Skill Gws SheetsGoogle Sheets: Read and write spreadsheets.
-
jawkx Bundle Codebase DesignDesign and improve deep modules with small interfaces, clean seams, strong locality, and tests through the interface. Use when designing or restructuring a module, placing a seam, reducing shallow indirection, improving testability, exploring alternative interfaces, or explicitly reviewing a codebase for architecture improvements.
-
wangxin116 Bundle HumanizerRewrite AI-sounding text so it reads like the writer without changing what it says. Use when editing or reviewing prose for AI tells: not-X-but-Y contrasts, one-line closers, staged openers, forced triads, dashes everywhere, inflated claims, sales language, stock AI words, bold labels, or filler. Based on Wikipedia's "Signs of AI writing."
-
cnfjlhj Bundle Writing Anti AI 2Use only when the user explicitly asks to remove formulaic AI-writing patterns, humanize prose, or make English or Chinese text sound more natural while preserving its meaning.
-
cnfjlhj Bundle Xhs Note Creator 2Use when the user wants Xiaohongshu note materials such as the note text, cover card, body cards, or publishing-ready assets. Do not use this for generic social copywriting or image generation when the deliverable is not a Xiaohongshu post package.
-
samber Bundle Developer SegmentationCuts a developer audience into a few named, sized and ranked segments - the two dimensions worth cutting on, a size range with a confidence tier, the user/champion/approver/buyer split inside each, a weighted score, one primary and one secondary segment, and a written anti-segment. Use whenever someone asks who their developers actually are, which developer audience to serve first, how big a language ecosystem or persona is, whether to target hobbyists or enterprise platform teams, who signs when the developer is not the buyer, or why content reaches everyone and converts nobody - even if they only say "who is this for". Not the journey map - use samber/developer-relations-skills@developer-journey-map.
-
samber Bundle Open Standards StrategyDecides how a company engages a named open standard or protocol - ignore it, consume it, certify conformance, extend it, contribute upstream, co-found a spec with peers, or drive its own as a de facto standard - plus the venue (Git-based spec, foundation, consortium, IETF/W3C/OASIS, ISO transposition), the patent-licensing mode, the conformance plan and the kill rule. Use whenever someone raises open standards participation, protocol strategy, standards body engagement, standards wars, joining versus competing with an emerging protocol, donating a specification to a neutral foundation, whether to standardize an interface at all, or a competitor's rival spec - even if they never say "standard". Not project governance - use samber/developer-relations-skills@oss-governance.
-
superxi-s Bundle Dispatch Plan ReviewSanitized SAC dispatch candidate review adapter.
-
superxi-s Bundle Dispatch Plan Risk GateSanitized SAC dispatch candidate risk-gate adapter.
-
superxi-s Bundle Change Request ReviewReview a change request using authoritative facts and supported evidence.
-
superxi-s Bundle Change Request Risk GateDeterministically assess a change request before execution.
-
robin0xfull Bundle Nono ProfileCreate, edit, validate, and test nono.sh sandbox profiles (JSON/JSONC) that scope a command's filesystem, network, and credential access. Use when the user wants to sandbox a tool/command with nono, write or update a nono profile, check a profile is valid, or test what a profile actually allows/denies.
-
luisotavio756 Skill Spec WriterConvert product ideas into structured specifications.
-
luisotavio756 Skill Product ManagerAct as a senior product manager.
-
luisotavio756 Skill Solution ArchitectAct as a staff software architect.
-
theaoproject Bundle Ao Product CaptureCapture a reusable product cutout from any accessible retailer product page and save the verified transparent image in the user's Canva AO Products folder. Use when the user supplies a product URL and wants the product prepared for later outfit compositions; do not use for purchasing products or creating the finished outfit design.
-
butfl Bundle Skills Hub全部 skills 的总索引与路由(master index & router for all local skills)。当用户问「有哪些 skill」「能做什么」「该用哪个 skill」、任务跨领域需要选型、或不确定从哪开始时使用。Triggers: 有什么skill / 用哪个skill / skill 列表 / which skill / list skills / what can you do.
-
korcanatabay-aruna Bundle Architecture GuideKullanıcı bir yazılım projesinin mimarisini, yapısını, parçalarını veya nasıl çalıştığını görmek ya da anlamak istediğinde kullan; bilgi proje belgelerinde zaten yazılı olsa bile bu skill'i çağır. Tetikleyiciler: 'mimarisini göster', 'mimariyi anlat', 'proje yapısı ne', 'bu proje nasıl çalışıyor', 'şu parçayı açıkla', 'akışı anlat', 'neden böyle tasarlanmış', 'X değişirse ne etkilenir', 'mimari harita güncel mi', 'haritayı güncelle', explain the architecture, trace this flow, what breaks if X changes. Mimariyi kanıt etiketli Türkçe anlatım ve Mermaid diyagramlarıyla öğretir. Komutlar: overview, explain [parça], trace [akış], why [karar], impact [değişiklik], check, update, save. Önce sohbette önizler, yalnızca save ile docs/architecture-map/ altına yazar. Uygulama kodunu değiştirmez; yeni sistem tasarımı, kod incelemesi veya hata ayıklama için değildir.
-
cosprints Skill Abcdx SegmentationРаскладывает платящих клиентов на сегменты A, B, C, D и X по марже на единицу и удовлетворённости, находит причинные критерии каждого сегмента и собирает план перераспределения ресурсов. Используй, когда нужно понять, на каких клиентах зарабатывает продукт, кого перестать обслуживать, какие вопросы задавать новым лидам, или когда просят «сделать ABCDX», «сегментировать базу», «понять, кто наш идеальный клиент».
-
heiets Bundle Debug ModeEvidence-driven runtime debugging loop. Generates competing hypotheses, instruments the code with session-tagged probes that stream to an isolated local log sink, has the user reproduce the bug, then confirms or rejects each hypothesis from real runtime data before fixing and removing every probe. Use when a bug's cause is not obvious from reading the code, when a fix attempt has already failed, for heisenbugs, race conditions, state corruption, "works locally but not in prod", or whenever the user says debug mode, find the root cause, or add logging to figure this out.
-
zseven-w Skill Dsh ConfigShow or set this session's DSH worker defaults (tier / effort / mode / timeout / on-off)
-
zseven-w Skill Dsh StatusShow live status of DSH worker jobs
-
zseven-w Skill Dsh PlaybookHow to dispatch well — choosing flash vs pro, writing self-contained briefs, parallelism, verifying results, and guardrails
-
kentico Bundle AgentifyAudits an Xperience by Kentico project for agentic-development readiness and reports how well it follows Kentico's AI-assisted-development best practices, flagging gaps and applying fixes on request. Use when the user wants to set up, prepare, or assess an XbyK project for AI coding assistants.
-
kentico Skill Migrate Code PageMigrates a page from a Kentico Xperience 13 project to Xperience by Kentico. Converts controllers, views, layouts, content retrieval, and all dependencies for the specified page. Use when migrating the business and presentation logic of a specific page after its Page Builder widgets have been migrated.
-
kentico Bundle Content RetrievalContent retrieval in Xperience by Kentico — best practices for retrieving content (pages, reusable content items, reusable-schema items) in code. Proactively read this before writing or modifying any code that retrieves content (IContentRetriever, ContentItemQueryBuilder), turning a Combined content selector / Page selector selection into data, or debugging slow content retrieval.
-
yuan-aaa-2333 Skill Chinese Software Copyright PackageUse when preparing a Chinese software copyright (软著) filing from an existing codebase — generating the 60-page source listing (前30页+后30页), drafting the software manual, or listing what the applicant still has to supply. Covers the page/line-count rules the registry enforces, why a partial last page gets rejected, blank-line handling, and the fields that must never be invented.
-
yuan-aaa-2333 Skill Numerical Optimization Bug PatternsUse when a numerical, geometric or combinatorial optimisation routine silently returns wrong or degenerate results, when a QUBO/penalty formulation prefers infeasible solutions, when an optimiser's later stage makes the answer worse, when a heuristic's quality must be proven rather than asserted, or when a derivation keeps contradicting what the code prints. Covers the specific defects that hide behind "it runs", the brute-force ground-truth harness, and stopping-the-derivation discipline.
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 developer-tutorial, readme-optimization, developer-case-study. 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.