Coding & Development
patch-regression-test
CVE のパッチ、ライブラリや実行環境の更新、静的コード解析の指摘への対応を適用した後に、アプリの動作が変わっていないこと(無影響確認)を確かめる。不足しているテストを洗い出してテストコードを書き、パッチ前後の結果を比べ、無影響確認テスト実施レポートを出力して、きっかけの Issue にコメントとして投稿する(PR があれば PR にも Issue へのリンクを残す)。リーダーの承認の記録も Issue のコメントとして残す。アプリのソースコードの修正、環境設定、workflow の変更、コミットは行わない。ユーザーがこのスキルの名前を挙げて明示的に呼び出したときだけ使う。
$ npx skills add doikota/agent-skillsmobile-development
React Native (TypeScript), Expo, and Kotlin mobile development workflow and performance standards (synthesized from Callstack, Vercel React Native Skills, and Official Expo SkillHub packages) covering Measure-Optimize-Remeasure, FlashList, Reanimated GPU animations, React Navigation / Expo Router, Safe Areas, and Kotlin TurboModules/Expo Modules. Use when building, updating, profiling, or debugging mobile app features.
$ npx skills add jorje95/agentic-dev-skillsjikkyo
"Use when you want to run /goal on a GitHub issue and have the run
$ npx skills add gipcompany/skillsminecraft-skins
Minecraft Java skins in launchers, websites, bots and mods. Use when code uploads or changes a player's skin through Mojang's API, tells classic (Steve, 4-pixel) from slim (Alex, 3-pixel) arms, reads or converts the 64x64 and legacy 64x32 skin layouts, renders or previews a skin, or lists skins from a catalogue for players to browse and wear.
$ npx skills add MopicMP/minecraft-dev-skillsdebrief
Review the exchange that just happened — how the agent worked, where it guessed, what it got wrong, and what to carry forward — as a one-page report with a decision-path diagram. Use when the user says "/debrief", "debrief this", "review that exchange", "how did you get there", or asks for a walkthrough of the work just done.
$ npx skills add skinssong/claude_skillseas-app-stores
Build and submit iOS and Android apps with EAS to TestFlight, the App Store, or Google Play. Supports Expo and other React Native projects, plus existing native apps. Use for eas.json setup, release pipelines, signing, app versions and build numbers, store submissions, and listing metadata. For Expo websites and API routes, use eas-hosting; for adding React Native screens to a native app, use expo-brownfield.
$ npx skills add Davidelox/claude-skillsfase-slutt
Avslutter en fase eller økt i et faseinndelt prosjekt: oppdaterer logg og STATUS, skriver selvvurdering til læringsloggen, sjekker at prosjektet fortsatt virker, kjører en rask sikkerhetssjekk, committer og klargjør for /clear. Brukes når en fase er ferdig og verifisert av brukeren, eller når en økt avsluttes midt i en fase. Triggere: «fase-slutt», «avslutt fasen», «avslutt økten», «end the phase», «wrap up this session».
$ npx skills add havardd/claude-code-skillshouse-review
Review Java / Spring Boot code against the house engineering standards (REST guidelines, code smells, Effective Java, persistence pitfalls, the eight lenses incl. required tests). Works on a branch diff, a commit, uncommitted changes, a path or module, or the whole codebase. Builds and runs the tests, verifies every serious finding, handles deliberate deviations (accept + mark, or fix), reports, then offers to fix. Project conventions come from .claude/review-profile.md, built from the codebase on first use.
$ npx skills add ManishAnandProgrammer/Claude-Skillsdeep-code-review
Deep multi-agent review of a diff, branch or GitHub PR: does it solve the right problem, plus parallel correctness, design, edge-case and over-engineering passes, with calibrated findings. Use for \"deep code review\", \"review this PR / diff / branch\".
$ npx skills add abipalli/agent-skillsdatapull
使用 DataPull CLI 安全导出 MySQL、PostgreSQL 或 SQL Server 的 DDL 结构文件;适用于数据库结构快照、环境诊断、连接登记、对象范围选择和导出异常恢复。
$ npx skills add phoben/agent-skillscrud-gen
Generate full layered CRUD for a JPA entity in any Spring Boot project, following the house pattern so the result passes house-review with no findings. Generates like the golden module of the house reference application (~/.claude/skills-reference) - API interface with OpenAPI docs, controller, service, mapper, repository with a Criteria projection impl (offset or cursor paging), request/response records, filter, ErrorCodes and messages, configurable limits, and the integration test class, with optional dropdown and media endpoints. Pre-flights the entity and its migration. `/crud-gen bootstrap` copies the shared house infrastructure into a project from the reference application (error contract, wrappers, paging, limits, logging, config, security, test base, ArchUnit). Project specifics come from .claude/crud-profile.md, discovered from the codebase on first use.
$ npx skills add ManishAnandProgrammer/Claude-Skillsagent-skill-architect
Use this skill whenever the user asks for work on an agent skill
$ npx skills add SirShreder/Cline-Toolkitconfig-migrate
盘点、规划并迁移项目级或用户级的 Skills、Rules、MCP、Agents、Hooks 和 Commands 配置;适用于 Claude、Codex、Cursor、Trae、ZCode、Kimi 等开发工具之间的配置迁移。
$ npx skills add phoben/agent-skillsbroken-link-checker
Click through a website in a real browser and get a list of every link that errors or shows an empty page, with the page it is on. Use when someone wants their site checked for broken links.
$ npx skills add 20vision/broken-link-checker-skillaeo-keyword-research-and-prompt-simulation
Turn a brand's real search demand into a trackable AI-visibility prompt set. Phase 0 scopes what the client sells; Phase 1 is category-anchored keyword research (Search Console first, a seed chain with a recirculation loop, data-trap and product-fit gates, SERP clustering to pages); Phase 2 builds the prompt universe from the final keyword set (harvested question data first, labelled simulation from a 12-family prompt matrix, answer-type, KPI and stage tags, fan-out blocks, three-source placement cross-checks); Phase 3 runs a baseline and share of voice. Ships a gated workbook (Prompt Map + Keyword Map). Use when asked for keyword research for a client or brand (AEO, GEO or classic SEO keyword research), a prompt universe, prompts to track in a prompt-tracking tool, AI visibility prompt simulation, a keyword-to-prompt map, a second pass on an approved prompt set, loading prompts into a tracker without the full workbook, or to answer a reviewer's comments on a prompt workbook.
$ npx skills add savenjudesajen/seo-aeo-agent-skills-toolsundo-history
Use when adding undo, redo or a history list to an app that edits structured data (items, folders, shapes, settings of objects). Covers what is undoable, snapshot versus patch design, when to record a step, human-readable step labels, the header buttons and history dropdown, keyboard shortcuts, restoring state safely, memory limits, and large datasets.
$ npx skills add viciouskinid/Skill.mdmapping-database-schemas
Use when asked to understand, document, explain, or diagram a database schema or dataset (BigQuery, Postgres, SQLite, SQL DDL, dbt or ORM models); when asked how tables connect, what the primary and foreign keys are, what a view is built from, or for an ER diagram.
$ npx skills add Parthiv-06/skillsdoc-extraction
Build or fix a document extraction pipeline (OCR of PDFs, scans, bank statements, invoices, receipts, cheques, forms) whose numbers you can trust. Text layer first, OCR or a vision model only where needed, page-to-page context for OCR, deterministic validators that decide what is correct, one adapter per layout, and a human review step. Use when the user is extracting data from documents, choosing an OCR engine, or chasing wrong extracted values.
$ npx skills add iampreetdave-max/agent-skillsmap-basemaps-and-controls
Use when building or changing a web map application. Covers choosing basemap tile layers and attribution, adding map controls (zoom, minimap, scale, coordinate readout, geolocate, place search, right-click menu), and keeping the map fast with large datasets (thousands of markers, long paths, many labels). Library-agnostic, with Leaflet examples.
$ npx skills add viciouskinid/Skill.mdbenchmark-report
Prove an AI feature works the way frontier AI labs prove model capability - a frozen benchmark with an answer key, a held-out set, repeated runs with error bars, baselines, per-slice breakdowns, failure analysis, a ratcheted regression gate, and a "system card" style report with only qualified claims. Use whenever an AI feature is built, changed or marketed (extraction, classification, document Q&A, agents, any model or prompt swap), whenever someone asks "how accurate is it", "prove it", "benchmark", "eval", "score it", "accuracy report", "is the new version better", or wants a number for a customer, investor or landing page - even if they don't say "benchmark". Not for ordinary unit tests, load testing, or website performance audits.
$ npx skills add dro-marin/skillsfrontkar-sade
Design and build a large-scale, production-grade Next.js (App Router, 16.x) frontend from zero, the way a senior frontend engineer would. It first interviews the user about the product and every tech choice (rendering, caching, data layer, state, UI, auth, i18n/RTL, testing, CI, PWA/TWA, web vitals, Prometheus metrics, security, deployment), comparing the options and recommending one, then writes ADRs and a rendering/caching map, scaffolds the repo, and builds it in reviewed, tested vertical slices. Use it whenever someone wants to start, bootstrap, scaffold or architect a new Next.js / React frontend, gets a project brief for a take-home or live coding interview, says "build this app with Next.js", "set up a senior-level frontend", "choose a stack for this project", or asks for SSR/CSR/PPR, caching or architecture decisions on a greenfield app, even if they never say "architect".
$ npx skills add MoeeinAali/skillsrender-deploy
Deploy applications to Render by analyzing codebases, generating render.yaml Blueprints, and providing Dashboard deeplinks. Use when the user wants to deploy, host, publish, or set up their application on Render's cloud platform.
$ npx skills add Vel-Labs/Vel-Skillsscope-to-acceptance
Turn an AI-workflow or agent project brief into separate discovery and implementation milestone drafts, scope boundaries, acceptance coverage, and missing-information reports. Use when a freelancer or agency needs a reviewable scope before preparing a proposal.
$ npx skills add d0031020/agent-skillsticket-and-epic
Use before changing code, documentation, infrastructure, or live state to track work in GitHub issues and native epics, isolate each ticket in a worktree, and coordinate decision-free subtickets with dedicated workers. Also use when investigating bugs, planning an epic queue, or landing contributor changes.
$ npx skills add xu-hao/agrein