Showing 32281–32310 of 77204 skills
Use from a consuming repository to file a gzkit defect or enhancement at tvproductions/gzkit.
tvproductions/gzkit
Use before implementing a GHI, OBPI or draft when direction or scope is unsure; renders a reasoning scaffold.
tvproductions/gzkit
Use after an OBPI's implementation, before reconcile, to review its code for reuse, quality and efficiency.
tvproductions/gzkit
Use to reconcile OBPI briefs and the ADR table against the ledger and report what only the operator can resolve.
tvproductions/gzkit
Use to sweep the governance shape, trace a node's lineage, diff against the last sweep, or read its blast radius.
tvproductions/gzkit
Use to run a GHI-driven patch release, or to publish a minor release handed over by gz closeout.
tvproductions/gzkit
Use to create an ADR, a pool ADR included, recording architecture intent and lane scope.
tvproductions/gzkit
Use when exiting plan mode or before implementing to verify ADR intent, OBPI scope and plan agree.
tvproductions/gzkit
Use to define or revise project-level intent as a PRD before ADR planning.
tvproductions/gzkit
Use after gz-pythonic-pattern-detect marks a candidate applied, to capture the rewrite's before/after proof.
tvproductions/gzkit
Use when gates are green but code still looks Java-flavored, to surface Pythonic refactor candidates.
tvproductions/gzkit
Use to review a skill by re-verifying its claims against the code it wields, then correct it and move last_reviewed.
tvproductions/gzkit
Use for status inquiries, blockers and next actions; reports workflow fronts with ADR lifecycle and gates.
tvproductions/gzkit
Use for a tech-debt review of files, paths, ADRs, OBPIs or the repo; produces a prioritized report.
tvproductions/gzkit
Use for repository hygiene; reports governance maintenance findings and regenerates surfaces with --fix.
tvproductions/gzkit
Use to check manifest, ledger, document or surface validity against schema rules.
tvproductions/gzkit
Use to create, attach issues to, move, change, add evidence to or record an issue close on a work package (WP-<NN>-<slug>) through gz wp.
tvproductions/gzkit
当任务需要实现、修改、重构或评审产品前端的可见界面、交互行为、前端状态与数据流、组件或样式组织时主动使用,无需用户点名;也用于这些前端行为的测试与验证策略。适用于页面、表单、列表、弹窗、响应式、样式与动效实现和前端代码归属调整。不用于视觉风格、配色、排版与设计方向这类设计判断,也不用于纯后端、构建部署、依赖升级、只修导入路径的机械改动、仅操作现有网站、仅生成设计图片或讨论本 Skill;用户明确要求不使用时不触发。
oil-oil/oil-frontend
Mobile development across SwiftUI, Jetpack Compose, React Native (Expo) and Flutter: scaffolding, feature architecture, static performance checks and store listings. Use when building, optimizing or shipping a mobile app.
borghei/Claude-Skills
Plan a flag-gated rollout: classify the flag, pick a rollout shape, set kill-switch thresholds and retire the flag. Use when planning a phased rollout, a kill switch, a holdout or a cleanup of old flags.
borghei/Claude-Skills
Build applications with Univer Office SDK, covering the Web SDK (browser Office editors, headless Sheets and Docs in Node), Server SDK (self-hosted OT collaboration, storage, auth, Office import/export), AI SDK (agent-operated Office CLIs, reviewable Worktrees), and Binding SDK (plain HTML pages bound to live Sheet data). Use when starting or designing any Univer-based app or choosing Univer packages, including when the user describes a spreadsheet, document, collaboration, or AI-office need without naming a Univer package.
dream-num/skills
프로젝트 루트에 DESIGN.md를 부트스트랩 — 실제 기업 레퍼런스 중 컨텍스트 매칭으로 추천하고 선택된 레퍼런스의 톤&매너를 보존한 variation을 생성. DESIGN.md 부재 상태에서의 UI 작업 또는 '디자인 시스템 세팅', 'set up our design system', 「デザインシステムを作って」, 「建立設計系統」류의 요청에 트리거. CLAUDE.md / AGENTS.md / Cursor rule shim도 함께 설치.
kwakseongjae/oh-my-design
선택된 reference brand의 라이브 사이트에서 디자인 컨텍스트(토큰·구조·visual reference)를 캡쳐. brand homepage 패칭, 컴퓨티드 스타일 inspect, 로고/스크린샷을 assets/_reference/<id>/ 로 가져와 attribution.md + LICENSE-NOTE.md와 함께 저장. '뱅크샐러드 에셋 가져와줘', 'X 사이트 패칭', 'X reference 캡쳐', 'X 라이브 스타일 추출', '브랜드 자료 받아와' 류 요청에 트리거. omd:init 직후 또는 omd:harness 중간에 호출 가능. DESIGN.md는 이 스킬이 만들지 않음 (omd:init 책임).
kwakseongjae/oh-my-design
Робот агента Personal Corp. Агент делает себе голову робота из набора деталей, хранит её в штабе в stack/avatars.json и кладёт в штаб страницу avatar/robot.html, где робот стоит за партой своего штаба и вокруг видны отделы, без сервера и интернета. На уроке по ссылке входа с экрана урока робот входит в живой класс и горит маячком, пока агент работает. Триггеры /avatar, /avatar <ссылка входа>, сделай себе аватар, покажи своего робота, приди на урок.
serejaris/personal-corp-os
Production-ready CI/CD configurations for Playwright — GitHub Actions, GitLab CI, CircleCI, Azure DevOps, Jenkins, Docker, parallel sharding, reporting, code coverage, and global setup/teardown.
testdino-hq/playwright-skill
Battle-tested Playwright patterns for writing and debugging reliable E2E, API, component, visual, accessibility, and security tests. Use when you need locator strategy, assertions, fixtures, network mocking, auth flows, trace debugging, or framework recipes for React, Next.js, Vue, and Angular. TypeScript and JavaScript.
testdino-hq/playwright-skill
For frontend engineers authoring UI — how to make components reliably locatable by tests and AI agents. Covers the official Playwright locator priority, semantic/accessible markup first, and how to add valid, unique, stable `data-testid` attributes (naming convention, uniqueness in lists, stability rules) for React, Vue, Angular, and Svelte. Use when writing or reviewing components, or when an agent needs durable locators.
testdino-hq/playwright-skill
QA engineering workflows on top of Playwright. Use when a QA engineer asks to design test cases from a ticket, PRD or acceptance criteria, decide what to automate, write a bug report from a failing test or trace, convert manual test cases (TestRail, Xray, CSV) into Playwright specs with case-ID traceability, or review Playwright test code and pull requests.
testdino-hq/playwright-skill
Stage and commit changes using Conventional Commits
BuddiesOfBudgie/docs
Inspect ADR health read-only; optionally select one ADR with --adr N.
arbiterForge/codeArbiter