Skip to main content
在 Manus 中运行任何 Skill
一键导入
ever-works
GitHub 创作者资料

ever-works

按仓库查看 4 个 GitHub 仓库中的 285 个已收集 skills。

已收集 skills
285
仓库
4
更新
2026-07-19
仓库浏览

仓库与代表性 skills

account-health-review
项目管理专家

Use when you need to assess whether a client account is healthy, at risk, or slipping — before renewal, after a rough patch, or on a regular cadence — and decide what to do about it.

2026-07-19
campaign-brief
市场调研分析师与营销专员

Use when a client request is ready to become production work and you must brief creative or media — turning a vague ask into an objective, an audience, and constraints the team can build against.

2026-07-19
client-proposal-rfp
项目管理专家

Use when responding to an RFP or writing a new-business proposal — to decide whether to pursue it, shape the offer, and produce a document a client can say yes to.

2026-07-19
quarterly-business-review
市场调研分析师与营销专员

Use when preparing the quarterly review a client account faces — to report results against the objective honestly, read what worked, and set what the next quarter buys.

2026-07-19
scope-and-sow
项目管理专家

Use when you need to write or change a statement of work — turning an agreed offer into a scope, deliverables, price, and terms that both protect the client and defend the agency's margin.

2026-07-19
comp-band-review
财务和投资分析师

Use when reviewing compensation for a role, a team, or the whole population — checks where people sit against defensible bands, finds equity gaps, and produces a ranked, costed set of adjustments.

2026-07-19
employee-faq
人力资源专员

Use when building or maintaining the self-serve answers employees reach for — turns the questions people actually ask into clear, sourced FAQ entries that deflect repeat questions and stay consistent with policy.

2026-07-19
onboarding-30-60-90
人力资源专员

Use when a hire is accepted and you need to plan their first ninety days — builds a milestone plan plus a pre-day-one setup checklist so a new person ramps deliberately instead of being left to figure it out.

2026-07-19
当前展示该仓库 Top 8 / 256 个已收集 skills。
ever-works
软件开发工程师

Repo-specific guide to the Ever Works monorepo (ever-works/ever-works) — its pnpm + Turborepo layout, the per-workspace test runners (Jest vs Vitest vs Playwright), file-naming and import-alias conventions, the commit/branch model, and the real build/lint/type-check commands. Use this whenever working anywhere in this repository so changes match the codebase's actual conventions and pass CI.

2026-07-19
ever-works
软件开发工程师

Repo-specific guide to the Ever Works monorepo (ever-works/ever-works) — its pnpm + Turborepo layout, the per-workspace test runners (Jest vs Vitest vs Playwright), file-naming and import-alias conventions, the commit/branch model, and the real build/lint/type-check commands. Use this whenever working anywhere in this repository so changes match the codebase's actual conventions and pass CI.

2026-07-17
deploy-to-vercel
软件开发工程师

Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".

2026-05-02
nestjs-best-practices
软件开发工程师

NestJS best practices and architecture patterns for building production-ready applications. This skill should be used when writing, reviewing, or refactoring NestJS code to ensure proper patterns for modules, dependency injection, security, and performance.

2026-05-02
next-best-practices
软件开发工程师

Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling

2026-05-02
nodejs-express-server
软件开发工程师

Build production-ready Express.js servers with middleware, authentication, routing, and database integration. Use when creating REST APIs, managing requests/responses, implementing middleware chains, and handling server logic.

2026-05-02
playwright-best-practices
软件质量保证分析师与测试员

Use when writing Playwright tests, fixing flaky tests, debugging failures, implementing Page Object Model, configuring CI/CD, optimizing performance, mocking APIs, handling authentication or OAuth, testing accessibility (axe-core), file uploads/downloads, date/time mocking, WebSockets, geolocation, permissions, multi-tab/popup flows, mobile/responsive layouts, touch gestures, GraphQL, error handling, offline mode, multi-user collaboration, third-party services (payments, email verification), console error monitoring, global setup/teardown, test annotations (skip, fixme, slow), test tags (@smoke, @fast, @critical, filtering with --grep), project dependencies, security testing (XSS, CSRF, auth), performance budgets (Web Vitals, Lighthouse), iframes, component testing, canvas/WebGL, service workers/PWA, test coverage, i18n/localization, Electron apps, or browser extension testing. Covers E2E, component, API, visual, accessibility, security, Electron, and extension testing.

2026-05-02
shadcn
网页开发工程师

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", or "switch to --preset".

2026-05-02
当前展示该仓库 Top 8 / 25 个已收集 skills。
brand-guidelines
网页与数字界面设计师

Applies an organization's official brand colors and typography to any artifact that benefits from a consistent look-and-feel. Use when brand colors or style guidelines, visual formatting, or company design standards apply. Reads brand tokens from the project rather than assuming a fixed palette.

2026-07-17
claude-api
软件开发工程师

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST

2026-07-17
doc-maintenance
软件开发工程师

Audit README, SPEC, and PRODUCT docs against recent git history for drift and make minimal PR-ready edits. Use when asked to review docs for accuracy, after major feature merges, or on a schedule.

2026-07-17
已展示 4 / 4 个仓库
已展示全部仓库