MARUCIE
- 137 skills
- 0 followers
- 4 hours ago last updated
- ▌ Complex Doc RAG 2 · marucieUse when building a RAG pipeline that ingests PDFs, Excel, CSV, or images — especially when debugging silent data loss, choosing between OCR tools, or handling edge cases like scanned pages, merged cells, or embedded charts.
- ▌ Observability 2 · marucieUse when adding structured logging, instrumenting Prometheus metrics, wiring up distributed tracing with OpenTelemetry, writing alerting rules, defining SLOs and error budgets, or building a Grafana golden-signals dashboard.
- ▌ Containerization 2 · marucieUse when writing Dockerfiles, setting up docker-compose for local dev, configuring Kubernetes resources (Deployment, Service, Ingress, HPA), sizing pod resource limits, or packaging a service with Helm.
- ▌ Systematic Debugging 2 · marucieUse when encountering a bug, test failure, crash, or unexpected behavior. Enforces root-cause investigation before any fix attempt. NOT for writing new features. Trigger: bug, error, failing test, broken, unexpected, crash, regression.
- ▌ Test Driven Development 2 · marucieUse when implementing any feature or bugfix, before writing implementation code
- ▌ Design Taste Frontend 2 · marucieUse for opinionated UI engineering standards: variance/motion/density baselines, component architecture rules, CSS hardware acceleration. Best for refining or auditing existing UI. NOT for greenfield builds (use frontend-design). NOT for design thinking (use qiaomu-design-advisor).
- ▌ Systematic Debugging 3 · marucieUse when encountering a bug, test failure, crash, or unexpected behavior. Enforces root-cause investigation before any fix attempt. NOT for writing new features. Trigger: bug, error, failing test, broken, unexpected, crash, regression.
- ▌ Bigdata Machine Learning · marucieMachine learning toolkit for big data teams. Includes scikit-learn, PyTorch Lightning, Transformers, SHAP for model training, deployment, and interpretation. Use when building ML pipelines, training models, or explaining predictions.
- ▌ Bigdata Visualization · marucieData visualization toolkit for big data teams. Includes Matplotlib, Seaborn, Plotly for static and interactive charts. Use when creating dashboards, reports, or exploring data visually.
- ▌ SQL Queries · marucieGenerate SQL queries from natural language descriptions. Supports BigQuery, PostgreSQL, MySQL, and other dialects. Reads database schemas from uploaded diagrams or documentation. Use when writing SQL, building data reports, exploring databases, or translating business questions into queries.
- ▌ Bigdata Processing · marucieCore big data processing toolkit for data teams. Includes Polars, Dask, Vaex for large-scale data processing, ETL pipelines, and distributed computing. Use when working with datasets larger than memory, building data pipelines, or optimizing data processing performance.
- ▌ Prototype · marucieRapid prototyping workflow. Skips normal standards to quickly validate a game concept or mechanic. Produces throwaway code and a structured prototype report.
- ▌ Visual Style · marucieCreate, extract, and apply portable visual design systems via visual-style.md files. Use when: (1) Creating a visual-style.md design system from scratch, (2) Extracting a visual style from a website URL, video, or PDF brand guide, (3) Applying a visual style to HeyGen videos, HTML slides, Figma, or paper.design, (4) Browsing the gallery of pre-built visual styles (Swiss, Saul Bass, Game Boy, etc.), (5) User mentions "visual style", "design system", "brand style", or "style guide", (6) Styling a HeyGen video with a consistent design language.
- ▌ Paper Write · marucie本科与硕士学位论文全流程撰写辅助。支持大纲审核（理工科/文科）、结构仿写（通用章节/实验章节/绪论/摘要）、参考文献获取、融合、润色、缩写、扩写、防 AIGC、中英互译、结构化信息提取。当用户提到论文撰写、大纲审核、论文章节仿写、参考文献、论文润色、防 AIGC、论文翻译时使用。
- ▌ Design Review · marucieReviews a game design document for completeness, internal consistency, implementability, and adherence to project design standards. Run this before handing a design document to programmers.
- ▌ Design System · marucieGuided, section-by-section GDD authoring for a single game system. Gathers context from existing docs, walks through each required section collaboratively, cross-references dependencies, and writes incrementally to file.
- ▌ Search First · marucieResearch-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Invokes the researcher agent.
- ▌ Vibe Debug · marucieAutomated test-driven debugging pipeline. Replaces human-in-the-loop 'still broken' prompting with: write reproducing test -> self-loop with test feedback -> exit when green.
- ▌ Database Designer · marucieDatabase schema design, migration planning, and RLS policies. Use when: schema design, 'design database', table relationships, row-level security. NOT for: query optimization (use postgresql-best-practices).
- ▌ Metrics Dashboard · marucieDefine and design a product metrics dashboard with key metrics, data sources, visualization types, and alert thresholds. Use when creating a metrics dashboard, defining KPIs, setting up product analytics, or building a data monitoring plan.
- ▌ North Star Metric · marucieDefine a North Star Metric and 3-5 supporting input metrics that form a metrics constellation. Classify the business game (Attention, Transaction, Productivity) and validate against 7 criteria for an effective North Star. Use when choosing a North Star Metric, setting up a metrics framework, learning about the North Star Framework, or deciding what to measure.
- ▌ Deep Research · marucieUse when task requires multi-step information synthesis across sources, not answerable in one search. Runs 7-stage research pipeline with sub-agents. NOT for quick lookups or single-source questions. Trigger: research, comprehensive analysis, literature review.
- ▌ Tavily Search · marucieTavily API ile güvenli web arama ve URL içerik çıkarma yap. Use when: hızlı web araştırması, kaynaklı sonuç toplama, belirli URL'lerden metin çekme ve özetleme gerektiğinde.
- ▌ AWS · marucieUse when writing boto3 or AWS SDK v3 code — configuring IAM auth, reading/writing S3, designing DynamoDB access patterns, writing Lambda handlers, processing SQS batches, or troubleshooting credential and throttling errors.
- ▌ Frontend Design · marucieUse when building web UI from scratch: components, pages, landing pages, dashboards, HTML/CSS layouts, posters. Produces production-grade, aesthetically intentional code. NOT for backend logic. NOT for refactoring existing UI without redesign intent (use design-taste-frontend).
- ▌ Ljg Paper Flow · maruciePaper workflow: read papers + cast cards in one go. Takes one or more arxiv links, paper URLs, PDFs, or paper names. For each paper, runs ljg-paper (generates org analysis) then ljg-card -l (generates long reading card PNG). Use when user says '论文流', 'paper flow', '读论文并做卡片', '论文卡片', or provides multiple papers wanting both analysis and cards.
- ▌ Caching · marucieUse when adding or debugging caching in a service — choosing a cache strategy, designing TTLs, preventing stampedes, reasoning about invalidation, or configuring HTTP Cache-Control headers.
- ▌ Lean Canvas · marucieUse when exploring startup hypotheses, testing business model viability, or comparing venture ideas on a single page. Trigger: user says 'lean canvas', 'business model', 'startup hypothesis', 'one-page business plan', or when validating whether an idea is worth pursuing before building anything.
- ▌ Redis · marucieUse when choosing a Redis data structure for a use case, implementing caching or rate limiting, building pub/sub or Streams-based real-time messaging, or writing atomic operations like distributed locks.
- ▌ Pm Cmd Setup Metrics · marucieDesign a product metrics dashboard with North Star metric, input metrics, health metrics, and alert thresholds
- ▌
- ▌ Web Multi Search · marucieSearch the web using multiple search engines simultaneously (Bing, Yahoo, Startpage, Aol, Ask) via async-search-scraper, iterating through result pages.
- ▌ Agentex · marucieUse when building, wiring, or debugging an Agentex agent — choosing agent type, configuring acp.py and manifest.yaml, using adk.messages or adk.state, or resolving Windows-specific setup issues.
- ▌ CI CD · marucieUse when setting up or debugging GitHub Actions pipelines — adding quality gates, configuring OIDC cloud auth, building matrix test runs, publishing artifacts to GHCR/PyPI/npm, or promoting builds from staging to production.
- ▌ Ansoff Matrix · marucieGenerate an Ansoff Matrix analysis mapping growth strategies across market penetration, market development, product development, and diversification. Use when considering growth options, planning market expansion, or evaluating strategic growth paths.
- ▌ Swot Analysis · maruciePerform a detailed SWOT analysis — strengths, weaknesses, opportunities, and threats with actionable recommendations. Use when doing strategic assessment, competitive analysis, or evaluating a product or business position.
- ▌ Fastapi · marucieUse when structuring a FastAPI application, designing dependency injection chains, defining Pydantic v2 schemas, adding JWT authentication, or writing async route tests with httpx.
- ▌ Mongodb · marucieUse when writing async MongoDB queries with Motor, designing aggregation pipelines, creating indexes, running multi-document transactions, or working with adk.state in Agentex agents.
- ▌ API Design · marucieUse when designing new REST endpoints, reviewing an existing API contract, adding pagination or filtering, planning a versioning strategy, or building a public or partner-facing API.
- ▌ Docker · marucieUse when writing or optimizing Dockerfiles, configuring Docker Compose services, debugging containers that behave differently from local, or reducing image size for Python and Node.js apps.
- ▌ Business Model · marucieGenerate a Business Model Canvas with all 9 building blocks. Use when creating a business model, documenting how a business creates value, or analyzing an existing business model.
- ▌ Langgraph · marucieUse when building or debugging LangGraph workflows — designing state graphs, adding conditional routing, wiring checkpointers, streaming tokens, implementing human-in-the-loop interrupts, or coordinating multi-agent subgraphs.
- ▌ Pydantic · marucieUse when defining request/response schemas, writing custom validators, controlling serialization for PATCH endpoints, validating non-model data with TypeAdapter, or configuring app settings from environment variables with pydantic-settings.
- ▌ Angular · marucieUse when building or refactoring Angular applications — choosing between signals, RxJS, and NgRx for state, configuring routing with guards and lazy loading, optimizing change detection, or writing TestBed component tests.
- ▌ Security · marucieUse when implementing authentication, authorization, input validation, or secrets management — or when auditing an existing service against OWASP Top 10 risks, configuring security headers, or running a STRIDE threat model.
- ▌ Industry Forces · maruciePerform Five Forces analysis — competitive rivalry, supplier power, buyer power, threat of substitutes, and threat of new entrants. Use when analyzing industry dynamics, assessing competitive forces, or evaluating market attractiveness.
- ▌ Pestle Analysis · maruciePerform a PESTLE analysis covering Political, Economic, Social, Technological, Legal, and Environmental factors. Use when assessing the macro environment, doing strategic planning, or evaluating external factors affecting your business.
- ▌ Multi Search Engine · marucieUse when searching across both Chinese and international sources simultaneously (17 engines: 8 CN + 9 Global). Trigger: 'search Baidu and Google', 'Chinese + English sources', cross-region market research, privacy-first search, WolframAlpha knowledge queries. NOT for: single-engine queries (use ask-search), real-time finance data, or when speed is critical (parallel requests are slower).
- ▌ Memory Map · marucieUse when installing or configuring memory_map, writing CLAUDE.md session-setup instructions, choosing what to save in memory vs history, managing cross-project memory, tuning compression, or troubleshooting why Claude isn't loading context at session start.
- ▌ Promptbase · marucieUse when writing, reviewing, or adapting a Claude Code skill for sale on PromptBase — checking scope, audience breadth, rejection risk, description quality, examples, and setup instructions.
- ▌ Tailwind · marucieUse when composing Tailwind utilities, building responsive or dark-mode layouts, defining component variants with cva, resolving conflicting classes with tailwind-merge, or configuring a custom theme.
- ▌ Unit Testing · marucieUse when writing unit tests for a function or module, mocking external dependencies, practising TDD on new business logic, or enforcing a coverage target across a codebase in Python, TypeScript, or Go.
- ▌ Product Strategy · marucieCreate a comprehensive product strategy using the 9-section Product Strategy Canvas — vision, segments, costs, value propositions, trade-offs, metrics, growth, capabilities, and defensibility. Use when building a product strategy, creating a strategic plan, or defining product direction.
- ▌ Design Taste Frontend · marucieUse for opinionated UI engineering standards: variance/motion/density baselines, component architecture rules, CSS hardware acceleration. Best for refining or auditing existing UI. NOT for greenfield builds (use frontend-design). NOT for design thinking (use qiaomu-design-advisor).
- ▌ Postgresql · marucieUse when writing complex PostgreSQL queries, diagnosing slow queries with EXPLAIN ANALYZE, designing indexes, handling concurrent writes, or planning safe schema migrations on large tables.
- ▌ Sqlalchemy · marucieUse when using async SQLAlchemy 2.0 — defining models, writing queries, managing async sessions, loading relationships without N+1, or setting up and debugging Alembic migrations.
- ▌ Typescript · marucieUse when writing advanced TypeScript — creating utility types, narrowing unions, resolving tricky type errors, configuring the compiler for strict mode, building branded types, or augmenting third-party module types.
- ▌ System Design · marucieUse when designing a new service from scratch, writing a tech spec or RFC, selecting a database or communication pattern, estimating capacity, or reviewing a design for scalability and reliability gaps.
- ▌ Test Strategy · marucieUse when choosing a testing model for a new project, auditing a test suite that is slow or provides low confidence, setting coverage targets, or writing a QA test plan for a release.
- ▌ Value Proposition · marucieDesign a detailed value proposition using a 6-part JTBD template — Who, Why, What before, How, What after, Alternatives. Use when creating a value proposition, analyzing customer value delivery, or articulating why customers should choose your product.
- ▌ Stitch Design Pipeline · marucieFully automated design workflow: PRD → Stitch prototype → Icon/Logo → Code translation. All steps automated end-to-end. User touches nothing.
- ▌
- ▌
- ▌ Iterative Autoresearch · marucie自动迭代优化框架：改一个东西 → 打分 → 好的留 → 差的扔 → 再改下一个。 不限于 ML — 任何能打分的东西都能自动优化（代码、内容、配置、prompt、skill、定价策略）。 触发条件：用户说"帮我优化"、"自动迭代"、"跑实验"、"对比方案"、"调优"、 "自动改进"、"autoresearch"、"不断尝试"、"打分迭代"等。 NOT for: 一次性任务、无明确评估指标的任务、探索性研究。
- ▌ Openai Agents · marucieUse when building or debugging OpenAI Agents SDK workflows — defining agents with tools and handoffs, wiring typed context, streaming responses, adding guardrails, or integrating with the Agentex ADK.
- ▌ Complex Doc RAG · marucieUse when building a RAG pipeline that ingests PDFs, Excel, CSV, or images — especially when debugging silent data loss, choosing between OCR tools, or handling edge cases like scanned pages, merged cells, or embedded charts.
- ▌ Performance · marucieUse when diagnosing a slow endpoint, fixing N+1 queries, adding a caching layer, offloading CPU-bound work to threads, or defining a latency budget for a service.
- ▌ Systematic Debugging · marucieUse when encountering a bug, test failure, crash, or unexpected behavior. Enforces root-cause investigation before any fix attempt. NOT for writing new features. Trigger: bug, error, failing test, broken, unexpected, crash, regression.
- ▌ Coding Standards · marucieUse when reviewing code for quality, naming a class or function, choosing a design pattern, refactoring a code smell, or establishing coding conventions for a new project.
- ▌ Event Driven · marucieUse when designing or debugging an event-driven system — choosing Kafka partitioning strategies, implementing the outbox pattern, handling dead-letter queues, ensuring idempotent consumers, or making event sourcing decisions.
- ▌ Observability · marucieUse when adding structured logging, instrumenting Prometheus metrics, wiring up distributed tracing with OpenTelemetry, writing alerting rules, defining SLOs and error budgets, or building a Grafana golden-signals dashboard.
- ▌ Solution Testing · marucieUse when writing Playwright E2E tests for critical user journeys, setting up post-deployment smoke tests, debugging flaky browser automation, or implementing BDD feature files with Gherkin.
- ▌
- ▌
- ▌
- ▌ Websockets Sse · marucieUse when building real-time features in FastAPI — choosing between WebSockets and SSE, implementing connection management, scaling broadcasts across workers with Redis, or debugging connection drops and missed events.
- ▌ Accessibility · marucieUse when building or reviewing UI components for keyboard and screen reader compatibility, adding ARIA to custom widgets, auditing a page for WCAG AA conformance, or preparing for a formal accessibility review.
- ▌ Microservices · marucieUse when decomposing a monolith, designing inter-service communication, implementing circuit breakers or sagas, reasoning about data ownership across services, or setting up an API gateway for a distributed system.
- ▌
- ▌
- ▌
- ▌ Database Design · marucieUse when designing a schema, adding indexes to fix slow queries, writing a zero-downtime migration, diagnosing N+1 issues with EXPLAIN ANALYZE, or configuring connection pooling for a PostgreSQL-backed service.
- ▌ Test Driven Development · marucieUse when implementing any feature or bugfix, before writing implementation code
- ▌
- ▌ Ft Tax Advisor · marucieUse when: tax type determination, tax rate application, tax filing, VAT/CIT/PIT calculation, tax policy interpretation. Trigger: 税种, 税率, 申报, 纳税, 增值税, 企业所得税, 个人所得税, 附加税. NOT for: tax planning optimization, international tax, legal disputes.
- ▌ Ft Tax Planner · marucieUse when: client needs tax optimization strategy, comparing tax burden across business structures, or evaluating legitimacy of tax planning schemes. Trigger: tax planning, tax optimization, tax savings calculation, business structure comparison, anti-avoidance boundary. NOT for: routine tax filing, historical tax declaration corrections, or transfer pricing documentation.
- ▌ Gsap Performance · marucieOfficial GSAP skill for performance — prefer transforms, avoid layout thrashing, will-change, batching. Use when optimizing GSAP animations, reducing jank, or when the user asks about animation performance, FPS, or smooth 60fps.
- ▌
- ▌ Containerization · marucieUse when writing Dockerfiles, setting up docker-compose for local dev, configuring Kubernetes resources (Deployment, Service, Ingress, HPA), sizing pod resource limits, or packaging a service with Helm.
- ▌ Integration Testing · marucieUse when writing tests that hit a real database or broker, setting up Testcontainers for a project, testing HTTP endpoints end-to-end within the service boundary, or implementing contract tests between two services.
- ▌ Performance Testing · marucieUse when load testing a service before launch or after a significant traffic change — writing k6 or Locust scripts, setting SLO-based pass/fail thresholds, diagnosing bottlenecks under load, or integrating performance tests into CI.
- ▌
- ▌
- ▌ Azure Service Bus · marucieUse when implementing reliable message processing with Azure Service Bus — choosing between queues and topics, configuring peek-lock settlement, handling dead-lettered messages, or enforcing ordered processing with sessions.
- ▌
- ▌
- ▌
- ▌
- ▌ Incident Response · marucieUse when triaging a production alert, writing a postmortem, creating or updating a runbook, classifying incident severity, or setting up on-call escalation paths.
- ▌