majiayu000
- 75k skills
- 0 followers
- 567 repo stars
- 3 weeks ago last updated
- ▌ List Connections · majiayu000 bundleUse when the user asks to find, create, or look up a Power Platform connection ID or connection reference for the current environment.
- ▌ Log Error Digest · majiayu000 bundleAnalyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or get distribution stats.
- ▌ Longbridge Intel · majiayu000 bundleMarket intelligence: strategy screener, popularity rankings, top movers with news correlation, quote anomalies, index/ETF constituent stocks, morning briefings, catalyst monitoring for watchlist, event-driven strategies, ETF fund flows, sector rotation, market microstructure, supply chain analysis, industry overviews, and ARK-style disruptive innovation analysis. Triggers: "筛选", "策略筛选", "排行", "热度", "异动", "成分股", "晨报", "早报", "催化剂", "事件驱动", "ETF资金流", "板块轮动", "产业链", "行业概览", "颠覆式创新", "ARK", "篩選", "排行", "異動", "成分股", "晨報", "ETF資金流", "板塊輪動", "產業鏈", "screener", "rank", "anomaly", "constituent", "morning brief", "catalyst", "event strategy", "ETF flow", "ETF资金流", "ETF申赎", "ETF資金流", "etf flow", "资金申赎", "etf 资金", "sector rotation", "supply chain", "ARK", "disruptive innovation", "板块筛选", "行业筛选", "板塊篩選", "強勢板塊", "弱勢板塊", "top sectors", "催化劑", "事件驅動", "行業概覽", "顛覆式創新", "策略篩選", "熱度"
- ▌ N8n Subworkflows · majiayu000 bundleBuild reusable n8n sub-workflows with typed inputs, all-vs-each execution, discoverable naming, and agent-tool exposure.
- ▌ Nw Agent Testing · majiayu000 bundle5-layer testing approach for agent validation including adversarial testing, security validation, and prompt injection resistance
- ▌ Nw Mikado Method · majiayu000 bundleEnhanced Mikado Method for complex architectural refactoring - systematic dependency discovery, tree-based planning, and bottom-up execution
- ▌ Nw UX Principles · majiayu000 bundleCore UX principles for product owners. Load when evaluating interface designs, writing acceptance criteria with UX requirements, or reviewing wireframes and mockups.
- ▌ Opsec Discipline · majiayu000 bundleUse when about to take any outward or offensive action (request, payload, persistence, lateral movement, exfil, or feeding captured traffic to the model) — to decide detection footprint, cleanup, and secret redaction first
- ▌ Outreach Manager · majiayu000 bundleUse when the user asks to "write influencer outreach", "follow up with a creator", or "negotiate partnership terms"; produces personalized pitches, multi-touch follow-up sequences, negotiation scripts with objection handling, and a status pipeline tracker. Not for finalizing signed agreements — use contract-helper.
- ▌ Pair Programming · majiayu000 bundleCollaborative coding with enforced micro-steps and user-paced control.
- ▌ Pause And Resume · majiayu000 bundleCooperatively pause unfinished work in the current session, leave a precise continuation checkpoint, and resume from it when the user later says continue. Use only when the user explicitly requests this pause workflow. Do not use for crashes, app shutdown, new-session handoffs, or ordinary task summaries.
- ▌ Permission Check · majiayu000 bundleDiagnose why Claude Code is (or isn't) prompting for permission. By default reads only repo-local layers (CLI project, CLI project-local, VSCode workspace). Host-global layers (CLI user `~/.claude/`, VSCode user settings) are read ONLY when the user explicitly confirms — those files may contain unrelated paths or secrets. Use when user says "why is it asking me to approve?", "permission check", "why am I getting prompts?", "bypass isn't working", "check my permissions". Read-only diagnostic.
- ▌ Persuasion Brief · majiayu000 bundleBuild the case to win someone over to a decision, idea, or change. Use when asked to persuade someone, build a case for an idea, get buy-in, win over a skeptic, or prepare to pitch a proposal internally. Produces a persuasion brief — the audience's current view and what moves them, the core argument, the proof, objection handling, the emotional and logical appeals, and the ask.
- ▌ Post Ocr Cleanup · majiayu000 bundleClean post-OCR text. Correction, QA, multilingual handling, provenance.
- ▌ Project Delivery · majiayu000 bundlePlans and delivers a single project — scope, estimation, scheduling, critical path, tracking, and recovering when it slips. Use this to plan a project, build or challenge a schedule, estimate credibly, track progress meaningfully, or recover a project that is late.
- ▌ Prompt Optimizer · majiayu000 bundleTurns rough intent or a weak prompt into a reliable one — diagnosing why output is inconsistent, restructuring the instruction, and adapting it across models. Use this when a prompt is not producing what was wanted, when output varies run to run, when writing a prompt for a repeated task, when moving a prompt between models, or when someone describes what they want an AI to do and needs it written properly.
- ▌ Public Relations · majiayu000 bundlePlans and executes earned media — press strategy, journalist outreach, announcements, commentary, and crisis response. Use this to plan a press push, write a pitch or release, find and approach the right journalists, prepare for an interview, decide whether something is newsworthy, or respond to a story going badly.
- ▌ Readme Generator · majiayu000 bundleUse when creating or rewriting README.md for projects. Triggers on "write README", "create README", "update README". Creates human-focused documentation with proper structure.
- ▌ Safety And Audit · majiayu000 bundleSets up safe working habits and a change log so you always know what Cowork has done to your files — and can undo anything. Use when setting up file protection guardrails, for establishing safe automation habits, during initial access configuration, when granting file permissions for the first time, or when the user says "is cowork safe", "file safety", "what if it deletes my files", "audit trail", "safety setup", "I'm nervous about file access", "how do I trust cowork with my files", "can cowork mess up my computer", "I heard someone lost files", or "how do I stay in control".
- ▌ Self Improvement · majiayu000 bundleContinuously improve AI workflows and capabilities. Use when reflecting on process, identifying friction, or after completing significant work.
- ▌ Simulation Study · majiayu000 bundleScaffold and run a reproducible Monte Carlo simulation study in R — parameterized DGP, an estimator grid, a seeded replication loop, and a summary of bias, RMSE, empirical SE, coverage, size/power with Monte Carlo standard errors. Use when the user says "run a Monte Carlo simulation", "simulation study", "check the bias/coverage of an estimator", "compare estimators in simulation", "size and power simulation", "Monte Carlo experiment", or wants to demonstrate an estimator's finite-sample properties. Produces a numbered R script in `scripts/R/` and saves per-replication raw results + a summary table to `scripts/R/_outputs/`.
- ▌ Slack Agent Flow · majiayu000 bundleLet an existing Slack agent create new agents that arrive as their own Slack bots — provisioned app, operator DM, and a shared three-way room, hot-started without a host restart.
- ▌ Story Short Scan · majiayu000 bundle短篇网文扫榜。分析知乎盐言、七猫、黑岩、点众等平台热门短篇数据,捕捉风口题材。触发方式:/story-short-scan、/短篇扫榜、「短篇什么火」「知乎故事排行」。
- ▌ Suede Ab Testing · majiayu000 bundleSuede-owned experimentation discipline for hypotheses, sample sizing, test duration, significance, and repeatable experiment programs. Use when comparing variants, deciding whether a result is reliable, or building an experiment backlog and cadence. NOT FOR: analytics instrumentation (use suede-analytics), post-click conversion diagnosis (use suede-site-alchemy), or writing the variant copy itself (use suede-copy).
- ▌ Suede Cold Email · majiayu000 bundleSuede-owned B2B cold-email discipline for evidence-based personalization, subject lines, opening lines, concise bodies, one clear CTA, and bounded follow-up sequences. Use when writing or repairing outbound email to qualified prospects. NOT FOR: building or qualifying the prospect list (use suede-prospecting), lifecycle or nurture email (use suede-emails), or broader sales collateral (use suede-sales-enablement).
- ▌ Teach Your Voice · majiayu000 bundleBuilds a personal voice profile so Cowork writes the way you write — not like a generic AI. Use when personalizing your writing style, for capturing your communication patterns and tone, during setup after getting generic-sounding output, when training Cowork to match your voice, or when the user says "teach claude my voice", "my writing style", "output doesn't sound like me", "brand voice", "personalize output", "make it sound like me", "it sounds too formal", "it sounds too robotic", "can cowork match my tone", or "how do I get cowork to write like me".
- ▌ To Questionnaire · majiayu000 bundleUse when the user wants to turn a knowledge gap into an async questionnaire for someone else: identify the recipient and the needed answers, then write a discovery questionnaire to to-questionnaire-<slug>.md. Triggers: "turn this into a questionnaire", "questionnaire for X", "I need to ask someone else", async information gathering.
- ▌ Typescript Check · majiayu000 bundleTypeScript type checking via tsc --noEmit with actionable error output.
- ▌ Understand Figma · majiayu000 bundleAnalyze a Figma file via the Figma REST API and generate an interactive design knowledge graph (pages, screens, components, component sets, instances, design tokens) with a kind:"design" dashboard.
- ▌ Unikit Implement · majiayu000 bundleExecute implementation tasks from a feature plan in .unikit/plans/. Reads TASKS.md and PLAN-BRIEF.md, then implements uncompleted tasks sequentially executing tasks inline (Read/Edit/Write/Bash) with rules loaded once at start. Supports selective execution by phase or task numbers. Use when the user says "implement", "start coding", "execute plan", "continue implementation", "do the next task", "implement phase 3", or wants to work through a planned feature. Also use when the user references tasks from .unikit/plans/ or asks to "continue where we left off".
- ▌ Univer Integrate · majiayu000 bundleIntegrate Univer Sheets, Docs, or Slides into React, Vue 3, HTML, or Node.js projects. Use when embedding Univer, choosing preset or plugin mode, initializing instances, configuring themes/locales/workers, or manipulating workbooks, worksheets, ranges, formulas, permissions, and events through the Facade API.
- ▌ Update Brand Kit · majiayu000 bundleMaintain a brand kit — the canonical brand context an ad or content pipeline reads (positioning, audience, voice, standing instructions, brand-type, value-props, colors), plus manage the product list and attach product photos. Use when someone says "update my brand kit", "set my brand voice/audience", "add a product to my brand", or hands you a folder of product shots to attach. Platform-agnostic: it teaches the field model, partial-update/clear semantics, override behavior, caps and validation, and the hero-image and product-matching rules — independent of any specific backend.
- ▌ Vlm Ocr Pipeline · majiayu000 bundleDesign VLM-based OCR pipelines. Use for model selection, prompting, architecture, multilingual documents, structured output, and evaluation planning.
- ▌ Zsh Shell Config · majiayu000 bundleZsh shell configuration, PATH management, completions, and framework setup.
- ▌
- ▌ Hpc Python · majiayu000 bundlePython HPC patterns — threading/multiprocessing/async, CUDA streams, latency hiding, PyTorch DDP. Use when writing performance-sensitive Python code, distributed training, or parallel data processing.
- ▌ Cfn Memory Management · majiayu000 bundlePrevent and detect memory leaks in Claude CLI operations through proactive monitoring, limits, and profiling. Use when managing memory limits for long-running agents, detecting memory leaks, profiling heap usage, or implementing recovery procedures.
- ▌ Perf Check · majiayu000 bundleUse when the user wants to check performance, find slow code, identify bottlenecks, or audit efficiency.
- ▌ Review D3d · majiayu000 bundleAudit the D3D11 interop layer for per-frame waste — buffer allocations, redundant state calls, GPU readback efficiency
- ▌
- ▌ I · majiayu000 bundleYou are a senior engineer interviewer at a top tech company. This is a real interview simulation.
- ▌ AI Brainstorm · majiayu000 bundleUse when the user wants to design, architect, or explore a feature before building it. HARD GATE: no implementation until the user approves the spec.
- ▌ Dev Blueprint · majiayu000 bundleTurn a one-line objective into a step-by-step construction plan for multi-session, multi-agent projects. Each step has a self-contained context brief so a fresh agent can execute it cold. Includes adversarial review, dependency graph, and parallel step detection. Use when the user requests a plan or roadmap for a complex multi-PR task, or describes work that needs multiple sessions. Do NOT use for tasks completable in a single PR or fewer than 3 tool calls.
- ▌ Gantt Roadmap · majiayu000 bundleTurn a plan or set of milestones into a timeline / Gantt chart. Use when asked to build a roadmap, schedule phases, show a project timeline, or visualize what happens when. Produces a ready-to-render Mermaid Gantt chart (renders live, exportable as PNG/SVG) — and, because it has real dates, the result also exports to a calendar (.ics) — plus notes on the critical path and risks.
- ▌ Lp Prioritize · majiayu000 bundleStartup go-item ranking - score and select top 2-3 items to pursue
- ▌ Scope Project · majiayu000 bundleAdversarial project planning workflow. Explores the problem space, drafts tickets in batches, then runs sequential adversarial loops — a mandatory UX loop ("should we build this?"), zero or more discretionary specialist loops (security, performance) for projects with architectural implications in those domains, and a mandatory implementer loop ("could we build this?") — to find gaps before implementation. Creates well-specified, batch-tagged tickets upstream only after every applicable loop signs off.
- ▌ Score Backlog · majiayu000 bundleScore and rank backlog items using RICE, ICE, or custom weighted scoring when the user asks to prioritize a backlog, rank features, or score items for prioritization
- ▌ Sequence Plan · majiayu000 bundleTopologically sort plan tasks into correct implementation order, renumber sequentially, and add explicit dependency/blocker metadata to enable parallel subagent execution.
- ▌ Spec Kit Plan · majiayu000 bundleUse when an approved Spec Kit `spec.md` must be translated into technical design artifacts (`plan.md`, `research.md`, `data-model.md`, `contracts/`, `quickstart.md`) before `spec-kit-tasks`, or when `plan.md` is missing/outdated after spec or constitution changes.
- ▌ Triage Issues · majiayu000 bundleAnalyze open GitHub issues and produce a sequenced implementation plan — grouping issues into parallel batches, ordering those batches, and tagging each issue with its recipe route. Use when user says "triage issues", "prioritize issues", or "plan issue order".
- ▌ Fsm Design · majiayu000 bundleSpecialized skill for finite state machine design and optimization in FPGAs
- ▌ GCP Coding · majiayu000 bundleLanguage-agnostic GCP best practices and common pitfalls. Use when writing code that integrates with GCP services (Cloud Run, Secret Manager, Cloud Storage, Pub/Sub, etc.) to avoid anti-patterns and follow Google Cloud's recommended approaches.
- ▌ Gemini Dev · majiayu000 bundleGoogle Gemini API development with google-genai SDK. Use for prompting, multimodal inputs, structured outputs, and agentic workflows.
- ▌
- ▌ Gh Open Pr · majiayu000 bundleCreate a GitHub pull request with gh. Use when asked to open/create a PR (pull request), "PR作って", "draft PR", or "gh pr create".
- ▌ Gh Pr View · majiayu000 bundleView GitHub pull request details using gh CLI. Shows PR status, reviews, checks, comments, and metadata. Use when user wants to inspect PR information.
- ▌ Git Branch · majiayu000 bundleUse when creating a new branch in dd-sdk-ios for a JIRA ticket or feature. Use when choosing a branch name or base branch for development work.
- ▌ Git Squash · majiayu000 bundleSafely squash multiple commits into one with automatic backup and verification
- ▌ Git Writer · majiayu000 bundleSafe workflow for git write operations (git rm). Use for removing files from git.
- ▌ Github API · majiayu000 bundleHow to interact with GitHub API. Use this skill for repos, PRs, issues, and user operations.
- ▌ Go Context · majiayu000 bundleUse when working with context.Context in Go — placement in signatures, propagating cancellation and deadlines, and storing values in context vs parameters. Also use when cancelling long-running operations, setting timeouts, or passing request-scoped data, even if they don't mention context.Context directly. Does not cover goroutine lifecycle or sync primitives (see go-concurrency).
- ▌ Go Logging · majiayu000 bundleUse when choosing a logging approach, configuring slog, writing structured log statements, or deciding log levels in Go. Also use when setting up production logging, adding request-scoped context to logs, or migrating from log to slog, even if the user doesn't explicitly mention logging. Does not cover error handling strategy (see go-error-handling).
- ▌
- ▌ Golang Web · majiayu000 bundleModern Go Web application architecture guide. Use when creating new Go web projects, APIs, or microservices. Covers project structure, tech stack selection, and best practices based on Go standards.
- ▌ Hackernews · majiayu000 bundleHacker News API via curl. Use this skill to fetch top stories, new posts, comments, and user profiles from Hacker News.
- ▌ Har To Vue · majiayu000 bundle将 HAR(HTTP Archive)文件转换为 Vue 源代码。支持批量转换网络请求为 Vue 组件、API 调用或页面数据结构,用于复刻网站或快速生成基于现有 API 的 Vue 应用。当 Claude 需要处理 HAR 文件以:(1)从浏览器抓包数据生成 Vue 代码,(2)批量转换多个请求为 API 服务,(3)复刻现有网站的 Vue 技术栈实现,(4)生成带有数据绑定的组件模板时使用。
- ▌
- ▌ Imagesharp · majiayu000 bundleGuidance for SixLabors ImageSharp cross-platform image processing library. USE FOR: image resizing, cropping, format conversion, watermarking, thumbnail generation, applying filters and effects, drawing text and shapes on images, metadata reading. DO NOT USE FOR: video processing, real-time computer vision (use OpenCV), GPU-accelerated rendering, PDF generation (use PdfSharpCore), 3D graphics.
- ▌ Inline Rbs · majiayu000 bundleWrite RBS type annotations directly in Ruby source files using comment syntax. Use when adding types to Ruby code with rbs-inline.
- ▌ Interfaces · majiayu000 bundleContracts defining the shape a class must conform to. Used for decoupling dependent classes from concrete implementations, enabling multiple implementations and easier testing.
- ▌ Java Guide · majiayu000 bundleJava language guardrails, patterns, and best practices for AI-assisted development. Use when working with Java files (.java), pom.xml, build.gradle, or when the user mentions Java. Provides modern Java patterns (records, sealed classes, streams), testing standards, and Spring conventions specific to this project's coding standards.
- ▌ Jd Parsing · majiayu000 bundledescription: Pflege das Parsing von Job Descriptions (JD); verwenden bei neuen Feldern, Headern oder Parsing-Regeln.
- ▌
- ▌ Kata Debug · majiayu000 bundleSystematically debug issues, investigating bugs, troubleshooting problems, or tracking down errors with persistent state across context resets. Triggers include "debug", "investigate bug", "troubleshoot", "find the problem", "why isn't this working", and "debug session".
- ▌ Kpi Number · majiayu000 bundleConfigure KPI number displays in drizzle-cube dashboards for showing single metric values with formatting. Use when displaying KPIs, single numbers, metrics, totals, or key performance indicators.
- ▌ Lambert Jl · majiayu000 bundleDevelop and maintain Lambert.jl, a Julia library implementing multiple algorithms for solving Lambert's problem. Use when working on Lambert.jl, adding new solvers, computing orbital transfers, or generating porkchop plots.
- ▌ Line Chart · majiayu000 bundleConfigure line charts in drizzle-cube dashboards for time series and trend analysis with multiple series support. Use when creating line charts, trend lines, multi-line graphs, or time series visualizations.
- ▌ Lint Check · majiayu000 bundleRun code quality linters when reviewing code. Checks style, complexity, and best practices. Supports Python (ruff), JavaScript (eslint), Go (golangci-lint), Ruby (rubocop), Java (Checkstyle/PMD). Use when reviewing any code changes for quality issues.
- ▌ M09 Domain · majiayu000 bundleCRITICAL: Use for domain modeling. Triggers: domain model, DDD, domain-driven design, entity, value object, aggregate, repository pattern, business rules, validation, invariant, 领域模型, 领域驱动设计, 业务规则
- ▌ Magento Di · majiayu000 bundleConfigure Magento 2 dependency injection — di.xml, types, virtual types, preferences, argument replacement, and Object Manager. Use when wiring dependencies, creating class variations, or configuring module integrations.
- ▌ Md To Code · majiayu000 bundle根據結構化的 AI coding 實作文件(.md)逐步實作程式碼。讀取 prompt.md 大綱, 依序參考技術規格、後端實作指示、前端實作指示,逐步確認後實作後端與前端程式碼。 使用時機:當使用者要求根據已產出的實作文件開始寫程式、實作功能、按照文件 coding、 依文件實作、開始開發時觸發。關鍵字:md to code、根據文件實作、開始寫程式、 按文件 coding、依文件開發、實作程式碼、開始實作、to code、toCode、implement, implementation, 寫程式, coding, 依規格實作, 按規格開發, 從文件產生程式碼, generate code, code generation, 開始開發。
- ▌ Merge Back · majiayu000 bundleMerge changes from an isolated project copy back to the original project. Use after finishing work in a forked copy.
- ▌ Mern Stack · majiayu000 bundleStack decisions for MERN apps (Next.js, pnpm monorepo). Reference before scaffolding or architecture work.
- ▌ Meta Agent · majiayu000 bundleGenerates new Claude Code subagent configuration files from user descriptions. Use proactively when the user asks to create a new subagent or agent. Keywords include create subagent, new agent, build agent, agent architecture.
- ▌ Meta Tools · majiayu000 bundleDesign, validate, and orchestrate development tools with reusable patterns, composition rules, and evidence-backed tests.
- ▌ Middleware · majiayu000 bundleHTTP request/response pipeline handlers that inspect, modify, or reject requests before or after they reach a controller. Used for authentication, throttling, header manipulation, and logging.
- ▌ Mole Debug · majiayu000 bundleSystematic debugging through methodical hypothesis-driven investigation. The mole follows vibrations to their source. Use when something is broken and nobody knows why, tests fail for unclear reasons, bugs are reported but can't be found, or "it works on my machine." Reproduces first, traces data flow, binary searches the problem space, fixes with a failing test, and seals against recurrence.
- ▌ Msvc Build · majiayu000 bundleCompile MSVC C++ projects with multi-processor support, automatic MSBuild detection, and intelligent error analysis.
- ▌ Mvp Design · majiayu000 bundleDesign Minimum Viable Prototype code following "code-as-documentation" principles. Produces architecture-focused documentation without code snippets, emphasizing design decisions over implementation details.
- ▌ Nean Stack · majiayu000 bundleStack decisions for NEAN apps (NestJS, Angular, Nx monorepo). Reference before scaffolding or architecture work.
- ▌ New Router · majiayu000 bundleScaffold a new tRPC router with repository, interface, tests, and barrel exports following project conventions
- ▌
- ▌ Objectpool · majiayu000 bundleImplements Zero Allocation patterns using Span, ArrayPool, and ObjectPool for memory efficiency in .NET.
- ▌ Ocaml Docs · majiayu000 bundleFixing odoc documentation warnings and errors. Use when running dune build @doc, resolving reference syntax issues, cross-package references, ambiguous references, hidden fields, or @raise tags in OCaml documentation.
- ▌ Okr Review · majiayu000 bundleQuarterly OKR review with key results scoring, progress tracking, and next quarter planning
- ▌ Ost Render · majiayu000 bundleRender `.claude/canvas/opportunities.yml` as a diagram or structured list. Read-only. Default format Mermaid mindmap. Consults the attribution registry per `${CLAUDE_PLUGIN_ROOT}/engine/render-conventions.md` consent + privacy gate. Second specialist in the render fleet.
- ▌ PHP Modern · majiayu000 bundleWrite modern PHP 8.x code — typed properties, enums, readonly classes, match expressions, named arguments, union/intersection types, fibers, attributes, and constructor promotion. Use when writing PHP for Magento or any PHP 8.x project.
- ▌ Power Apps · majiayu000 bundleExpert guidance for Power Apps development including PCF controls, canvas apps, model-driven apps, Power Fx formulas, and Power Apps Test Engine. Use when building PCF components with React/TypeScript, writing Power Fx expressions, customizing model-driven forms, or testing canvas apps.
- ▌
- ▌ Prisma CLI · majiayu000 bundlePrisma CLI commands reference covering all available commands, options, and usage patterns. Use when running Prisma CLI commands, setting up projects, generating client, running migrations, or managing databases. Triggers on "prisma init", "prisma generate", "prisma migrate", "prisma db", "prisma studio".