majiayu000
- 75k skills
- 0 followers
- 567 repo stars
- 3 weeks ago last updated
- ▌ Apollo Server · majiayu000 bundleGuide for building GraphQL servers with Apollo Server 5.x. Use this skill when: (1) setting up a new Apollo Server project, (2) writing resolvers or defining GraphQL schemas, (3) implementing authentication or authorization, (4) creating plugins or custom data sources, (5) troubleshooting Apollo Server errors or performance issues.
- ▌ Aptos Society · majiayu000 bundleAptos Society: World Extractable Value (WEV) implementation via GayMove contracts. Path A vault-only multiverse finance with worldnet ledger for 26 Agent-O-Rama worlds. Deployed 2024-12-29 on Aptos mainnet.
- ▌ Atomic Design · majiayu000 bundleAtomic Design methodology for React component architecture. Use for structuring component libraries, organizing UI hierarchies, and creating scalable design systems. Triggers on requests for component organization, design system structure, UI hierarchy, or questions about Atoms/Molecules/Organisms/Templates/Pages.
- ▌ Audio Extract · majiayu000 bundle从视频文件中提取音频。Use when user wants to 提取音频, 抽取音频, 视频转音频, 导出音频, extract audio, video to audio, get audio from video, 把视频的声音提取出来.
- ▌ Audio Layering Somatic Cue · majiayu000 bundleNervous system engineering for safe, embodied trance experiences
- ▌ Audio Systems · majiayu000 bundleGame audio systems, music, spatial audio, sound effects, and voice implementation. Build immersive audio experiences with professional middleware integration.
- ▌ Audio Trimmer · majiayu000 bundleCut, trim, and edit audio segments with fade effects, speed control, concatenation, and basic audio manipulations.
- ▌ Audit And Fix · majiayu000 bundleI'll perform a comprehensive security audit and automatically fix vulnerabilities for: $ARGUMENTS
- ▌ Audit Process · majiayu000 bundleRun a comprehensive multi-stage automation audit with parallel agents
- ▌ Audit Support · majiayu000 bundleSupport SOX 404 compliance with control testing methodology, sample selection, and documentation standards.
- ▌ Aurora Schema · majiayu000 bundleAurora YAML schema analysis and editing. Validates field names, descriptions, types, and module semantics following DDD best practices. Trigger: When analyzing or editing *.aurora.yaml files, improving field naming, adding descriptions, or validating schema semantics.
- ▌ Auth Patterns · majiayu000 bundleSupabase auth can cause hangs and deadlocks due to the Web Locks API. This skill covers safe patterns to avoid these issues.
- ▌ Auth Provider · majiayu000 bundle认证提供商统一接口，支持 Supabase Auth、Clerk、Firebase Auth 等主流认证服务。 提供用户注册、登录、OAuth、会话管理、权限验证等功能。
- ▌
- ▌ Auto Parallel · majiayu000 bundleEnable parallel agent execution for multi-domain features with git worktree isolation
- ▌ Auto Validate · majiayu000 bundleNext.js 코드 작성 후 자동 검증 (tsc, lint, build). Use when (1) 코드 구현 완료 후, (2) PR 생성 전, (3) 커밋 전 검증 필요 시. 모든 검증 통과 시에만 다음 단계 진행.
- ▌ Auto Workflow · majiayu000 bundle자율 판단 + 자율 발견 워크플로우 (v2.0 - Ralph Wiggum 철학 통합). "할 일 없음 → 종료"가 아닌 "할 일 없음 → 스스로 발견". 5계층 우선순위, 9개 커맨드 자동 트리거, Context 예측 기반 관리.
- ▌ Autogen Setup · majiayu000 bundleMicrosoft AutoGen multi-agent configuration for conversational AI systems
- ▌ Autoregmonkey · majiayu000 bundle智能计量经济学分析代理。当用户输入以"autoregmonkey："开头时，LLM会解析经济学计量任务，参考RAG数据库知识，动态调用Python和Stata技能执行任务，最后生成中文报告。
- ▌ Awkward Array · majiayu000 bundleGuidance for working with Awkward Array 2.0 jagged arrays and records in Python. Use when building or debugging `awkward` workflows, including record construction with `ak.zip`, adding fields with `ak.with_field`, filtering/aggregation, combinatorics (`ak.cartesian`/`ak.combinations`), `argmin`/`argmax` slicing, flattening, sorting, and NumPy interop or common Awkward pitfalls.
- ▌ AWS Architect · majiayu000 bundleThis skill provides comprehensive AWS architecture design expertise for startup companies, emphasizing serverless technologies, scalability, cost optimization, and modern cloud-native patterns.
- ▌
- ▌
- ▌ AWS MCP Setup · majiayu000 bundleConfigure AWS Documentation MCP server to query up-to-date AWS knowledge, APIs, and best practices
- ▌ AWS Sagemaker · majiayu000 bundleAmazon SageMaker for building, training, and deploying machine learning models. Use for SageMaker AI endpoints, model training, inference, MLOps, and AWS machine learning services.
- ▌ Axiom Axe Ref · majiayu000 bundleUse when automating iOS Simulator UI interactions beyond simctl capabilities. Reference for AXe CLI covering accessibility-based tapping, gestures, text input, screenshots, video recording, and UI tree inspection.
- ▌ Axiom Codable · majiayu000 bundleUse when working with Codable protocol, JSON encoding/decoding, CodingKeys customization, enum serialization, date strategies, custom containers, or encountering "Type does not conform to Decodable/Encodable" errors - comprehensive Codable patterns and anti-patterns for Swift 6.x
- ▌ Axiom Haptics · majiayu000 bundleUse when implementing haptic feedback, Core Haptics patterns, audio-haptic synchronization, or debugging haptic issues - covers UIFeedbackGenerator, CHHapticEngine, AHAP patterns, and Apple's Causality-Harmony-Utility design principles from WWDC 2021
- ▌ Axiom Hig Ref · majiayu000 bundleReference — Comprehensive Apple Human Interface Guidelines covering colors (semantic, custom, patterns), backgrounds (material hierarchy, dynamic), typography (built-in styles, custom fonts, Dynamic Type), SF Symbols (rendering modes, color, axiom-localization), Dark Mode, accessibility, and platform-specific considerations
- ▌ Axiom Storage · majiayu000 bundleUse when asking 'where should I store this data', 'should I use SwiftData or files', 'CloudKit vs iCloud Drive', 'Documents vs Caches', 'local or cloud storage', 'how do I sync data', 'where do app files go' - comprehensive decision framework for all iOS storage options
- ▌ Azure Storage · majiayu000 bundleAzure Storage Services including Blob Storage, File Shares, Queue Storage, Table Storage, and Data Lake. Provides object storage, SMB file shares, async messaging, NoSQL key-value, and big data analytics capabilities. Includes access tiers (hot, cool, archive) and lifecycle management.
- ▌ Backend Setup · majiayu000 bundleThis skill should be used when the user asks to "create an agent runtime server", "set up agent runtime backend", "configure Modal sandbox", "implement PersistenceAdapter", "start WebSocket server", "create REST API for agents", or needs to build a Node.js backend using @hhopkins/agent-runtime.
- ▌ Badger Triage · majiayu000 bundleOrganize the hive that Bee collected. The badger methodically sorts issues into project columns, assigns sizes and priorities, moves work from backlog to ready, and plans milestones. Use when you need to triage your GitHub project board, size issues, set priorities, or plan timelines.
- ▌ Balance Guide · majiayu000 bundleGuide for balancing new Heart Rush content including talents, races, bloodmarks, and progression. Use when creating or modifying game mechanics to ensure they fit the existing power curve.
- ▌ Banach Spaces · majiayu000 bundleProblem-solving strategies for banach spaces in functional analysis
- ▌ Basalt Cortex · majiayu000 bundleMine knowledge from Gmail, Google Chat, Slack, Drive, local files, MCP servers, and web into an Obsidian-compatible vault (~/Documents/basalt-cortex/). Basalt format: markdown files with YAML frontmatter for clients, contacts, communications, and knowledge facts. Opens directly in Obsidian, syncs to basaltcortex.com via CLI daemon. Triggers: 'run the cortex', 'mine emails', 'mine slack', 'mine chat', 'cortex init', 'cortex search', 'cortex stats', 'what do I know about', 'set up cortex', 'mine my inbox'.
- ▌
- ▌ Batch Quality · majiayu000 bundlePre-flight validation and quality gates for batch LLM operations. ACTUALLY tests samples through LLM before burning tokens. Uses SPARTA contracts for DuckDB validation queries. Integrates with task-monitor for enforced quality gates.
- ▌ Bdd Assistant · majiayu000 bundleGuide developers through Behavior-Driven Development workflow. Use when: writing BDD scenarios, using Gherkin syntax, Given-When-Then format, feature files, Three Amigos collaboration. Keywords: BDD, behavior-driven, Given When Then, Gherkin, Cucumber, scenario, feature file, step definition, 行為驅動開發.
- ▌ Bdd Practices · majiayu000 bundleWrites behavior specifications in Gherkin format. Use when defining features from user perspective or creating acceptance tests.
- ▌ Bdd Scenarios · majiayu000 bundleUse when writing effective BDD scenarios including acceptance criteria, edge cases, and scenario organization. Use when defining behavior specifications.
- ▌ Bead Workflow · majiayu000 bundleManage beads correctly including claiming, closing, announcements, and dependencies. Use when starting work on a task, when finishing a task, when the user mentions beads or tasks, or when coordinating with other agents on task ownership.
- ▌ Bel Open File · majiayu000 bundleThis skill should be used when the user wants to open or preview a file that already exists on disk using the operating system's default application. Triggers on requests like "open this file", "show me the PDF", "preview the image", "view the document", or "display the spreadsheet". Works with all file types including PDFs, images, documents, emails, and spreadsheets.
- ▌ Bellog Notion · majiayu000 bundleProvides Notion CMS integration patterns and best practices for Bellog. Triggers when working with Notion data or implementing Notion-based features.
- ▌
- ▌ Betterdisplay · majiayu000 bundleUse when user says /betterdisplay or wants to change display resolution settings and sync to dotfiles
- ▌ Bi Dashboards · majiayu000 bundleBusiness intelligence and marketing dashboard creation with multi-platform support
- ▌ Bio Genome Intervals Bigwig Tracks · majiayu000 bundleCreate and read bigWig browser tracks for visualizing continuous genomic data. Convert bedGraph to bigWig, extract signal values, and generate coverage tracks using UCSC tools and pyBigWig. Use when preparing coverage tracks for genome browsers or extracting signal at specific regions.
- ▌ Binder Design · majiayu000 bundleGuidance for choosing the right protein binder design tool. Use this skill when: (1) Deciding between BoltzGen, BindCraft, or RFdiffusion, (2) Planning a binder design campaign, (3) Understanding trade-offs between different approaches, (4) Selecting tools for specific target types. For specific tool parameters, use the individual tool skills (boltzgen, bindcraft, rfdiffusion, etc.).
- ▌ Bip Narrative · majiayu000 bundleGenerate thematic, prose-style narrative digests from GitHub activity
- ▌ Bknd Webhooks · majiayu000 bundleUse when configuring webhook integrations in Bknd. Covers receiving incoming webhooks via HTTP triggers, sending outgoing webhooks with FetchTask, event-triggered webhooks on data changes, signature verification, retry patterns, and async processing.
- ▌ Estimate · majiayu000 bundleEstimates task effort by analyzing complexity, dependencies, historical velocity, and risk factors. Produces a structured estimate with confidence levels.
- ▌ Gen Plan · majiayu000 bundleGenerate iterative `plan-N.md` files in the repo root (max N=5). Use only when asked; clarify before `plan-1.md`; stop at `plan-5.md`.
- ▌ Make Req · majiayu000 bundleDecompose a task, plan, roadmap, or feature description into a structured set of requirements grouped for independent planning. Use when user says "make req", "make requirements", "decompose requirements", "extract requirements", or wants to break down a task into what needs to be true.
- ▌ New Plan · majiayu000 bundleCreate a new planning document and register it in the project CLAUDE.md. Use when starting multi-script or multi-session work that needs tracking, or when the user invokes /new-plan.
- ▌ Plan Arc · majiayu000 bundleDesign the proposed architecture for a task before implementation planning. Use when user says "plan arc", "design architecture", "propose architecture", or wants to define the target system shape before making a plan.
- ▌
- ▌ Plan New · majiayu000 bundleDrafts implementation plan from ready PRD and research artifacts. Use when PRD and research gates pass and plan stage should start.
- ▌
- ▌
- ▌ Show Way · majiayu000 bundleUse when the user asks for a flattened view of roadmaps and next actions. Returns a dependency-ordered task list with status glyphs and a next-actions frontier as chat output, without taking execution authority. Not for multi-session route planning — use wayfinder.
- ▌ Confetti · majiayu000 bundleTrigger a two-step confetti celebration by opening the Raycast confetti URL and speaking a phrase with the Alex voice. Use when the user asks to run confetti, celebrate, or trigger the confetti sequence.
- ▌ Electron · majiayu000 bundleAutomate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.
- ▌ Vast Gpu · majiayu000 bundleRent, manage, and destroy GPU instances on vast.ai. Use when user says "rent gpu", "vast.ai", "rent a server", "cloud gpu", or needs on-demand GPU without owning hardware.
- ▌ Vcp Init · majiayu000 bundleInitialize VCP configuration for this project. Creates global config (~/.vcp/config.json) if it doesn't exist, then creates project config (.vcp/config.json). Detects frameworks, scopes, and discovers the plugin path. Run this once when setting up VCP for a new project.
- ▌ Build Tam · majiayu000 bundleBuild a Total Addressable Market list by sourcing accounts and contacts from providers like Apollo, Crustdata, and PDL.
- ▌
- ▌ Cobuilder · majiayu000 bundleThis skill should be used when the user asks to "brainstorm a feature", "create a PRD", "write a solution design", "plan a new initiative", "start a new project", "ideate on a feature", "brainstorm and build", "go from idea to implementation", "generate a TDD pipeline", or when System 3/Guardian needs to drive the complete ideation → PRD → SD → worktree → autonomous TDD pipeline. Parent skill for CoBuilder orchestration-level workflows. For worker-level powers (TDD, debugging, verification), see the separate worker-superpowers skill.
- ▌ User Discovery Research · majiayu000 bundleMaster user research methodologies, customer interviews, persona development, and journey mapping. Understand customer problems deeply before building.
- ▌ Ice Score · majiayu000 bundleUse to prioritize solutions or opportunities using ICE scoring with evidence-backed confidence.
- ▌ Idea Team · majiayu000 bundle想法群聊室主持人 — 把一句话想法丢给多角色 AI 团队（调研员/反方/类比者）做查漏补缺。每个角色有自己的 voice，他们互相 @ 接话；你随时插话。**这是创意扩展工具，不打分、不否决、不堵路**。Use when 用户说"组个团队聊一下"、"开会讨论这个想法"、"找几个角度看看"、"群聊一下 X"、"team review X"，或调用插件命令 `/idea-coach:idea-team`。Do NOT use when 用户已决定做这个想法只要 PRD（用 `idea-to-product`）、或用户要单独某个角色 skill、或用户只想自由 brainstorm（不需要 team 结构）。
- ▌
- ▌ One Pager · majiayu000 bundleDistil anything — a startup, product, project, or idea — into a single persuasive page. Use when asked to make a one-pager, a one-page summary, a leave-behind, a startup/product one-sheet, or a tl;dr brief. Produces a structured single page — headline + tagline, the problem, the solution, why-now/proof, and a clear ask/CTA — designed to be skimmed and remembered, ready to export as a typeset PDF.
- ▌ Pm Review · majiayu000 bundleQuality review of individual decisions or decision registers. Checks schema compliance, body quality, connection completeness, and staleness. Not a content audit — a structural and reasoning audit. Triggers on "/pm-review", "/pm-review [decision]", "review this decision", "check quality", "audit decisions".
- ▌ Pm Update · majiayu000 bundleBackward pass through older decisions to update status, meta_state, and cross-links after a sprint or documentation session. Finds decisions made outdated by newer evidence. Triggers on "/pm-update", "/pm-update [decision]", "update registers", "propagate changes", "mark superseded".
- ▌ Ralph Add · majiayu000 bundleAdd new stories to an existing prd.json without resetting completed story statuses. Use this to extend a project with new features.
- ▌ Ralph Prd · majiayu000 bundleCreate Product Requirements Document (PRD) and setup for Ralph autonomous loop. Use when user runs /create-prd command, wants to set up a project for Ralph, mentions "ralph setup", "create prd", "product requirements", or needs to generate tasks for autonomous development.
- ▌ Retention · majiayu000 bundleDiagnoses and reduces churn — cancellation flows, save offers, failed-payment recovery, at-risk detection, and the product and service causes underneath. Use this when churn is rising or unexplained, to design a cancellation or win-back flow, to recover involuntary churn, to identify at-risk accounts before they leave, or to decide whether a retention problem is a product problem.
- ▌ Saying No · majiayu000 bundleDecline a request, push back on scope, or protect priorities without burning the relationship. Use when asked how to say no, turn down a request, push back on your boss/stakeholder, decline extra work, or protect the roadmap from a pet feature. Produces a graceful, firm response — the no, the honest why, an alternative or trade-off, and the exact wording, tuned to who's asking.
- ▌ Spec Plan · majiayu000 bundleTranslate an approved plan into specs with acceptance criteria and derived tasks. Use after plan mode when transitioning to implementation.
- ▌
- ▌ To Issues · majiayu000 bundleDecompose a plan, PRD, or spec into independently-grabbable vertical-slice issues (markdown file by default, GitHub issues via flag). Trigger when the user wants implementation tickets, work decomposition, or to convert an implementation plan into parallelizable work. Takes a plan file and emits atomic vertical slices.
- ▌ Voiceover · majiayu000 bundleGenerates audio narration from a text file using Chatterbox TTS. Use when the user wants to generate voiceover/audio from ANY text file.
- ▌ Write Prd · majiayu000 bundle사용자의 기능 아이디어를 시니어 전문가 관점에서 검토하고 PRD를 작성합니다. 기획/API/비즈니스/개발 관점에서 일반 방법론과 비교하여 문제점과 트레이드오프를 분석합니다.
- ▌ Just · majiayu000 bundlejust is a handy command runner for saving and running project-specific commands. Features include recipe parameters, .env file loading, shell completion, cross-platform support, and recipes in arbitrary languages. This skill is triggered when the user says things like "create a justfile", "write a just recipe", "run just commands", "set up project automation with just", "understand justfile syntax", or "add a task to the justfile".
- ▌ Mise · majiayu000 bundleExpert in mise—a fast, flexible polyglot runtime and task manager. Specializes in tool version management, environment variable control, task automation, and shell integration across development workflows.
- ▌ Nika · majiayu000 bundleRuns repeatable AI work as checked, budgeted workflow files. The agent captures a repeated task as a .nika.yaml DAG, audits cost/permits/schema before a single token is spent, and runs it with tamper-evident traces.
- ▌
- ▌ AI Verify · majiayu000 bundleUse when you need to PROVE a claim with evidence, run quality/security scans, or validate that work is actually complete. Evidence before claims -- no 'should work' allowed.
- ▌ Gsd Audit Fix · majiayu000 bundleAutonomous audit-to-fix pipeline — find issues, classify, fix, test, commit
- ▌ Phx Challenge · majiayu000 bundleChallenge mode reviews - rigorous questioning before approving changes. Use when you want thorough scrutiny of Ecto changes, LiveView events, OTP designs, or PR readiness.
- ▌ Check Doc · majiayu000 bundleVerify documentation and CLAUDE instructions are updated alongside code changes
- ▌
- ▌ Denarrate · majiayu000 bundleStrip narrative mode from descriptive artifacts. Comments describe state and intent — they don't tell stories.
- ▌ Dorodango · majiayu000 bundleIteratively polish code through successive quality passes run in fresh subagents.
- ▌ Eval Plan · majiayu000 bundleEvaluate implementation plan before execution - validates architecture, coverage, dependencies, and best practices. TRIGGER when: user wants plan validated ("evaluate plan", "check plan", "validate plan", "review the plan before starting"). DO NOT TRIGGER when: user wants to execute plan (use /execute-plan), create plan (use /start-issue or /plan), or review code (use /review).
- ▌
- ▌ New Space · majiayu000 bundleUse when a user starts a new work session and asks to split human decisions from agent execution. Writes a contract-bound brief under run/<session-id>/ and runs spawn, work, review, and human-gate phases to completion. Not for remote, credential, publish, deploy, or irreversible changes.
- ▌ Nw Review · majiayu000 bundleDispatches an expert reviewer agent to critique workflow artifacts. Use when a roadmap, implementation, or step needs quality review before proceeding.
- ▌ Prove Fix · majiayu000 bundle[Code Quality] Prove fix correctness with code proof traces, confidence scoring, and stack-trace-style evidence chains. Use after /fix in bugfix workflows.