majiayu000
- 75k skills
- 0 followers
- 567 repo stars
- 3 weeks ago last updated
- ▌ Heyreach Master · majiayu000 bundleInternal resource library for HeyReach integration. Contains shared API client, operation scripts, and reference documentation.
- ▌ Hf Tool Builder · majiayu000 bundleUse this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful when chaining or combining API calls or the task will be repeated/automated. This Skill creates a reusable script to fetch, enrich or process data.
- ▌ Hic Aggregation · majiayu000 bundleBuild comprehensive chromatin contact maps by aggregating Hi-C loop calls (BEDPE) across multiple ENCODE experiments, donors, and labs. Use when the user wants to answer "what regions are in 3D contact in my tissue?" by creating a union catalog of chromatin loops. Handles resolution-aware anchor matching, cross-lab variation, and Hi-C-specific quality metrics.
- ▌ Hive Dependabot · majiayu000 bundleTriage and resolve multiple Dependabot updates in batch; use when there are many dependency PRs.
- ▌ Hono Ipc Routes · majiayu000 bundleImplement type-safe IPC communication in Electron using Hono RPC. Use when creating API routes between main and renderer processes, setting up typed clients, or implementing request/response IPC patterns. Provides HTTP-like semantics over Electron IPC.
- ▌ Hook Management · majiayu000 bundleCentral authority for Claude Code hooks management in this repository. Automates enforcement of critical repository rules through hooks. Use when adding hooks, managing hooks, configuring hooks, troubleshooting hooks, or understanding hook behavior. Delegates to docs-management skill for official hooks documentation. Provides organization-specific patterns, configuration management, and workflow guidance.
- ▌ Hooks Reference · majiayu000 bundleUse this skill when asked about "hooks", "PreToolUse", "PostToolUse", "SessionStart", "hook events", "validate tool use", "block commands", "add context on session start", or implementing event-driven automation.
- ▌ Hooks Validator · majiayu000 bundleValidates React code for Rules of Hooks violations. Catches issues like hooks called after conditional returns that cause production crashes (React error
- ▌ Howdy Structure · majiayu000 bundleCreate PHP classes following Howdy framework conventions. Use when creating new classes or files in the plugin.
- ▌ Httpie API Test · majiayu000 bundleAPI 接口测试工作流，使用 HTTPie 作为核心工具。当用户需要测试 API 接口、执行接口调用、生成测试报告、管理接口依赖关系、或在项目中建立标准化的接口测试流程时使用此 skill。适用于 RESTful API 测试、接口联调、回归测试等场景。
- ▌ Hubspot Connect · majiayu000 bundleConnect to HubSpot CRM for contact, company, deal, and engagement management. Load when user mentions 'hubspot', 'crm', 'contacts', 'companies', 'deals', 'list contacts', 'create contact', 'search deals', or any HubSpot CRM operations. Meta-skill that validates config, discovers CRM objects, and routes to appropriate operations.
- ▌ Human Extractor · majiayu000 bundleGPU-accelerated pipeline for detecting, tracking, and classifying humans in dashcam footage. This skill should be used when users need to extract human presence from videos, analyze dashcam footage for people detection, perform investigative analysis of human subjects in recordings, or classify individuals with optional head covering detection.
- ▌ Hunt RAG Vector · majiayu000 bundleHunt vector-store / embedding-layer weaknesses in RAG pipelines (OWASP LLM08 Vector and Embedding Weaknesses) — persistent corpus poisoning that survives across sessions and users (distinct from one-shot indirect prompt injection, which is owned by hunt-llm-ai), cross-tenant vector-database IDOR (unauthenticated or unscoped queries against Pinecone/Weaviate/Chroma/Milvus/Qdrant/pgvector), source-text/metadata leakage in similarity-search results, and retrieval-hijack via adversarial embedding proximity ('SEO poisoning' for RAG). Targets: any app with a shared knowledge base, document upload feeding a chatbot, or a directly reachable vector-DB port. Validate: a second, clean session/account must inherit a poisoned result, or a cross-tenant artifact must be independently verifiable — confabulation is not a finding, same bar as hunt-llm-ai. Use when target is RAG-backed, exposes a vector-DB port, or lets users upload documents that other users' queries later retrieve.
- ▌ Hype Assessment · majiayu000 bundleAssess overall hype levels across AI topics by comparing lab researcher enthusiasm against critic skepticism. Use after topic synthesis to identify which topics are overhyped, underhyped, or accurately assessed by the field.
- ▌ Hyperbolic Bulk · majiayu000 bundleOn-chain GF(3) entropy storage via Aptos Move - bulk-boundary correspondence where entropy lives in the interior and observables project to agents
- ▌ Hyperforce 2025 · majiayu000 bundleSalesforce Hyperforce public cloud infrastructure and architecture (2025)
- ▌ Hypothesis Test · majiayu000 bundleGuide selection and interpretation of statistical hypothesis tests. Use when: (1) Choosing appropriate test for research data, (2) Checking assumptions before analysis, (3) Interpreting test results correctly, (4) Reporting statistical findings, (5) Troubleshooting assumption violations.
- ▌ I18N Translator · majiayu000 bundleInternationalization specialist for Phoenix/Elixir applications. Use when you need to extract hardcoded strings and replace them with gettext calls, manage translation files (POT/PO), or provide translations for French and Italian. Handles templates (.heex), controllers, LiveViews, error messages, and UI text.
- ▌ Icon Generation · majiayu000 bundleGenerate app icons (SVG/PNG) and launcher icons for Android Flutter apps. Use when creating UI icons, launcher icons, or platform-ready icon assets. Handles sizing, formats, and flutter_launcher_icons integration.
- ▌ Ict Mnq Trading · majiayu000 bundleICT-based MNQ futures trading analysis system for MFFU prop firm evaluation. Use when user provides market data (PDH, PDL, FVG levels, liquidity sweeps) and asks for trade analysis, entry/exit points,
- ▌ Ide Diagnostics · majiayu000 bundleFix TypeScript errors, get diagnostics, rename symbols, find references, organize imports. Use when user needs IDE/LSP tools for code navigation, diagnostics, and refactoring.
- ▌ Ide Integration · majiayu000 bundleIDE integration tips for VS Code, JetBrains, and terminal workflows. Use when setting up Claude Code with your IDE, configuring keybindings, optimizing terminal workflows, or synchronizing file navigation. Covers extensions, split terminals, clipboard, and diff viewing.
- ▌ Idea Brainstorm · majiayu000 bundleFacilite des sessions de brainstorming créatif pour explorer et développer des idées. Utiliser quand l'utilisateur a une idée vague, veut explorer des possibilités, dit "j'ai une idée", "brainstorm", "réfléchissons", ou veut générer des concepts avant de structurer un projet.
- ▌ Idea Consultant · majiayu000 bundleUse this skill when the user wants to "evaluate my business idea", "analyze my startup idea", "help me flesh out this concept", "what do I need to figure out to launch this", "act as a consultant for my idea", or has a seed idea they want to develop into a comprehensive plan. This skill transforms vague ideas into actionable frameworks with expert-level recommendations.
- ▌ Idea Evaluation · majiayu000 bundleAssess solution ideas on impact and feasibility to prioritize prototyping. Use during Ideate phase when deciding which ideas to pursue.
- ▌ Idea Normalizer · majiayu000 bundledescription: Normalize an idea into a consistent structure (writes to ideas/<IDEAID>/runs and updates ideas/<IDEAID>/latest). If Open Questions exist, ask the user and finalize with captured answers.
- ▌ Idea Plugin Dev · majiayu000 bundleDevelop IntelliJ IDEA plugins with two templates, standard plugins and AI-integrated plugins. Use when creating new IntelliJ IDEA plugins, setting up plugin projects, implementing actions, settings pages, or integrating with IntelliAI Engine. Supports both simple plugins without AI dependencies and advanced plugins with AI provider selection and prompt template management.
- ▌ Idea Validation · majiayu000 bundleValidate idea and create detailed PRD. Saves docs/PRD.md to project. Use when: user describes an app idea, wants to create something new. Triggers: "I want to build", "create app", "make website", "build MVP", "хочу создать", "сделать приложение".
- ▌ Identity Denial · majiayu000 bundleStructure stories around protagonists who refuse to acknowledge what they're becoming. Use when exploring self-deception, moral transformation, or the gap between self-perception and reality.
- ▌ Image Generator · majiayu000 bundleGenerate branded images using Google Gemini's image generation API. Supports multiple formats (LinkedIn headers, Medium headers, square concepts, vertical explainers). Reads brand guidelines from the project's BRAND.md file for consistent visual identity.
- ▌ Optimizing Images · majiayu000 bundleOptimizes images and generates responsive markup. Use when the user asks about image formats (WebP, AVIF), srcset, responsive images, Next.js Image, or reducing image file sizes.
- ▌ Commit Messager · majiayu000 bundleWrite clear and concise commit messages that accurately describe the changes made in the codebase
- ▌ Commit Messages · majiayu000 bundleUse this skill to draft a commit message for staged changes. Execute Skill(sanctum:git-workspace-review) first to capture the repository path, status, and diffs. If no changes are staged, stage the relevant files before continuing.
- ▌ Commit Patterns · majiayu000 bundleGenerates conventional commit messages. Use when creating git commits or reviewing staged changes. Ensures NO AI attribution in commits.
- ▌ Git Storytelling Commit Strategy · majiayu000 bundleUse when planning commit strategies or determining when to commit changes. Helps developers commit early and often to tell the story of their development process.
- ▌ Committing Code · majiayu000 bundleWrites git commit messages using conventional commits format with gitmoji. Use when creating git commits, preparing commit messages, or when the user asks to commit changes. Triggers on "commit", "git commit", "save changes", or any request to record changes to version control.
- ▌ Common Mistakes · majiayu000 bundleUse before implementing pgdbm patterns to avoid common mistakes - provides rationalization table and red flags that prevent pool multiplication, schema errors, and template syntax violations
- ▌ Common Pitfalls · majiayu000 bundleApply when debugging errors, reviewing code for issues, or encountering unexpected behavior. Contains known mistakes with ChurchTools API, Vue components, TypeScript, Safari cookies, and form handling.
- ▌
- ▌ Compare Options · majiayu000 bundleMulti-expert comparison and ranking of options with structured deliberation. PROACTIVELY activate for: (1) decision making between alternatives, (2) trade-off analysis, (3) option evaluation, (4) vendor/tool comparison, (5) strategy selection. Triggers: "compare options", "evaluate alternatives", "rank options", "which should I choose", "compare these", "trade-off analysis", "decision between"
- ▌ Complexity Gate · majiayu000 bundleEstimate issue complexity before implementation to prevent timeouts. Uses cheap estimation to save expensive implementation tokens.
- ▌ Component Layer · majiayu000 bundleThis skill should be used when the user asks to 'create a component', 'add a button', 'build a card', 'add UI element', or 'create a feature component'. Provides guidance for React components using shadcn/ui, Radix primitives, and CVA patterns in components/**/*.tsx.
- ▌ Component Slots · majiayu000 bundleAdding data-slot attributes for CSS targeting and component documentation
- ▌ Compose Manager · majiayu000 bundleDocker Compose を管理する。「compose 起動」「docker-compose up」「サービス起動」「compose 停止」「サービス止めて」「down」「compose ログ」「サービスのログ」「compose ps」「サービス状態」「compose build」「サービスビルド」などで起動。
- ▌ Compress Prompt · majiayu000 bundleCompresses prompts/skills into minimal goal-focused instructions. Trusts the model, drops what it already knows, maximizes action space. Use when asked to compress, condense, or minimize a prompt.
- ▌ Computer Vision · majiayu000 bundleImplement computer vision tasks including image classification, object detection, segmentation, and pose estimation using PyTorch and TensorFlow
- ▌ Concept Vetting · majiayu000 bundleUse when orchestrator generates new concepts or user says "vet concepts", "check conflicts", "find duplicates", "scan for overlaps" - scans story-tree database to detect duplicate, overlapping, or competing concepts. Returns conflict pairs with types and confidence scores for human review.
- ▌ Config Auditing · majiayu000 bundleNeovim configuration audit knowledge base. Use when: reviewing config files for issues, checking deprecated APIs, optimizing settings, or performing health checks. Provides checklists, best practices, and version-specific deprecated API detection patterns.
- ▌ Config Migrator · majiayu000 bundleMigrates codex configuration files from v2.0 push-based sync to v3.0 pull-based retrieval format with automatic backups
- ▌ Configuring Git · majiayu000 bundleThis skill should be used when the user configures Git with Home Manager, sets up delta, rerere, or encounters gitconfig conflicts. Covers custom aliases, git-cleanup scripts, rebase reverse display.
- ▌ Configuring Zed · majiayu000 bundleProvides guidance for configuring and customizing the Zed editor. Use when modifying Zed settings, keybindings, themes, or extensions.
- ▌ Confluence Docs · majiayu000 bundleAtlassian Confluence integration for enterprise documentation. Create and update pages via API, manage spaces and permissions, handle content migration, and sync between Markdown and Confluence.
- ▌
- ▌
- ▌ Consultando SQL · majiayu000 bundleExecuta consultas analiticas SQL no banco de dados via linguagem natural. Use para perguntas ad-hoc sobre rankings, agregacoes, distribuicoes, tendencias, cruzamentos de tabelas. Converte perguntas em SQL, valida com Evaluator-Optimizer, e executa read-only. Cobre 104 tabelas ativas via catalogo dinamico.
- ▌ Consume Youtube · majiayu000 bundleSearch and annotate ingested YouTube transcripts. Works with content already processed by /ingest-youtube.
- ▌ Content Auditor · majiayu000 bundleThis skill should be used when users need to evaluate course content, workshop materials, or training programs against a set of evaluation criteria (such as ICP-BAF learning outcomes). The skill audits content comprehensively, identifies gaps, and provides actionable recommendations.
- ▌ Content Editing · majiayu000 bundleComprehensive editing checklist and procedures covering grammar and style rules, fact-checking, consistency verification, and readability metrics. Use when reviewing drafts, ensuring quality, or preparing content for publication.
- ▌ Content Refiner · majiayu000 bundleRefine verbose educational content by eliminating redundancy, tightening prose, and strengthening lesson connections. Use when content is wordy, repetitive, or lacks narrative flow between sections.
- ▌ Content Writing · majiayu000 bundleThis skill enables writing of project descriptions that communicate business value, outcomes, and impact while deliberately avoiding disclosure of technical implementation details, code logic, or proprietary information.
- ▌ Context Dx Meta · majiayu000 bundleDX V3 workflow system, skills, slash commands, Beads issue tracking, and Serena code navigation. Handles skill creation, command configuration, workflow automation, and Beads/Serena integration. Use when working with developer workflows, creating skills, configuring commands, or Beads/Serena integration, or when user mentions DX improvements, skill creation, workflow automation, developer experience, "skill not found" errors, "command not working" errors, meta-workflow, DX tooling, or V3 system.
- ▌ Context Mapping · majiayu000 bundleMap relationships between bounded contexts using DDD context mapping patterns. Use when defining upstream/downstream relationships, integration strategies (ACL, OHS, PL), or generating Context Mapper DSL output. Follows event storming for bounded context discovery.
- ▌
- ▌ Context Monitor · majiayu000 bundleMonitors context token usage and warns when approaching limits. Automatically activates when context usage exceeds thresholds (30k, 50k, 70k tokens). Provides recommendations for context management and /clear usage. Auto-activates based on token usage, no specific keywords needed.
- ▌ Context Network · majiayu000 bundleBootstrap, maintain, and evolve context networks across their full lifecycle. Use when starting a new project, when existing documentation feels scattered, or when agent effectiveness degrades due to missing context.
- ▌ Context Restore · majiayu000 bundleUse when you need to fully restore working context from a previous session - loads STATUS.json, reads key files, rebuilds mental model of current work state. Do NOT use for quick questions or when starting fresh unrelated work - the full context restoration adds overhead that isn't needed for standalone tasks.
- ▌ Context Routing · majiayu000 bundleDetermines minimal context and routes tasks to the correct prompts, agents and tools.
- ▌ Context Updater · majiayu000 bundle项目上下文自动更新器。当新增功能、重构代码、修改架构时触发，确保 project_context.md 保持最新。触发词：新功能, 重构, 架构变更, 新模块, 新系统, 完成实现。
- ▌ Context7 Intake · majiayu000 bundleUse when Codex needs curated documentation context or outlines from the Context7 MCP server.
- ▌ Context7 Skills · majiayu000 bundleUse when managing Context7 CLI skills with npx ctx7 (search, install, list, remove, info).
- ▌ Contract Review · majiayu000 bundleAnalyze commercial agreements against organizational standards with clause-by-clause review
- ▌
- ▌ Conventions CSS · majiayu000 bundleApply when writing styles. Ensures consistency with design system and project patterns.
- ▌ Conventions Vue · majiayu000 bundleApply when working with Vue components, composables, stores, or styling. Ensures code matches established project patterns.
- ▌ Conversion Copy · majiayu000 bundleThis skill should be used when the user asks to 'write landing page copy', 'improve conversion', 'optimize CTA', 'review signup flow', 'write headlines', 'form microcopy', 'trust signals', 'onboarding copy', 'lead gen copy', or needs high-converting copy for signup forms, multi-step flows, and lead generation funnels.
- ▌ Convert Elm Roc · majiayu000 bundleConvert Elm code to idiomatic Roc. Use when migrating Elm frontend code to Roc applications, translating browser-based Elm to platform-agnostic Roc, or refactoring Elm web applications to Roc CLI/native tools. Extends meta-convert-dev with Elm-to-Roc specific patterns.
- ▌ Convert Roc Elm · majiayu000 bundleConvert Roc code to idiomatic Elm. Use when migrating Roc applications to Elm frontend code, translating platform-agnostic Roc to browser-based Elm, or refactoring Roc CLI tools to Elm web applications. Extends meta-convert-dev with Roc-to-Elm specific patterns.
- ▌ Convex Realtime · majiayu000 bundleImplement real-time features using Convex reactive queries that automatically update when data changes, enabling live collaboration, instant updates, and reactive UIs without manual polling. Use when building live dashboards, implementing collaborative editing, creating chat applications, showing real-time notifications, building activity feeds, implementing presence indicators, creating reactive search, or any feature requiring instant data synchronization across clients.
- ▌ Coolify Manager · majiayu000 bundleCoolify Server Manager. Use this skill when you need to perform commands on user's server on user's behalf
- ▌ Copilot Handoff · majiayu000 bundleCreate Copilot-optimized task specifications for handoff between Claude and GitHub Copilot. Use when planning implementation tasks that Copilot will complete. Optimizes comment format, provides rich context, includes checklists and examples.
- ▌ Core Researcher · majiayu000 bundleDeep research and information gathering specialist for thorough investigation, pattern analysis, and knowledge synthesis
- ▌ Core Web Vitals · majiayu000 bundleCore Web Vitals計測・診断スキル。Lighthouse CLI、Bundle Analyzer、パフォーマンス問題の特定と対策。
- ▌ Corpus Analysis · majiayu000 bundleGap detection and knowledge mapping techniques for comparing BRD requirements against corpus coverage. Includes SurrealQL queries for analyzing sources, entities, and topic coverage, plus prioritization frameworks for research task generation.
- ▌ Cost Calculator · majiayu000 bundleCost estimation scripts and tools for calculating GPU hours, training costs, and inference pricing across Modal, Lambda Labs, and RunPod platforms. Use when estimating ML training costs, comparing platform pricing, calculating GPU hours, budgeting for ML projects, or when user mentions cost estimation, pricing comparison, GPU budgeting, training cost analysis, or inference cost optimization.
- ▌ Cost Estimation · majiayu000 bundleGuidelines for estimating token usage and costs per task and phase. Reference this skill when planning to provide accurate budget estimates.
- ▌ Council Of Five · majiayu000 bundleSpawn 5 Opus subagents with randomly-generated distinct personas to debate a problem from multiple angles. Use when exploring UX decisions, architecture choices, or any decision that benefits from diverse perspectives arguing creatively.
- ▌ Count MCP Tools · majiayu000 bundleCount the total number of MCP tools in the Umbraco MCP Server project and provide a breakdown by collection. Use when the user asks about tool counts, tool statistics, or how many tools exist.
- ▌ Course Designer · majiayu000 bundleProvides comprehensive guidance for course design including curriculum development, learning objectives, and course structure. Use when the user asks about course design, needs to design courses, create learning objectives, or structure educational content.
- ▌ Cql Type System Schema Handling · majiayu000 bundleImplement and deserialize all CQL types including primitives (int, text, timestamp, uuid, varint, decimal), collections (list, set, map), tuples, UDTs (user-defined types), and frozen types. Use when working with CQL type deserialization, schema validation, collection parsing, UDT handling, or type-correct data generation.
- ▌ Crane Aerodrome · majiayu000 bundleThis skill should be used when the user asks about "Aerodrome integration", "Aerodrome swap", "Aerodrome liquidity", "volatile pool", "stable pool", "Slipstream", "concentrated liquidity on Aerodrome", or needs to interact with Aerodrome DEX on Base using Crane's service libraries.
- ▌ Crane Utilities · majiayu000 bundleThis skill should be used when the user asks about "set collections", "AddressSet", "Bytes32Set", "math utilities", "ConstProdUtils", "AMM math", "hash functions", "BetterMath", "pagination", "EIP-712", "cryptography", or needs utility libraries for Crane Diamond development.
- ▌ Crash Debugging · majiayu000 bundleCrash log analysis, symbolication, and debugging workflows for iOS apps. Use when investigating app crashes, analyzing crash reports, symbolicating stack traces, or identifying root causes. Covers crash log retrieval, symbolication with dSYM files, stack trace analysis, and common crash patterns.
- ▌ Create Crud API · majiayu000 bundleCreate API-first CRUD endpoints with validation. Use when implementing create, read, update, delete operations for any resource.
- ▌ Create Dev Task · majiayu000 bundleUse to generate development task documents for the Dev agent. Creates specifications describing WHAT needs fixing based on validated issues and investigations.
- ▌ Create E2e Test · majiayu000 bundleCreate Playwright E2E tests for user flows. Use when testing complete user journeys, protected routes, form submissions, or cross-page navigation.
- ▌ Create Exercise · majiayu000 bundleCreate consistent, high-quality educational programming exercises or tutorials following strict template guidelines. Use this skill whenever you need to create or refine a programming exercise or tutorial for your course. Automatically applies template structure, formatting rules, and quality verification.
- ▌ Create MCP Eval · majiayu000 bundleCreate or modify evaluations for MCP Server(s). Use whenever you are tasked with changed MCP evals.
- ▌ Create Odoo Pwa · majiayu000 bundleGenerate an offline-first Progressive Web App with Odoo Studio backend integration. Use when user wants to create new Odoo-backed application, mentions "PWA with Odoo", "offline Odoo app", "Odoo Studio PWA", or similar terms. Supports SvelteKit, React, and Vue frameworks.
- ▌ Create Resource · majiayu000 bundleOrchestrator skill for creating a complete CRUD resource with all layers. Use when creating a new domain entity like notes, users, or courses from scratch. Triggers on "create resource", "new entity", "add crud for".
- ▌ Create Standard · majiayu000 bundleGuide for creating coding standards via the Packmind CLI. This skill should be used when users want to create a new coding standard (or add rules to an existing standard) that captures team conventions, best practices, or coding guidelines for distribution to AI coding assistants.