majiayu000
- 75k skills
- 0 followers
- 567 repo stars
- 3 weeks ago last updated
- ▌ Get Week Content · majiayu000 bundleRead and parse Week.md content for weekly review. Returns structured data including frontmatter, sections, completeness assessment, and extracted entities.
- ▌ Github Fix Issue · majiayu000 bundleFix GitHub issues end-to-end — from analysis through branch creation, implementation, testing, and PR submission. Use this skill whenever the user mentions fixing a GitHub issue, resolving a bug from an issue tracker, working on a GitHub issue number, or says things like "fix issue
- ▌ Hexo Blog Update · majiayu000 bundleStandardized workflow for creating and publishing Hexo blog posts with local preview and deployment.
- ▌ Homelab Workflow · majiayu000 bundleEnforce homelab-proxmox workflow patterns including single source of truth documentation, prompt logging, git commits, environment variables, and phase tracking. Use this skill when completing tasks, updating docs/ or CLAUDE.md files, or when workflow compliance validation is needed. Provides AI-powered fixes for violations.
- ▌ Hooks Automation · majiayu000 bundleAutomated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration
- ▌ Jira Add Journey · majiayu000 bundleAdd a Validation Journey section to an existing JIRA ticket by analyzing the change type and generating appropriate verification steps with evidence markers.
- ▌ Macos Automation · majiayu000 bundleAppleScript, JXA, Shortcuts, Automator, osascript, System Events, accessibility API
- ▌ Manage Approvals · majiayu000 bundleManage the human-in-the-loop approval workflow. Check for pending approval requests, review approved/rejected items, process decisions, and check for expired requests. Use when managing sensitive actions that require human sign-off before execution.
- ▌ Monitor Contacts · majiayu000 bundleAlways-on contact freshness monitoring service. Runs on a schedule (via
- ▌ Noir Sync Update · majiayu000 bundlePerform necessary follow-on updates as a result of updating the noir git submodule.
- ▌ Organize Commits · majiayu000 bundleOrganize staged changes into logical commits with conventional commit messages. Groups related changes and creates well-structured commit history.
- ▌ Partner Delivery · majiayu000 bundleDeliver repeatable MotherDuck architectures across multiple clients. Use when standardizing isolation, provisioning, regional deployment, sharing boundaries, and client-specific exceptions for a consultancy or partner delivery model.
- ▌ Phase Transition · majiayu000 bundleTransition between session phases (RESEARCH → PLAN → IMPLEMENT → REVIEW → VERIFY)
- ▌ Pipeline Summary · majiayu000 bundleCreate a GitHub issue and PR summarizing pipeline bugs and fixes. Use when a pipeline run completes with accumulated bug fixes on a feature branch.
- ▌ Process Meetings · majiayu000 bundleProcess synced Granola meetings to update person pages, extract tasks, and organize meeting notes
- ▌ Pydub Automation · majiayu000 bundleAutomate repetitive audio tasks with Python using PyDub for batch processing, format conversion, normalization, and content assembly. Use when: Processing large numbers of audio files consistently; Converting between audio formats at scale; Normalizing loudness across a batch of files; Assembling intros/outros automatically to episodes; Trimming silence or extracting segments programmatically
- ▌ Refresh Research · majiayu000 bundleUse when user invokes /refresh-research to re-fetch refreshable research sources, detect meaningful changes, and update synthesis files. Supports specific files, categories, staleness thresholds, backfill of source_type, and audit-only dry runs.
- ▌ Refund Processor · majiayu000 bundleProcess a refund request by gathering context and preparing the refund workflow.
- ▌ Repo Maintenance · majiayu000 bundleUse when triaging or maintaining the eslint-custom-rules repository.
- ▌ Resolve Findings · majiayu000 bundleChoose an implementation path (direct or plan) for evaluated findings and dispatch it. Direct path applies fixes directly; plan path runs /turboplan. Use after /evaluate-findings has tagged findings and they need to be implemented, or when the user asks to "resolve findings", "apply evaluated findings", or "dispatch findings to implementation".
- ▌ Simstim Workflow · majiayu000 bundleOrchestrate the complete Loa development cycle (PRD → SDD → Sprint → Implementation)
- ▌ Spec Kit Specify · majiayu000 bundleUse when a Spec Kit feature needs `spec.md` authored or rewritten from natural-language requirements, especially when the feature has no usable specification or requirements are too vague for planning.
- ▌ Specsafe Explore · majiayu000 bundlePre-spec exploration. Research and spike before creating formal spec.
- ▌ Talk Stage3 Concepts · majiayu000 bundleStage 3 — Build a numbered, scored concept catalogue. Every concept gets HIGH / MEDIUM / LOW talk-potential rating.
- ▌ Talk Stage4 Position · majiayu000 bundleStage 4 — Strategic angles, titles, descriptions, peer feedback draft. Includes mandatory CHECKPOINT before script can start.
- ▌ Talk Stage6 Revision · majiayu000 bundleStage 6 — Revision sheets for during and after the talk. Master concept table, Q&A cheat-sheet, glossary, external resources.
- ▌ Statute Analysis · majiayu000 bundleStatute and regulation interpretation framework. Use when reading statutes, classifying requirements, analyzing operative keywords, applying canons of construction, or mapping compliance obligations from legislative text.
- ▌ Sync Demo Seeder · majiayu000 bundleSynchronizes scripts/seed-demo.sql with the current Drizzle schema and migrations. Use this skill whenever a new migration is added or src/lib/db/schema.ts changes, to keep the demo dataset consistent with the database structure.
- ▌ Task Skill Name · majiayu000 bundleCollection of independent tasks for [domain]. Use when performing specific operations in this domain.
- ▌
- ▌ Unified Taskflow · majiayu000 bundle【强制】复杂任务管理系统。 AI 必须在遇到以下情况时**先读取此 SKILL.md**，再执行任何操作： - 多文件变更、规划设计、新功能开发 - 用户说"帮我想想/重构/升级/实现" 禁止使用内置 agentic_mode 的 artifact 目录处理复杂任务，必须使用项目根目录下的 .taskflow/ 目录。
- ▌ Update Practices · majiayu000 bundleProcess the practices inbox, evaluate, incorporate into dotforge, and suggest propagation to projects.
- ▌ Upstream Tracker · majiayu000 bundleManage upstream issue tracking for this project. Use when the user wants to log a bug or friction point in a vendor package or npm dependency, review open upstream items, resolve a tracked issue, run a trend review, generate the upstream observations section of a sprint retrospective, promote upstream observations to Basic Memory, discover known friction from other projects, or track a contribution opportunity. Trigger phrases: 'upstream', 'track this', 'vendor issue', 'log this bug', 'review upstream', 'trend review', 'cross-vendor', 'this is a bug in X', 'promote to memory', 'promote upstream', 'sync from memory', 'known friction', 'resolved upstream', 'mark as fixed', 'tool issue', 'action bug', 'contribution opportunity', 'upstream this', 'contribute back', 'upstreamable', or any mention of friction with an external package.
- ▌ Workflow Diagram · majiayu000 bundleGenerates a Mermaid workflow diagram showing process steps, decisions, and state transitions. Use when documenting CI/CD pipelines or lifecycle processes.
- ▌ Workflow Tooling · majiayu000 bundleUse the workflow utilities and validation scripts when editing workflow JSON or serialization logic.
- ▌ Wuerfel Aufbauen · majiayu000 bundleBaut die dreidimensionale Wuerfel-Struktur fuer ein neues Pruefprojekt auf — drei Achsen: Spalten (Datenpunkte als Spaltenprompts) Zeilen (Dokumente mit optionalen Zeilenprompts) Arbeitsblaetter (Perspektiven wie Recht / Steuer / Wirtschaft / Datenschutz / IT / Betrieb). Erzeugt das Wuerfel-Schema `wuerfel-schema.yaml` mit allen drei Achsen Ankerpunkten Materialitaetsschwellen Spaltenprompt-Bibliotheksverweisen und Belegkette-Konventionen. Vorlauf zu jedem Reviewlauf. Geeignet fuer M&A-DD Vendor-Onboarding Immobilienportfolios Arbeitsvertrags-Stapel und Eigenwuerfel.
- ▌ Zoho Desk Triage · majiayu000 bundlePull open tickets from [Zoho Desk](https://composio.dev/toolkits/zoho-desk) and triage by priority and department
- ▌ AI Writing Tropes · majiayu000 bundleComprehensive catalog of AI writing patterns that make text feel machine-generated.
- ▌ Alphaear Reporter · majiayu000 bundlePlan, write, and edit professional financial reports; generate finance chart configurations. Use when condensing finance analysis into a structured output.
- ▌ Article Writer Jp · majiayu000 bundleJapanese tech article writer with non-duplicate H2/H3 structure design, content generation, and image TODO placeholders. Triggers on requests for 記事作成, 記事を作って, 記事を書いて, 〇〇の記事, テック記事, 解説記事, ブログ記事作成.
- ▌ Cre Lender Credit · majiayu000 bundleCRE Lender/Credit analysis suite - 8 specialist skills for U.S. CRE loan screening and sizing, sponsor and appraisal review, credit memo writing, annual risk rating, covenant and watchlist monitoring, problem loans, and portfolio stress testing.
- ▌ Create Comparison · majiayu000 bundleCreate a comparison article (X vs Y) that helps readers choose.
- ▌ Enhanced Markdown · majiayu000 bundleGuide LLMs to output markdown that fully utilizes Markdown Viewer extension rendering capabilities including Mermaid, Vega-Lite, Infographic, DOT diagrams, and HTML styling for maximum human readability.
- ▌ Event Copywriting · majiayu000 bundleWrite compelling copy for events including conferences, webinars, workshops, galas, and trade shows. Use for: event naming and branding, event descriptions, save-the-date communications, invitation copywriting, speaker and session descriptions, registration page copy, event email sequences, post-event communications, and sponsorship proposals.
- ▌ Fiction Architect · majiayu000 bundleUse when constructing plot structure, story arcs, or narrative frameworks.
- ▌ Landing Copy Hero · majiayu000 bundleUse whenever `landing-copywriter` drafts the section directly beneath the locked headline — the subhead/lede that makes the headline's claim credible. Trigger when the section's role is "hero support" in `landing-sequencer`'s list, distinct from the headline itself (`landing-copy-headline`) or the problem/agitation section (`landing-copy-problem`).
- ▌ Landing Page Copy · majiayu000 bundleWrite landing page copy with attention to the hero, value proposition, social proof, objection handling, and conversion-focused CTAs. Use this skill whenever the user wants to write a landing page, sales page, hero section, or any conversion-focused web copy. Triggers on landing page, sales page, hero copy, value proposition, headline, subheadline, hero section, CTA copy, conversion copy, opt-in page, squeeze page. Also triggers when the user has a marketing campaign or product launch needing dedicated conversion copy.
- ▌
- ▌ Minimalism Driven · majiayu000 bundleEnforce minimalism as doctrine while authoring code: start from the null solution and gate every addition on a named, demonstrated need before it is written. Use when starting an implementation where scope creep, speculative abstraction, or unneeded surface is a risk, or when the user says "minimal", "bare minimum", or "no gold-plating".
- ▌ Motion To Dismiss · majiayu000 bundleDrafts FRCP 12(b) motions to dismiss for commercial litigation. Triggers on requests to draft motions to dismiss, 12(b)(6) motions, jurisdictional challenges, venue motions, or pre-answer dispositive motions during the pleadings phase.
- ▌
- ▌ Narrative Writing · majiayu000 bundleExtract narrative structure entities from text. Use when analyzing stories, chapters, acts, episodes, prologues, epilogues, plot branches, campaigns, events, and story arc progression.
- ▌ Ppw Repo To Paper · majiayu000 bundleScan an experiment repo and generate a complete paper outline (H1/H2/H3) with user approval checkpoints at each level, then generate body text with evidence annotations, citations, and bilingual output. Python ML repos. 扫描实验仓库，逐级生成论文大纲（H1/H2/H3），每级用户确认后推进， 然后生成带证据标注、引用和双语输出的正文文本。
- ▌ Sales Copywriting · majiayu000 bundleSales Copywriting is the strategic craft of writing persuasive content specifically designed to drive conversions, generate leads, and close sales.
- ▌ Writing Hugo Blog · majiayu000 bundleCreate Hugo blog posts in Chinese. Triggers when user asks to write a blog post, create a draft article, or convert research into blog format. Follows a structured workflow: explore blog config, understand content formats, gather topic requirements, generate draft, and review writing quality.
- ▌ Youtube Companion · majiayu000 bundleWrite Substack newsletters that accompany YouTube videos. Use when user has a YouTube video (transcript, outline, or link) and needs the companion newsletter with video embed, summary sections, and resources. Different from standalone newsletters - these drive to and summarize video content.
- ▌ Agent Output Formats · majiayu000 bundleStandardized output formats for research, planning, implementation, and review agents. Use when generating agent outputs or parsing agent responses.
- ▌ Agentskill Expertise · majiayu000 bundleAgent Skill design knowledge base — mechanisms, philosophy, patterns, pitfalls. Use when: designing new skills, reviewing skill quality, or deciding whether something should be a skill.
- ▌ AI Agent Development · majiayu000 bundleAI agent development workflow for building autonomous agents, multi-agent systems, and agent orchestration with CrewAI, LangGraph, and custom agents. Use when designing or implementing AI agents.
- ▌
- ▌ Auto Review Loop LLM · majiayu000 bundleAutonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".
- ▌
- ▌ Deepagents Subagents · majiayu000 bundle在 Deep Agents 中使用 SubAgentMiddleware 启动子代理进行任务委托、上下文隔离和专门工作。
- ▌ Langgraph Functional · majiayu000 bundleLangGraph Functional API with @entrypoint and @task decorators. Use when building workflows with the modern LangGraph pattern, enabling parallel execution, persistence, and human-in-the-loop.
- ▌
- ▌ Ralph Autonomous Dev · majiayu000 bundleEnables autonomous development loops that run until all tasks pass. Use when the user says "until done", "keep going", "finish this", "終わるまでやれ", or requests long-running autonomous iteration with fix_plan.md tracking.
- ▌
- ▌ Add Ollama Provider · majiayu000 bundleRoute a NanoClaw agent group to a local Ollama model instead of the Anthropic API. Ollama speaks the Anthropic API natively (v1/messages), so no provider code changes are needed — just env var overrides and a model setting. Use when the user wants to run their agent locally, cut API costs, or experiment with open-weight models. See docs/ollama.md for background.
- ▌ AI Collab Protocols · majiayu000 bundleSurface in-task-collaboration protocols when the user describes an AI workflow informally — URL-as-entity-reference, PR-comment threads as session memory. Trigger when the user names entities by colloquial label instead of stable URL, asks "how should I structure this for Claude", or describes a multi-step Claude workflow without a durable handle. Apply reactively, not as a checklist.
- ▌ AI Evaluation Suite · majiayu000 bundleComprehensive AI/LLM evaluation toolkit for production AI systems. Covers LLM output quality, prompt engineering, RAG evaluation, agent performance, hallucination detection, bias assessment, cost/token optimization, latency metrics, model comparison, and fine-tuning evaluation. Includes BLEU/ROUGE metrics, perplexity, F1 scores, LLM-as-judge patterns, and benchmarks like MMLU and HumanEval.
- ▌ Anthropic Sdk Guide · majiayu000 bundleGuide for Anthropic Python/TypeScript SDK usage including messages API, streaming, prompt caching, batches, token counting, and error handling. Use when the user is building with the Anthropic API, setting up Claude SDK, calling messages endpoints, implementing streaming, or troubleshooting API errors.
- ▌ Cache Cost Tracking · majiayu000 bundleLLM cost tracking with Langfuse for cached responses. Use when monitoring cache effectiveness, tracking cost savings, or attributing costs to agents in multi-agent systems.
- ▌ Cc Cost Engineering · majiayu000 bundleAI Agent 成本工程 — 基於 Claude Code 的成本追蹤、prompt cache 最佳化、token 預算控制逆向分析。Use when: 優化 token 消耗、設計成本控制機制、分析 cache 效率、選擇模型配置。
- ▌ Codex Retrospective · majiayu000 bundleUse when you want Codex to review its own recent history (last N days or specific period) and improve its behavior. Produces minimal, high-signal updates to AGENTS.md and tiny reusable skills. The goal is long-term fluency — Codex gradually becomes better at your specific style, constraints, and workflows.
- ▌ Elevenlabs Remotion · majiayu000 bundleGenerate professional voiceovers using ElevenLabs AI. Use when the user needs to create voiceovers for videos, audio narration, or text-to-speech content. Supports multiple voices with character presets (narrator, salesperson, expert) for natural delivery. Includes single scene regeneration for fine-tuning.
- ▌ Langchain Ecosystem · majiayu000 bundleComplete guide for LangChain, LangGraph, and Deep Agents development. Covers framework selection, agents, tools, RAG, middleware, graphs, persistence, HITL, subagents, and memory. Triggers when code imports langchain/langgraph/deepagents, or user asks about building AI agents, RAG pipelines, stateful graphs, human-in-the-loop workflows, or agent orchestration.
- ▌ Langchain Streaming · majiayu000 bundleStream outputs from LangChain agents and models - includes stream modes, token streaming, progress updates, and real-time feedback
- ▌ Langgraph Streaming · majiayu000 bundle从 LangGraph 流式传输实时更新：流式模式（values、updates、messages、custom、debug）用于响应式 UX
- ▌ LLM Model Selection Skill · majiayu000 bundleChoosing the right model for the task — power vs. cost vs. speed.
- ▌ Moai AI Nano Banana · majiayu000 bundleNano-Banana AI service integration for content generation, image creation, and AI-powered workflows. Use when integrating AI services for content creation.
- ▌ N8n Syntax AI Nodes · majiayu000 bundleUse when building AI or LLM workflows in n8n v1.x (v1.19.4+). Prevents incorrect sub-node wiring by mismatching NodeConnectionTypes. Covers agent nodes (6 types), chain nodes, tool nodes, memory backends (8 types), vector stores (11 types), output parsers, text splitters, retrievers, AI sub-node connections (12 NodeConnectionTypes), langchain integration, RAG patterns, and human-in-the-loop. Keywords: n8n, AI nodes, LLM, langchain, RAG, vector store, agents.
- ▌ Orchardcore AI Chat · majiayu000 bundleSkill for configuring AI Chat in Orchard Core using the CrestApps AI Chat module. Covers chat profiles, admin chat UI, frontend chat widgets, provider connections, and the AI Agent module for task automation.
- ▌ Phoenix Arize Setup · majiayu000 bundleArize Phoenix observability platform setup for LLM debugging and evaluation
- ▌ Prompting Leitfaden · majiayu000 bundlePrompting-Leitfaden für juristische KI-Nutzung in Kanzleien: Anwendungsfall Anwalt oder Mitarbeitende wollen KI effektiver nutzen und benoetigen praxiserprobte Prompt-Methoden. Mandantenkommunikation mit KI, Anwaltsgeheimnis beim Prompten. Prüfraster Vier-Elemente-Methode Zielformulierung Ausgabeformat Hintergrundwissen Beispiel, Rollenanweisung, Schritt-fuer-Schritt-Methode, Iteration, Zitate-Verifikation. Output Prompting-Leitfaden mit Vorlagen und Checkliste für juristische Aufgabentypen. Abgrenzung zu Halluzinations-Handhabung und zu Compliance-Regelsatz.
- ▌ Query Decomposition · majiayu000 bundleQuery decomposition for multi-concept retrieval. Use when handling complex queries spanning multiple topics, implementing multi-hop retrieval, or improving coverage for compound questions.
- ▌ Text Classification · majiayu000 bundleDesign and validate LLM-based text classification. Use for codebooks, prompts, validation samples, agreement statistics, and reporting model-coded data.
- ▌ Token Usage Monitor · majiayu000 bundleBuild and share a visual dashboard for OpenClaw token usage, model cost comparison, and recent model change timeline. Use when user asks token usage check, model cost tracking, or usage comparison.
- ▌ Adversarial Training · majiayu000 bundleDefensive techniques using adversarial examples to improve model robustness and security
- ▌
- ▌ Building RAG Systems · majiayu000 bundleBuild production RAG systems with LangChain orchestration and Qdrant vector store. Covers 8 RAG architectures (Simple, HyDE, CRAG, Self-RAG, Agentic), document processing, semantic chunking, retrieval chains, and evaluation with LangSmith/RAGAS. Use when implementing RAG pipelines, semantic search, or AI knowledge systems. NOT for simple keyword search.
- ▌ Embedding Strategies · majiayu000 bundleSelect and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
- ▌ Feature Store Design · majiayu000 bundleOnline/offline feature serving, point-in-time correctness, Feast patterns, and feature computation design.
- ▌ Hugging Face Trackio · majiayu000 bundleTrack and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API) or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, HF Space syncing, and JSON output for automation.
- ▌ Interview Cheatsheet · majiayu000 bundleGenerate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch PyTorch code, comparison tables, and 25 高频面试题 (L1 必会 / L2 进阶 / L3 顶级 lab). Cross-model codex review checks math, code, historical citations, and style discipline; then /render-html produces a single-file HTML with academic-newspaper template. Output: docs/tutorials/<slug>_tutorial.{md,html,review.json}. Use when the user says '写面试 cheat sheet', '写一份 X 教程', '帮我准备 Y 面试题', '出一份 X 速查', or wants a 600-1000 line Chinese tutorial on a specific ML topic.
- ▌ Model Card Generator · majiayu000 bundleModel documentation skill for generating model cards following Google's model card framework.
- ▌ Explainability · majiayu000 bundleSee the main Model Explainability skill for comprehensive XAI coverage.
- ▌ Technology Selection · majiayu000 bundleGuides technology selection and implementation of AI and ML features in .NET 8+ applications using ML.NET, Microsoft.Extensions.AI (MEAI), Microsoft Agent Framework (MAF), GitHub Copilot SDK, ONNX Runtime, and OllamaSharp. Covers the full spectrum from classic ML through modern LLM orchestration to local inference. Use when adding classification, regression, clustering, anomaly detection, recommendation, LLM integration (text generation, summarization, reasoning), RAG pipelines with vector search, agentic workflows with tool calling, Copilot extensions, or custom model inference via ONNX Runtime to a .NET project. DO NOT USE FOR projects targeting .NET Framework (requires .NET 8+), the task is pure data engineering or ETL with no ML/AI component, or the project needs a custom deep learning training loop (use Python with PyTorch/TensorFlow, then export to ONNX for .NET inference).
- ▌ Transport Properties · majiayu000 bundleThis skill group covers first-principles calculation of electronic transport properties using the Boltzmann transport equation (BTE) within the constant relaxation time approximation (CRTA). The workflow uses Quantum ESPRESSO for the underlying DFT calculation and BoltzTraP2 for solving the BTE. VASP-based workflows are also documented for sites with VASP access.
- ▌
- ▌