AI & ML

majiayu000 Bundle

Detect user's intent from their message and activate the right workflow silently.

majiayu000 Bundle

Detect and use llms.txt files for LLM-optimized documentation. Use when checking if a site has LLM-ready docs before scraping.

majiayu000 Bundle

Multi-agent investigation for stubborn bugs. Use when: going in circles debugging, need to investigate browser/API interactions, complex bugs resisting normal debugging, or when symptoms don't match expectations. Launches parallel agents with different perspectives and uses Chrome tools for evidence gathering.

majiayu000 Bundle

Agent Development Kit from Google

majiayu000 Bundle

Build with OpenAI's stateless APIs - Chat Completions (GPT-5.2, GPT-5.1, o3, o4-mini), Realtime API (voice), Batch API (50% savings), Embeddings, Images (DALL-E 3), Audio (Whisper + TTS), and Moderation. Node.js SDK and fetch for Cloudflare Workers. Use when: implementing chat with GPT-5.2/5.1/o3/o4-mini, Realtime voice API (WebSocket), Batch API for cost savings, xhigh reasoning (GPT-5.2), streaming responses, function calling/tools, structured outputs, embeddings for RAG, DALL-E 3 images, Whisper transcription, TTS (13 voices), or troubleshooting rate limits (429), API keys (401), streaming errors.

majiayu000 Bundle

Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports. Uses a fresh cross-model reviewer with web/DBLP/arXiv lookup to catch hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context citations (cite present but the cited paper does not establish the claim). Use when user says "审查引用", "check citations", "citation audit", "verify references", "引用核对", or before submission to ensure bibliography integrity.

majiayu000 Bundle

Fundamental reading and writing capability for the OCTAVE format. Inject this to give an agent basic structural competence without the overhead of full architectural specifications. Triggers on: octav

majiayu000 Bundle

This skill provides structured methodologies for identifying, analyzing, and mitigating security threats in system designs. Use it when designing new systems, reviewing existing architectures, or assessing security posture.

majiayu000 Bundle

Monitor dbt execution using the dbt Artifacts package. Use this skill when you need to track test and model execution history, analyze run patterns over time, monitor data quality metrics, or enable programmatic access to dbt execution metadata across any dbt version or platform.

majiayu000 Bundle

Debug MCP server issues and analyze logs for the Orient. Use this skill when investigating tool failures, API errors, slow operations, or troubleshooting MCP tool behavior. Covers log file locations, JSON log format, correlation IDs for request tracing, common debugging commands, and log rotation configuration.

majiayu000 Bundle

Use the gog CLI to interact with Google Workspace services (Calendar, Gmail, Tasks, Drive, Docs, Slides, Sheets). This skill is for coding agents that have Bash access and prefer CLI tools over MCP tools. Use when asked to check calendar, send emails, manage tasks, or access Google services from the terminal.

majiayu000 Bundle

Speech feedback to user via MCP audio servers. Use when providing status updates or asking questions.

majiayu000 Bundle

Expert prompt engineering and music generation with Suno AI v4.5+ for professional-quality songs across all genres with advanced composition techniques

majiayu000 Bundle

Use when you need to fine-tune(ファインチューニング) and optimize LangGraph applications based on evaluation criteria. This skill performs iterative prompt optimization for LangGraph nodes without changing the graph structure.

majiayu000 Bundle

Validates command frontmatter, delegation patterns, simplicity guidelines, and documentation proportionality. Use when reviewing, auditing, analyzing, evaluating, improving, or fixing commands, validating official frontmatter (description, argument-hint, allowed-tools, model), checking delegation clarity or standalone prompts, assessing simplicity guidelines (6-15 simple, 25-80 documented), validating argument handling, or assessing documentation appropriateness. Distinguishes official Anthropic requirements from custom best practices. Also triggers when user asks about command best practices, whether a command should be a skill instead, or needs help with command structure.

majiayu000 Bundle

Guide for writing, refactoring, and testing MoonBit projects. Use when working in MoonBit modules or packages, organizing MoonBit files, using moon tooling (build/check/run/test/doc/ide etc.), or following MoonBit-specific layout, documentation, and testing conventions.

majiayu000 Bundle

Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, constructing context from retrieved documents, adding citations, or implementing hybrid search.

majiayu000 Bundle

Use this skill when discussing technical topics Ryan has written about - OpenPKG, TypeScript tooling, agent-native architecture, documentation coverage. Provides deep context from his actual writings.

majiayu000 Bundle

MiniMax MCP server integration with token-efficient AI delegation. Use for web search, image analysis, MCP server integration in terminal/desktop Kimi Code CLI, and Claude-MiniMax collaboration patterns. Provides working scripts and slash commands.

majiayu000 Bundle

dbt command-line operations, model selection syntax, Jinja patterns, troubleshooting, and debugging. Use this skill when running dbt commands, selecting specific models, debugging compilation errors, using Jinja macros, or troubleshooting dbt execution issues.

majiayu000 Bundle

Import GGUF models from HuggingFace into Ollama. Pull models directly using the hf.co/ prefix, track download progress, and use imported models for inference.

majiayu000 Bundle

Use when creating editable technical diagrams with draw.io / diagrams.net sources, including architecture diagrams, ERD, UML, sequence diagrams, flowcharts, ML model diagrams, official shape lookup, brand symbols, Graphviz auto-layout, codebase structure maps, .drawio validation, or draw.io CLI export fallback. Do not use for ordinary raster image generation, freehand sketches, interactive canvas/Three.js scenes, or decorative SVG animation. Chinese triggers include draw.io, diagrams.net, 可编辑架构图, .drawio, ER 图, UML, 序列图, 自动布局, 形状检索, 代码结构图.

majiayu000 Bundle

Search, filter, and retrieve Claude/Codex history indexed by the memex CLI. Use when the user wants to index history, run lexical/semantic/hybrid search, fetch full transcripts, or produce LLM-friendly JSON output for RAG.

majiayu000 Bundle

PyTorch CUDA environment and performance guidance, with emphasis on CUDA 13 toolkit/driver requirements, PyTorch wheel compatibility, and runtime checks. Use when configuring PyTorch on NVIDIA GPUs, d

majiayu000 Bundle

This skill should be used when the user asks to "use serena", "semantic search", "symbol analysis", "find references", "code navigation", or needs Serena MCP guidance. Provides Serena tool usage patterns.

majiayu000 Bundle

This skill should be used when the user asks to "start working on issue", "what should I work on", "pick up task", "continue work", "find next task", "hand off", or "end session". Provides agent work session patterns for the FP CLI including claiming work, logging progress, and VCS-based change tracking.

majiayu000 Bundle

Enforces LLM-optimized style compliance for documentation and code. Use when creating/modifying markdown (headers, lists, Dictums, separators), code organization (comments, dividers, naming), or validating voice (grammar, tone, imperative phrasing) and formatting against taxonomy/whitespace standards.

majiayu000 Bundle

Chrome MCP browser testing. Console/network debugging, JS execution, GIF recording.

majiayu000 Bundle

How the devbox automatically updates llm-agents (claude-code) via GitHub Actions and systemd timers. Use when debugging update failures or understanding the update flow.

majiayu000 Bundle

Reconstruct a repository as cited entry-to-test flows, bounded claims, and a reusable baseline or verified delta. Triggers: "build a repository mental model", "trace this codebase", "refresh the prior recon".

majiayu000 Bundle

AI rules and SDK reference for writing tests with Stably Playwright SDK. Use this skill when writing or modifying Playwright tests with Stably AI features. Triggers on tasks involving toMatchScreenshotPrompt, agent.act(), page.extract(), or when deciding between Playwright vs Stably SDK methods. Includes best practices for AI assertions, extraction, and autonomous agents.

majiayu000 Bundle

Qwen CLI delegation workflow implementing delegation-core for Alibaba's Qwen models. Triggers: qwen cli, qwen delegation, alibaba qwen, qwen batch, multi-file analysis, qwen summarization, qwen extraction, 100K context Use when: delegation-core selected Qwen, need Qwen's large context capabilities, batch processing or multi-file analysis required DO NOT use when: deciding which model to use - use delegation-core first. DO NOT use when: qwen CLI not installed or configured. Consult this skill when implementing Qwen-specific delegation workflows.

majiayu000 Bundle

Work with markdown-based task lists in .llm/todo.md files. Use when managing tasks, working with todo lists, extracting incomplete tasks, marking tasks complete, or implementing tasks from a task list.

majiayu000 Bundle

This skill renders pages or specific regions (bounding boxes) of a PDF into PNG images. It is designed for human-agent collaboration workflows where the agent needs to show the human what it has detected (e.g., tables, figures) for verification or calibration.

majiayu000 Bundle

Token budget tracking and enforcement for Gastown convoy-level execution. Hard limits with pre-execution checking, per-convoy and per-agent tracking, structured stop reasons.

majiayu000 Bundle

AI capabilities in n8n - agents, LangChain, vector stores, LLM providers, RAG, AI workflows