AI & ML

majiayu000 Bundle

Launch a Streamlit GUI for Task Master tasks.json editing. Use when users want a visual interface instead of CLI/MCP commands.

majiayu000 Bundle

Detects common LLM coding agent artifacts in codebases. Identifies test quality issues, dead code, over-abstraction, and verbose LLM style patterns. Use when cleaning up AI-generated code or reviewing for agent-introduced cruft.

majiayu000 Bundle

Use when user asks to leverage claude or claude code to do something (e.g. implement a feature design or review codes, etc). Provides non-interactive automation mode for hands-off task execution without approval prompts.

majiayu000 Bundle

Operate an AI agent inside OpenClaw World over HTTP IPC. Use when tasks involve registering or reconnecting an agent, moving, chatting, forming alliances, running turn-based combat, checking world phase/state, or handling survival and betting commands.

majiayu000 Bundle

Create PydanticAI agents with type-safe dependencies, structured outputs, and proper configuration. Use when building AI agents, creating chat systems, or integrating LLMs with Pydantic validation.

majiayu000 Bundle

Discover and follow recipes via MCP resources for setup guides, skills, and cookbooks. The meta-skill for using fullstackrecipes effectively.

majiayu000 Bundle

Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, and streaming row updates. Designed to work alongside HF MCP server for comprehensive dataset workflows.

majiayu000 Bundle

Autonomous p5.js visualization agent. It implements, inspects, critiques design/UX, fixes, and launches the result.

majiayu000 Bundle

Operational prompt engineering patterns, templates, and validation flows for Claude Code.

majiayu000 Bundle

Repo navigation and “where do I start?” guide for OpenEvent-AI. Use when an agent/dev is lost, needs an overview of the project or a subsystem, or needs pointers to the most important docs, entrypoints, scripts, and tests without rescanning the entire codebase.

majiayu000 Bundle

Automatic workflow suggestion and utility agent routing based on prompt analysis. Trigger keywords: auto-detect, intent, suggest, trigger, routing, workflow detection, utility agents, prompt analysis, smart routing

majiayu000 Bundle

Central authority for managing Claude Code user configuration directories (~/.claude/ and ~/.claude.json). Covers storage cleanup, backup/restore, reset workflows, MCP server preservation, history management, plan management, session statistics, and configuration health auditing. Delegates to docs-management skill for official documentation. Use when managing user config, cleaning up storage, backing up settings, resetting Claude Code, or auditing configuration health.

majiayu000 Bundle

Search local Claude Code documentation to answer implementation questions. Use when asked about Claude Code features, subagents, workflows, skills, hooks, MCP servers, plugins, settings, CLI options, headless mode, or any Claude Code capability.

majiayu000 Bundle

Identify and document model hyperparameters from papers. Use when setting up training configurations.

majiayu000 Bundle

Guide for building concurrent, fault-tolerant systems using OTP (GenServer, Supervisor, Task, Agent) and Elixir concurrency primitives

majiayu000 Bundle

Add a persistent wiki knowledge base to a NanoClaw group. Based on Karpathy's LLM Wiki pattern. Triggers on "add wiki", "wiki", "knowledge base", "llm wiki", "karpathy wiki".

majiayu000 Bundle

Analyze ML model architecture from papers and code. Use when understanding model structure for implementation.

majiayu000 Bundle

AI-powered NK cell therapy design for cancer immunotherapy including CAR-NK engineering, memory-like NK generation, and KIR/HLA matching optimization.

majiayu000 Bundle

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.

majiayu000 Bundle

World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development. Expertise in Claude, GPT-4, prompt design patterns, few-shot learning, chain-of-thought, and AI evaluation. Includes RAG optimization, agent design, and LLM system architecture. Use when building AI products, optimizing LLM performance, designing agentic systems, or implementing advanced prompting techniques.

majiayu000 Bundle

Build temet-run TUI components following project patterns for daemon monitoring, agent management, and observability integration. Use when implementing agent dashboards, status displays, log viewers, multi-agent layouts, IPC integration, and OpenTelemetry instrumentation in Textual widgets. Specific to temet-run's architecture and requirements.

majiayu000 Bundle

Multi-agent code analysis orchestration using claudemem. Share claudemem output across parallel agents. Enables parallel investigation, consensus analysis, and role-based command mapping.

majiayu000 Bundle

所有 35+ 個 MCP 工具的完整參考，包含參數說明和使用範例。

majiayu000 Bundle

Create parametric OpenSCAD 3D models of workshop tools (drill presses, vacuums, saws, etc.) for workshop layout planning. Use when asked to "model a tool", "create OpenSCAD for [tool]", "add [tool] to workshop", or when planning workshop layouts that need tool representations. Supports brand-accurate colors (Bosch, Festool, Makita, DeWalt, Milwaukee) and standardized code structure with customizer parameters.

majiayu000 Bundle

Front door for agent automation — decide the SHAPE (Workflow vs NTM vs skill), then hand off. Triggers: "build automation", "convert skills to workflows", "which shape".

majiayu000 Bundle

Standardized reference documentation section structure for agents - project guidance, conventions, related agents, and Skills. Use when implementing or updating agent documentation.

majiayu000 Bundle

Show AgentOps next action.

majiayu000 Bundle

Autonomous 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".

majiayu000 Bundle

Use when creating llmring.lock file for new project (REQUIRED for all applications), configuring model aliases with semantic task-based names, managing environment-specific profiles (dev/staging/prod), or setting up fallback models - lockfile creation is mandatory first step, bundled lockfile is only for llmring tools

majiayu000 Bundle

Hook Development Rules

majiayu000 Bundle

Automated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical data (e.g., deception detection, content analysis). Combines literature insights with data-driven hypothesis testing. For manual hypothesis formulation use hypothesis-generation; for creative ideation use scientific-brainstorming.

majiayu000 Bundle

Validates Jira projects and boards exist, creates missing resources automatically. Smart enough to prompt user to select existing or create new projects. For boards, accepts either IDs (validates existence) or names (creates boards and updates .env with IDs). NEW - Per-project configuration support - JIRA_BOARDS_{ProjectKey} for hierarchical board organization across multiple projects. Activates for jira setup, jira validation, jira configuration, missing jira project, missing jira boards, jira .env setup, per-project boards.

majiayu000 Bundle

This skill should be used when the user wants to file their tax return electronically via the 確定申告書等作成コーナー (NTA Tax Return Preparation Corner) using Claude in Chrome, Antigravity Browser Sub-Agent, or Playwright CLI (fallback). It guides the browser-based input of calculated tax data. Trigger phrases include: "e-Tax提出", "電子申告", "e-Taxで申告", "作成コーナーに入力", "確定申告書等作成コーナー", "作成コーナー", "申告書を提出".

majiayu000 Bundle

Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.

majiayu000 Bundle

This sop guides you through the process of transforming a rough idea into a detailed design document with an implementation plan and todo list. It follows the Prompt-Driven Development methodology to systematically refine your idea, conduct necessary research, create a comprehensive design, and develop an actionable implementation plan. The process is designed to be iterative, allowing movement between requirements clarification and research as needed.

majiayu000 Bundle

The Planning Skill generates and optimizes Product Requirements Documents (PRDs) and Implementation Plans as AI artifacts - file-based context caches optimized for AI agent consumption rather than human reading.