AI & ML

majiayu000 Bundle

Planning agent that creates implementation plans and handoffs from conversation context

majiayu000 Bundle

Activates the Pickle Rick persona. Use this ONLY when the user explicitly requests to start the "Pickle Rick" mode or loop. DO NOT use this for general greetings (e.g., "hi") normal assistance.

majiayu000 Bundle

Use Playwright MCP to check UI styles and usability. Automatically used for requests like "check UI", "verify appearance", "take screenshot".

majiayu000 Bundle

Cheapskate Skill

majiayu000 Bundle

A/B test CLAUDE.md instruction changes against eval benchmarks. Capture baselines, test variants, compare results.

majiayu000 Bundle

Deep generative models for single-cell omics. Use when you need probabilistic batch correction (scVI), transfer learning, differential expression with uncertainty, or multi-modal integration (TOTALVI, MultiVI). Best for advanced modeling, batch effects, multimodal data. For standard analysis pipelines use scanpy.

majiayu000 Bundle

Compile a small, deterministic StyleSeed rule bundle for one agent, output grammar, surface adapter, domain, page type, brand recipe, palette recipe, and optional profile. Use before setup or build, when STYLESEED.md changes, when updating StyleSeed, or whenever an agent would otherwise load the full rule handbook.

majiayu000 Bundle

Build 3D web apps with Three.js (WebGL/WebGPU). 556 searchable examples, 60 API classes, 20 use cases. Actions: create 3D scene, load model, add animation, implement physics, build VR/XR. Topics: GLTF loader, PBR materials, particle effects, shadows, post-processing, compute shaders, TSL. Integrations: WebGPU, physics engines, spatial audio.

majiayu000 Bundle

Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of ~4 extra LLM turns.

majiayu000 Bundle

Run a multi-agent review of changed files for reuse, quality, efficiency, and clarity issues followed by automated fixes. Use when the user asks to "simplify code", "review changed code", "check for code reuse", "review code quality", "review efficiency", "simplify changes", "clean up code", "refactor changes", or "run simplify".

majiayu000 Bundle

Run a multi-agent review of changed files for reuse, quality, efficiency, clarity, and altitude issues followed by automated fixes. Use when the user asks to "simplify code", "review changed code", "check for code reuse", "review code quality", "review efficiency", "simplify changes", "clean up code", "refactor changes", or "run simplify".

majiayu000 Bundle

Run a multi-agent review of code comments and markdown documentation for unnecessary content, then fix the issues. Covers what-restating comments, name-mirroring doc comments, status-update prose, and other documentation noise. Use when the user asks to "simplify docs", "simplify documentation", "clean up comments", "clean up docs", "review documentation", "strip unnecessary comments", "reduce doc noise", or "run simplify-docs".

majiayu000 Bundle

Add Ollama MCP server so the container agent can call local models and optionally manage the Ollama model library.

majiayu000 Bundle

Background task scheduler for Pi and Claude Code. Register, list, and run scheduled jobs. Supports cron syntax and one-shot triggers.

majiayu000 Bundle

Enforces decisive decision-making. Search best practices, decide on ONE option, provide reasoning. NEVER ask user to choose.

majiayu000 Bundle

Route natural language requests to appropriate skills and workflows. Use when relevant to the task.

majiayu000 Bundle

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

majiayu000 Bundle

Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.

majiayu000 Bundle

Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead.

majiayu000 Bundle

Search arXiv for papers and extract knowledge into memory. Use `search` to find papers, `learn` to extract knowledge.

majiayu000 Bundle

Guide to the math cognitive stack - what tools exist and when to use each

majiayu000 Bundle

GitHub CLI Agent Session Extension

majiayu000 Bundle

Maintain a wiki-style world bible for collaborative fiction. Use for long-running story worlds, shared universes, membership sites, or any fiction requiring persistent canonical reference.

majiayu000 Bundle

Modular Code Organization

majiayu000 Bundle

Create and manage MotherDuck data shares for zero-copy data distribution. Use when sharing databases with team members, other organizations, or making data publicly available.

majiayu000 Bundle

AI agent orchestration board for task visualization and team coordination.

majiayu000 Bundle

Multi-role requirement analysis and task breakdown workflow using 4 specialized AI agents (PM, UX, Tech, QA). Each agent conducts web research before analysis to gather industry best practices, case studies, and current trends. Supports Quick Mode (parallel, ~3 min, one Q&A session) and Deep Mode (serial, ~8 min, Q&A after EACH agent so answers inform subsequent analysis). Triggers on 'foreman-spec', 'spec feature', 'break down requirement', 'define tasks', 'spec this'.

majiayu000 Bundle

Load data into MotherDuck from local files, object storage, HTTPS, dataframes, or external databases. Use when choosing a MotherDuck-specific ingestion path, especially CTAS and INSERT...SELECT, bulk loading, secrets, and Postgres-endpoint versus DuckDB-client tradeoffs.

majiayu000 Bundle

Model system responsibilities across clients, servers, and optional peer-to-peer nodes for traditional distributed applications. Triggers: client-server, web architecture, mobile backend, API design, thin client, thick client, peer-to-peer, P2P, offline-first, synchronization Use when: traditional web/mobile applications with centralized services, clear separation between client and server responsibilities needed DO NOT use when: selecting from multiple paradigms - use architecture-paradigms first. DO NOT use when: peer-to-peer dominates - consider dedicated P2P patterns. Consult this skill when designing client-server systems or API architectures.

majiayu000 Bundle

Final code/plan review using Codex. Use as the last review step after sonnet and opus.

majiayu000 Bundle

Search, filter, and retrieve Claude/Codex history indexed by the automem 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

Create git commits with user approval and no Claude attribution

majiayu000 Bundle

Stage meaningful diffs and create commits with WHY-focused messages. Use when agent needs to commit code changes.

majiayu000 Bundle

Jira ticket creation and management for AI agent commands, with severity-based processing and proper integration

majiayu000 Bundle

Claude Code CLI commands, flags, headless mode, and automation patterns

majiayu000 Bundle

Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.