AI & ML

majiayu000 Bundle

Commit code after each logical unit of work is complete Use when configuring AI agent workflows and patterns. Agent Behavior category skill.

majiayu000 Bundle

🖥️ Claude Code Only - Requires terminal access to execute Gemini CLI commands.

majiayu000 Bundle

Meta-skill for improving and optimizing prompts using Anthropic's prompt engineering best practices. Provides the 4-step improvement workflow (example identification, initial draft, chain of thought refinement, example enhancement), keyword registries for documentation lookup, and decision trees for improvement strategies. Use when improving prompts, optimizing for accuracy, adding chain of thought reasoning, structuring with XML tags, enhancing examples, or iterating on prompt quality. Delegates to docs-management skill for official prompt engineering documentation.

majiayu000 Bundle

Data science and machine learning platform functions for the East language (TypeScript types). Use when writing East programs that need optimization (MADS, Optuna, SimAnneal, Scipy), machine learning (XGBoost, LightGBM, NGBoost, Torch MLP, Lightning, GP), ML utilities (Sklearn preprocessing, metrics, splits), conformal prediction (MAPIE), or model explainability (SHAP). Triggers for: (1) Writing East programs with @elaraai/east-py-datascience, (2) Derivative-free optimization with MADS, (3) Bayesian optimization with Optuna, (4) Discrete/combinatorial optimization with SimAnneal, (5) Gradient boosting with XGBoost or LightGBM, (6) Probabilistic predictions with NGBoost or GP, (7) Neural networks with Torch MLP or Lightning, (8) Data preprocessing and metrics with Sklearn, (9) Conformal prediction intervals with MAPIE, (10) Model explainability with Shap.

majiayu000 Bundle

Complete guide for Google Gemini API using the CORRECT current SDK (@google/genai v1.27+, NOT the deprecated @google/generative-ai). Covers text generation, multimodal inputs (text + images + video + audio + PDFs), function calling, thinking mode, streaming, and system instructions with accurate 2025 model information (Gemini 2.5 Pro/Flash/Flash-Lite with 1M input tokens, NOT 2M). Use when: integrating Gemini API, implementing multimodal AI applications, using thinking mode for complex reasoning, function calling with parallel execution, streaming responses, deploying to Cloudflare Workers, building chat applications, or encountering SDK deprecation warnings, context window errors, model not found errors, function calling failures, or multimodal format errors. Keywords: gemini api, @google/genai, gemini-2.5-pro, gemini-2.5-flash, gemini-2.5-flash-lite, multimodal gemini, thinking mode, google ai, genai sdk, function calling gemini, streaming gemini, gemini vision, gemini video, gemini audio, gemini pdf, syste

majiayu000 Bundle

Optimal patterns for MiniMax MCP tools (web_search + understand_image)

majiayu000 Bundle

Evaluate and update Pollinations user tiers. Check balances, upgrade devs, batch process users. For finding users with errors, see model-debugging skill first.

majiayu000 Bundle

Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging

majiayu000 Bundle

Portable visual skill pack for the Agent Skills ecosystem (Claude Code, Claude Desktop, Claude Cowork, Claude Design, Goose, Cursor, Codex). Discovers community-published styles + formats via the gooseworks CLI, runs an extract-style workflow on reference images, and exports rendered PNGs via Playwright.

majiayu000 Bundle

CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.

majiayu000 Bundle

Coordinates Claude agent teams via filesystem protocol. Use when orchestrating parallel agents with task dependencies. Do not use for single-agent tasks.

majiayu000 Bundle

Run a deliberative two-model committee between GPT-5.5 and Claude Opus 4.8, chaired by GPT-5.6 "Sol." Same two deliberating members as model-committee; the difference is the chair — Sol aggregates the scores, applies the tie rule, and synthesizes the decision. Use when the user needs one consequential decision from multiple defensible options and wants a Sol-chaired deliberation. Suitable for architecture, research design and interpretation, manuscript strategy, ambiguous diagnosis, evaluation design, and policy or standards tradeoffs. Not for factual lookups, independent-coder reliability, open-ended brainstorming, routine implementation, or final high-stakes professional judgment.

majiayu000 Bundle

Use when the user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD". Extracts a DDD-style glossary from the current conversation into UBIQUITOUS_LANGUAGE.md, flags ambiguities and synonyms, and proposes opinionated canonical terms.

majiayu000 Bundle

Structured file enumeration and content analysis for understanding codebase structure before reviews or refactoring. Triggers: file analysis, codebase structure, directory mapping, hotspot detection, code exploration, file enumeration, structure mapping, module boundaries Use when: before architecture reviews to understand file organization, exploring unfamiliar codebases to map structure, estimating scope for refactoring or migration DO NOT use when: general code exploration - use the Explore agent. DO NOT use when: searching for specific patterns - use Grep directly. Provides structural context for downstream review and refactoring workflows.

majiayu000 Bundle

Expert in Metro bundler configuration, optimization, troubleshooting, caching strategies, custom transformers, asset management, source maps, bundling performance. Activates for metro, metro bundler, metro.config.js, bundler, bundle, cache, transformer, asset resolver, metro cache, bundling error, unable to resolve module, port 8081.

majiayu000 Bundle

Create standard SuperCollider audio effects for Bice-Box (delays, reverbs, filters, distortions). Provides templates, ControlSpecs, common patterns, and MCP workflow for safely creating/updating effects.

majiayu000 Bundle

Build stateless MCP servers with TypeScript on Cloudflare Workers using @modelcontextprotocol/sdk. Provides patterns for tools, resources, prompts, and authentication (API keys, OAuth, Zero Trust). Use when exposing APIs to LLMs, integrating Cloudflare services (D1, KV, R2, Vectorize), or troubleshooting export syntax errors, unclosed transport leaks, or CORS misconfigurations.

majiayu000 Bundle

Workout block model, types, and operations. Use when building workouts, managing block kinds (strength/AMRAP/EMOM/Tabata/ForTime/cardio), handling sets/reps, or working with workout persistence and be

majiayu000 Bundle

Run a structured team health assessment. Use when asked to run a team health check, assess team morale, facilitate a team retrospective on ways of working, or evaluate team dynamics. Produces a health assessment across key dimensions with RAG status, underlying signals, and prioritised improvement actions.

majiayu000 Bundle

Analyzes project requirements to identify missing skills and automatically creates them. Enforces MCP Code Execution pattern for skills that use external tools. This skill should be used when starting a new project to ensure all required skills exist.

majiayu000 Bundle

End-to-end verification for the site-visit (Step 7) flow. Use when you need to reproduce or validate that the system reaches the site-visit prompt/options and can proceed to confirmation, either via deterministic backend-only traces (manual_ux_scenario_I/H) or via browser UI checks (Playwright/MCP).

majiayu000 Bundle

Use when writing E2E tests with Playwright, setting up test infrastructure, or debugging flaky browser tests. Invoke for browser automation, E2E tests, Page Object Model, test flakiness, visual testin

majiayu000 Bundle

Upgrade Obsidian wikis to latest format. Handles structure migration (phases/tasks → workstreams/specs), comment format upgrades (adding emoji prefixes), and LWW source-of-truth model. Use when user mentions "upgrade wiki", "migrate wiki", "update wiki format", or has old-format comments.

majiayu000 Bundle

Explains how to add and debug playwright MCP tools and CLI commands.

majiayu000 Bundle

Enforces workflow discipline across ALL projects. Ensures Claude checks for specialized agents before responding, announces skill/agent usage, and creates TodoWrite todos for multi-step tasks. Activates on every session start. Triggers: automatic on all sessions, "use the right agent", "follow workflow".

majiayu000 Bundle

Guide for using claude CLI in headless mode with --print, output formats, and JSON schema

majiayu000 Bundle

Gemini CLI for one-shot Q&A, summaries, and generation.

majiayu000 Bundle

Fast LLM inference with Groq API - chat, vision, audio STT/TTS, tool use. Use when: groq, fast inference, low latency, whisper, PlayAI TTS, Llama, vision API, tool calling, voice agents, real-time AI.

majiayu000 Bundle

Creates structured output formats (JSON/YAML/Markdown-KV/XML) and response style scope configurations via accuracy-token tradeoff analysis. Use when defining agent schemas, building CLAUDE.md output sections, configuring hierarchy overrides, or standardizing serialization patterns across agents/commands.

majiayu000 Bundle

Compresses verbose responses by removing filler and framing to save 200-400 tokens. Use when responses feel bloated or context is filling fast.

majiayu000 Bundle

Asymmetric time dilation for MCP operations - deliberate slow paths enable capability accumulation through Cat# bicomodule composition.

majiayu000 Bundle

Use when coordinating multi-agent work with dependencies, parallel workstreams, or complex handoffs requiring milestone tracking

majiayu000 Bundle

Analyze workflow patterns using the Agent Monitor's workflow intelligence API — orchestration DAGs, tool flow transitions, subagent effectiveness, model delegation patterns, error propagation by depth, concurrency lanes, compaction impact, and agent co-occurrence. Produces prioritized optimization recommendations with quantified impact.

majiayu000 Bundle

Gemini CLI delegation workflow implementing delegation-core for Google's Gemini models. Triggers: gemini cli, gemini delegation, google gemini, 1M context, large file analysis, gemini batch, gemini summarization, gemini extraction Use when: delegation-core selected Gemini, need Gemini's 1M+ token context window, batch processing or large document summarization required DO NOT use when: deciding which model to use - use delegation-core first. DO NOT use when: gemini CLI not installed or authenticated. Consult this skill when implementing Gemini-specific delegation workflows.

majiayu000 Bundle

Expert guidance for creating, building, and using Claude Code subagents and the Task tool. Use when working with subagents, setting up agent configurations, understanding how agents work, or using the Task tool to launch specialized agents.

majiayu000 Bundle

Deep bug investigation using consultant agent. Identifies root causes and fix suggestions.