AI & ML

majiayu000 Bundle

Analyzes task/feature complexity (1-10) and recommends subtask breakdown for planning and prioritization. Provides actionable recommendations for agent selection, phase distribution, and risk assessment. Silent analysis that feeds into other workflows.

majiayu000 Bundle

Persistent memory for PACT agents. Save context, goals, lessons learned, decisions, and entities. Semantic search across sessions. Use when: saving session context, recalling past decisions, searching lessons. Triggers: memory, save memory, search memory, lessons learned, remember, recall

majiayu000 Bundle

Use when coordinating multiple AI agents in real-time - provides inter-agent messaging via Rust PTY wrapper with file-based protocol and reliability features

majiayu000 Bundle

Run a deliberative two-model committee between GPT-5.5 and Claude Opus 4.8, chaired by Fable 5. Same two deliberating members as model-committee; the difference is the chair — Fable 5 aggregates the scores, applies the tie rule, and synthesizes the decision, so a lightweight, fast Claude-family chair handles the tally and synthesis while the heavier reasoning stays with the two members. Use when the user needs one consequential decision from multiple defensible options and wants a Fable-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

Create, schedule, run, and debug MotherDuck Flights — Python jobs that run on MotherDuck compute. Use whenever someone wants to create a flight, schedule a Python script or recurring job on MotherDuck, set up scheduled ingestion from Postgres, dlt sources, S3, BigQuery, Snowflake, or APIs, refresh aggregates or transformations on a cron, or operate flights with get_flight_guide, create_flight, run_flight, flight logs, secrets, schedules, and versions.

majiayu000 Bundle

Research and configure new/custom AI models not yet in models.dev. Use when user mentions a new model release, asks to add a model from a non-standard provider, or wants to configure a custom/self-hosted model. Triggers: "new model", "just released", "configure [model name]", "add [provider] model", "set up [model]", custom endpoints, self-hosted models, bleeding-edge releases.

majiayu000 Bundle

Optimize and analyze work items for LLM-assisted development

majiayu000 Bundle

Use when working with Jakarta EE — JAX-RS endpoints, CDI/EJB services, JPA/Hibernate, WildFly deployment

majiayu000 Bundle

Sync skills (symlinks) and MCP settings from Claude to Gemini CLI and Codex CLI

majiayu000 Bundle

LLM council/panel voting: multi-model coders, consensus rules, inter-rater agreement (kappa, alpha), correlated-error diagnostics.

majiayu000 Bundle

Fix Elixir/Phoenix code until Codex CLI review comes back clean — bounded review, fix, verify loop before opening a PR. Use when codex is installed and you want an external cross-model critic on your changes before pushing.

majiayu000 Bundle

Audit experiment integrity before claiming results. Uses cross-model review (GPT-5.4) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says "审计实验", "check experiment integrity", "audit results", "实验诚实度", or after experiments complete before writing claims.

majiayu000 Bundle

Enforces zero-tolerance code quality policy using Clippy with strict lints, all warnings treated as errors

majiayu000 Bundle

Operate MotherDuck from a terminal with the MotherDuck CLI. Use when a coding agent or developer needs shell-based authentication, structured query output, or file-oriented Dive and Flight authoring; use MCP instead for chat-only exploration and inline results.

majiayu000 Bundle

Generate agent-ready prompts from existing task specification files. Use when regenerating prompts after editing tasks, updating prompt templates, or preparing tasks for cpo execution.

majiayu000 Bundle

Executes comprehensive test suite across unit, integration, E2E, database, protocols, and intelligence algorithms

majiayu000 Bundle

Validates Model Context Protocol (MCP) compliance by running official compliance test suite against Pierre server

majiayu000 Bundle

Use when working with route.ts files, API endpoints, server actions, or web backend logic in the monorepo

majiayu000 Bundle

Best practices for writing Claude Code skills, CLAUDE.md files, and prompts optimized for Opus 4.5. Use when creating or reviewing skills, writing agent instructions, or optimizing prompts for Claude 4.x models.

majiayu000 Bundle

Adds Microsoft Copilot Studio connector to a Power Apps code app. Use when invoking Copilot Studio agents, sending prompts to agents, or integrating agent responses.

majiayu000 Bundle

Access up-to-date, version-specific documentation and code examples from Context7. Use this skill to verify library and framework details.

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

Explain MotherDuck pricing and ROI tradeoffs. Use when an economic_buyer, technical_owner, or analytics_lead is asking about spend, budget guardrails, workload cost drivers, plan fit, or whether MotherDuck is worth adopting.

majiayu000 Bundle

Never Use TaskOutput

majiayu000 Bundle

Build a live MotherDuck dashboard as a Dive. Use when composing one shareable KPI, trend, and breakdown story over existing MotherDuck data, especially when the result should stay a saved workspace artifact rather than a full application.

majiayu000 Bundle

用于生成可投稿级别图件的元技能。当需要创建期刊投稿图（如多面板布局、显著性标注、误差条、色盲友好配色，以及符合特定期刊格式要求，如 Nature、Science、Cell）时使用。该技能可统筹调用 matplotlib / seaborn / plotly 并应用投稿级绘图风格。若仅用于快速探索性分析，直接使用 seaborn 或 plotly 即可。

majiayu000 Bundle

Verify OrcaFlex model results against industry standards (DNV, API, ISO). Perform capacity checks, safety factor verification, and compliance reporting for offshore structures.

majiayu000 Bundle

Posts finalized review comments to GitHub as a pending review after critique iteration is complete.

majiayu000 Bundle

Provides MoAI-ADK foundational principles including TRUST 5 quality framework, SPEC-First DDD methodology, delegation patterns, progressive disclosure, and agent catalog reference. Use when referencing TRUST 5 gates, SPEC workflow, EARS format, DDD methodology, agent delegation patterns, or MoAI orchestration rules. Do NOT use for context and token management (use moai-foundation-context instead) or strategic analysis (use moai-foundation-philosopher instead).

majiayu000 Bundle

GitHub Copilotカスタマイゼーションファイル（プロンプト、エージェント、インストラクション、スキル）の作成ガイド。.prompt.md、.agent.md、.instructions.md、SKILL.mdファイルをVS Codeのベストプラクティスに従って作成する際に使用してください。

majiayu000 Bundle

Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns.

majiayu000 Bundle

Auto-invoke WHEN: Writing Claude Code commands, hooks, or skills. Creating prompts for sub-agents. Optimizing LLM outputs. Designing production prompt templates. Do NOT invoke WHEN: General coding tasks. Reading/debugging code. Running commands.

majiayu000 Bundle

Use Context Hub (chub) for curated, versioned API/SDK docs and agent skills. Keep OpenAI tasks on official docs first (via `openai-docs` in Codex).

majiayu000 Bundle

Complete implementation guide for Cloudflare Vectorize - a globally distributed vector database for building semantic search, RAG (Retrieval Augmented Generation), and AI-powered applications with Clo

majiayu000 Bundle

Dynamic agent composition and management system. USE WHEN user says create custom agents, spin up custom agents, specialized agents, OR asks for agent personalities, available traits, agent voices. Handles custom agent creation, personality assignment, voice mapping, and parallel agent orchestration.

majiayu000 Bundle

Use when completing tasks, implementing major features, or before merging to verify work meets requirements