Claude Skills by majiayu000

Activate autonomous Ralph Wiggum loop mode for iterative task completion. Use when you have a well-defined task with clear completion criteria that benefits from persistent, autonomous execution.

Use after first code change. Autonomous iteration until all quality gates pass (max 7 iterations).

Setup the Ralph autonomous AI coding loop - ships features while you sleep

Autonomous feature development loop. Executes complete 9-phase cycle (Interview -> Think Critically -> Plan -> Branch -> Implement -> Verify -> PR -> Merge -> Wrap-Up) with minimal human intervention. Triggers on "/ralph", "start autonomous loop", "run ralph loop".

Start a Ralph Wiggum autonomous task loop that keeps Claude working until a task is complete. Uses the Stop hook pattern to re-inject prompts when Claude tries to exit before finishing. Supports two completion strategies: promise-based (Claude outputs a completion token) and file-movement-based (task file moves to /Done). Use when a multi-step task requires Claude to iterate until completion, such as processing all items in /Needs_Action or generating a complete audit.

Ralph Wiggum-inspired automation loop for specification-driven development. Orchestrates task implementation, review, cleanup, and synchronization using a Python script. Use when: user runs /loop command, user asks to automate task implementation, user wants to iterate through spec tasks step-by-step, or user wants to run development workflow automation with context window management. One step per invocation. State machine: init → choose_task → implementation → review → fix → cleanup → sync →...

Iterative development loop methodology for autonomous AI work. Configure self-correcting coding loops that iterate until completion criteria are met, integrate with Archon for task tracking, and support multiple execution modes. Use when running autonomous coding sessions, implementing self-correcting workflows, or building iterative development pipelines.

Execute an autonomous development loop that picks one task per iteration, implements it, verifies it, and commits the result — each iteration in a fresh context window. Use when user runs /ralph, mentions "ralph loop", "autonomous loop", "builder verifier", "run tasks automatically", "iterate on tasks", "develop autonomously", or wants an automated build-verify-commit cycle with task tracking.

Ralph Loop plugin manager. Provides start, cancel, status, and help commands for autonomous task loops. Enforces safety guardrails (sandbox, deny rules, PR-only, max-iterations). Use /ralph-loop:start to begin, /ralph-loop:cancel to stop.

Autonomous agent loop for completing features. Use when asked to 'use ralph', 'ralph this', or to autonomously implement a feature end-to-end. Creates prd.json with user stories, then executes them one by one until complete.

Ralph autonomous coding loop with MiniMax subagent delegation. Managed loop (not recursive) with progress tracking, completion detection, and circuit breakers.

Run RALPH autonomous development loop to implement features from the PRD.

Run RALPH autonomous development loop to implement features from the PRD.

Run RALPH autonomous development loop with multi-agent pipeline

Run long-running autonomous AI agents using PRD-based task scoping.

Set up automated agent-driven development with Ralph. Run AI agents in a loop to implement features from user stories, verify acceptance criteria, and log progress for the next agent.

Use only when the user explicitly invokes `$ralph-specum`, requests Ralph Specum in Codex, asks Ralph Specum to handle a named phase, or explicitly requests autonomous or quick mode or continuation without pauses.

Execute iterative development loop through user stories. Implements one story at a time with quality gates, commits, and learning persistence. Ships features autonomously.

Run ralph-tui task loops for automated PRD execution. Covers headless mode, PRD preparation, agent selection (opencode/claude), session management, and troubleshooting. Use when asked to "run ralph-tui", "execute PRD tasks", or "start a ralph session".

AI agent loop orchestrator for autonomous task execution - coding, content, any multi-step work

Ralph Wiggum: Project Manager — Continuous ticket consumption, code review, and work generation loop. Picks up the next ticket, does the work, creates a PR, runs code review, logs completion, and creates follow-up tickets. Use when asked to start the loop, consume tickets, or grind through work.

Autonomous task completion loop with PRD tracking and LLM memory

Autonomous TDD development loop with parallel agent swarm, category evolution, and convergence detection. Use when running autonomous game development, quality improvement loops, or comprehensive codebase reviews.

Next-generation autonomous development orchestrator with cognitive feedback loops. Executes complex multi-step features from PRDs through iterative agent sessions with quality verification, context synthesis, and recursive learning. Use when implementing features that require multiple stories, exceed single context windows, or need autonomous execution with quality guarantees. Replaces manual iteration with intelligent orchestration.

Autonomous AI coding orchestration using the Ralph Wiggum technique and Ralphy CLI. This skill should be used when running AI agents in continuous loops until tasks complete, orchestrating multi-task development with PRD/YAML files, configuring parallel agent execution, or implementing the Ralph Wiggum autonomous development methodology. Triggers on mentions of ralphy, ralph, autonomous loops, PRD-driven development, or multi-agent orchestration.

專責處理 RIF (Required Behavior Frame) 類型的需求。讀取規格目錄結構，生成/審查 Event Handler 設計與實作。支援冪等性、重試、死信佇列。

Classify any user request into a structured format for prompt generation. Use this skill whenever you need to understand what type of task a request represents, determine complexity, decide whether planning is needed, or route a request to the right skills and agent strategy. Trigger on: any request that needs to be analyzed before generating a Claude Code prompt, when someone says 'classify this', 'what kind of task is this', when the prompt-generator or prompt-router skills need input class...

Research agent for external documentation, best practices, and library APIs via MCP tools

Risk management and constitutional compliance specialist. Ensures all trading decisions comply with constitutional limits and manages portfolio risk. Integrates Constitution Article 4 (Risk Management).

Builds AI agents using OpenAI Agents SDK with async/await patterns and multi-agent orchestration. Use when creating tutoring agents, building agent handoffs, implementing tool-calling agents, or orchestrating multiple specialists. Covers Agent class, Runner patterns, function tools, guardrails, and streaming responses. NOT when using raw OpenAI API without SDK or other agent frameworks like LangChain.

Builds AI agents using OpenAI Agents SDK with async/await patterns and multi-agent orchestration. Use when creating tutoring agents, building agent handoffs, implementing tool-calling agents, or orchestrating multiple specialists. Covers Agent class, Runner patterns, function tools, guardrails, and streaming responses. NOT when using raw OpenAI API without SDK or other agent frameworks like LangChain.

Builds AI agents using OpenAI Agents SDK with async/await patterns and multi-agent orchestration. Use when creating tutoring agents, building agent handoffs, implementing tool-calling agents, or orchestrating multiple specialists. Covers Agent class, Runner patterns, function tools, guardrails, and streaming responses. NOT when using raw OpenAI API without SDK or other agent frameworks like LangChain.

Builds AI agents using OpenAI Agents SDK with async/await patterns and multi-agent orchestration. Use when creating tutoring agents, building agent handoffs, implementing tool-calling agents, or orchestrating multiple specialists. Covers Agent class, Runner patterns, function tools, guardrails, and streaming responses. NOT when using raw OpenAI API without SDK or other agent frameworks like LangChain.

Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases.

Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases.

Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.

Autonomous fix-verify workflow for Script Kit GPUI. Use when fixing bugs, making changes, or completing tasks. Covers the mandatory build-test-verify loop, logging modes, and session completion protocol.

Autonomous skill creator for Claude Code CLI. Uses multi-phase orchestrated workflow with Task tool subagents to research domains, design architecture, generate content, and validate quality. Creates production-ready skills following Anthropic's Agent Skills specification.

Darwin Gödel Machine patterns for self-improving AI agents with open-ended

Core behavioral guidelines and interaction patterns for the agent. This skill provides the foundation for how the agent should communicate and behave across all interactions. Use this skill to establish consistent behavior patterns at the beginning of a session. The skill defines tone, proactivity level, and request handling strategies that should be applied throughout the session. THIS SKILL HAS HIGH PRIORITY - always load at session start and re-trigger periodically to avoid behavioral drif...

Universal init prompt — every agent spawned into an AgentOps repo runs `ao session bootstrap` first.

Autonomous pipeline monitor using sense-think-act loop. Watches snakemake/nextflow jobs, detects errors, applies fixes from memory, restarts on failure.

Sibyl Codex 独立第三方审查 - 使用 OpenAI Codex 提供不同 AI 视角的评审

Sibyl Codex 写作 agent - 使用 Codex (GPT-5) 撰写论文

Sibyl 比较分析者 agent - 对标 SOTA 和同类工作，定位结果贡献

Sibyl 反对者 agent - 挑战主流假设，寻找反面证据和盲点

Sibyl 批评者 agent - 苛刻但公正的学术批评

Sibyl 编辑 agent - 整合论文各章节为完整稿件

Sibyl 实验执行 agent - 编写代码并在远程 GPU 上执行实验

Sibyl 终审 agent - NeurIPS/ICML 级别的论文终审