В каталоге 183 730 навыков в 14 категориях.
Project-agnostic agent setup wizard for Ralph Orchestra with Quick Start, Standard, and Expert modes
Check all MCP servers and services before workflow execution. MUST pass before any Ralph command proceeds.
Generate auto-compact-resilient Ralph Wiggum loop prompts for Claude Code, with a PRD and progress file for large featur...
Use when a user has a rough prompt that needs a staged prompt-improvement workflow for `$ralph-wiggum-codex`, with saved...
Generate Ralph-compatible prompts for multiple related tasks. Creates phased prompts with sequential milestones, cumulat...
Generate Ralph-compatible prompts for entire projects from scratch. Creates comprehensive prompts with architecture phas...
Generate Ralph-compatible prompts for research, analysis, and planning tasks. Creates prompts with systematic research p...
Generate Ralph-compatible prompts for single implementation tasks. Creates prompts with clear completion criteria, autom...
Manual QA validation trigger for RALPH implementations
Use this skill after a ralph-code phase has completed but before marking the task as complete in SCOPES.yml
Resume RALPH execution from last checkpoint
Resume a PAUSED Ralph session — retry failed task, skip, or abort
Resume from saved session state after interruption or compaction. Recovers context from checkpoints and agent-memory.
Review RALPH worktree changes before merging
Interactive review of auto-generated Ralph artifacts. Use when user asks to "ralph review stories", "ralph review tasks"...
Run a sequential three-tier code review on a finished implementation branch — Haiku (surface) → Sonnet (logic) → Opus (d...
Rollback to a previous checkpoint
Run RALPH autonomous development loop to implement features from the PRD.
Run long-running autonomous AI agents using PRD-based task scoping.
Ralph-v2 session operations reference for schema validation, timeout recovery, and timestamp commands. Use when validati...
Set up automated agent-driven development with Ralph. Run AI agents in a loop to implement features from user stories, v...
Ralph-v2 live signal mailbox protocol for polling, ack handling, broadcast quorum, and signal routing. Use when a Ralph...
Self-improving review loop for Ralph Wiggum skills. Reviews skills against best practices, implements improvements, and...
Spawn parallel agents in git worktrees for automated feature implementation. Creates isolated development environments f...
Use only when the user explicitly invokes `$ralph-specum`, requests Ralph Specum in Codex, asks Ralph Specum to handle a...
This skill should be used only when the user explicitly asks to use `$ralph-specum-cancel`, or explicitly asks Ralph Spe...
This skill should be used only when the user explicitly asks to use `$ralph-specum-design`, or explicitly asks Ralph Spe...
This skill should be used only when the user explicitly asks to use `$ralph-specum-feedback`, or explicitly asks Ralph S...
This skill should be used only when the user explicitly asks to use `$ralph-specum-help`, or explicitly asks Ralph Specu...
This skill should be used only when the user explicitly asks to use `$ralph-specum-implement`, or explicitly asks Ralph...
This skill should be used only when the user explicitly asks to use `$ralph-specum-index`, or explicitly asks Ralph Spec...
This skill should be used only when the user explicitly invokes `$ralph-specum-prototype`, or explicitly asks Ralph Spec...
This skill should be used only when the user explicitly asks to use `$ralph-specum-refactor`, or explicitly asks Ralph S...
This skill should be used only when the user explicitly asks to use `$ralph-specum-requirements`, or explicitly asks Ral...
This skill should be used only when the user explicitly asks to use `$ralph-specum-research`, or explicitly asks Ralph S...
This skill should be used only when the user explicitly asks to use `$ralph-specum-start`, or explicitly asks Ralph Spec...
This skill should be used only when the user explicitly asks to use `$ralph-specum-status`, or explicitly asks Ralph Spe...
This skill should be used only when the user explicitly asks to use `$ralph-specum-switch`, or explicitly asks Ralph Spe...
This skill should be used only when the user explicitly asks to use `$ralph-specum-tasks`, or explicitly asks Ralph Spec...
This skill should be used only when the user explicitly asks to use `$ralph-specum-triage`, or explicitly asks Ralph Spe...
Monitor all active Ralph Wiggum agents and their progress. Shows iteration counts, gate status, and blocked tasks.
Display Ralph build status and progress. Use when user asks for "ralph status", "build status", "queue status", or wants...
This skill should be used when the user asks to "add a task for Ralph", "list Ralph tasks", "remove Ralph task", "setup...
The Ralph Wiggum technique for minimal, declarative prompts that enable loop-based autonomous execution.
Use this skill when writing tests, especially when working in TDD style to define tests before the actual functions are...
Run ralph-tui task loops for automated PRD execution. Covers headless mode, PRD preparation, agent selection (opencode/c...
AI agent loop orchestrator for autonomous task execution - coding, content, any multi-step work
Generate a Product Requirements Document (PRD) for ralph-tui task orchestration. Creates PRDs with user stories that can...
Long-running iterative development loops with pacing control and verifiable progress. Use when tasks require multiple it...
Ralph Wiggum iterative development loop methodology for persistent AI agent work. Implements continuous iteration loops...
Use when a task is well-defined, has an automatic way to verify success (tests, linter, build), and is tedious or large...
Autonomous AI coding loop for unattended development - lets Claude work continuously on tasks while you sleep, with mand...
Executa loops autonomos de desenvolvimento via tecnica Ralph Wiggum. Usar quando: (1) Iniciar loop Ralph na sessao atual...
Devil's advocate PRD/document reviewer with humor and sharp critique
Iterative development loop for solving complex tasks through trial-and-error. Use when you need to "fix until passing",...
Surgical Debugger & Code Optimizer. Autonomous root-cause investigation, persistence-loop fixing, and high-fidelity code...
Use when a coding task needs an objective-first long-running loop with fresh-context work and review phases, explicit ac...
Multi-step autonomous plan execution with bounded iteration (max 10), state persistence, dependency checking, error retr...
Ralph Wiggum: Project Manager — Continuous ticket consumption, code review, and work generation loop. Picks up the next...
Autonomous TDD development loop with parallel agent swarm, category evolution, and convergence detection. Use when runni...
Autonomous task completion loop with PRD tracking and LLM memory
Autonomous backlog processing workflow for Brain Dump. Use when working through multiple tickets autonomously or when as...
Next-generation autonomous development orchestrator with cognitive feedback loops. Executes complex multi-step features...
Start a ralph style looping session
Configure Claude Code, Codex CLI, and Gemini CLI for Ralph-style automation with fewer approval prompts while keeping pr...
Work on a single highest-priority feature from current_ documents, test it, update docs, and commit
Autonomous AI coding orchestration using the Ralph Wiggum technique and Ralphy CLI. This skill should be used when runni...
Iterative planning with Planner, Architect, and Critic until consensus
반복적 기획 합의 워크플로우. Planner가 계획을 수립하고, Architect가 구조를 검토하고, Critic이 비판적으로 평가하는 과정을 합의에 도달할 때까지 반복합니다. Use when planning com...
Use this skill when planning must prioritize correctness and risk control over speed.
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution
Alias for $plan --consensus
Embody Ram Dass - AI persona expert with integrated methodology skills
Expert on RAM subsystem for ES-1841. Provides guidance on memory map, DRAM refresh, parity checking, conventional memory...
Red Planet Labs Rama with Gay.jl deterministic coloring for 100x backend
rama-gay-zig skill
Write Python code in the style of Luciano Ramalho, author of Fluent Python. Emphasizes deep understanding of Python's da...
This skill provides guidance for Raman spectrum peak fitting tasks. It should be used when analyzing spectroscopic data,...
Ramanujan graphs and Alon-Boppana spectral optimality for edge growth
Generate a deep, gold-quality "journey" JSON for a single Ramco ERP activity (e.g. Create Direct PO, Edit & Approve PO,...
This prompt instructs an image model to generate an ultra-realistic, analog-flash, early-2000s bedroom snapshot in a 3:2...
Use when you must analyze the ideal ramjet cycle: compute the flight stagnation temperature from the speed of sound and...
Use when you must analyze the supersonic ramjet inlet: compute the diffuser total pressure recovery at the flight Mach n...
Student semester onboarding — clinic procedures, tool walkthrough, practice exercises before real cases. Reads the handb...
Read-only Ramp corporate spend: transactions, cards and card limits, users, departments. No spend actions by design. Tri...
Fetch and follow Ramp's published agent playbooks inside Paperclip, with mandatory approval gates for spend, incorporati...
学生学期导入——诊所程序、工具导览、真实案件之前的实践练习。 读取指导老师在设置时上传的手册并以互动方式教学。 当新诊所学生说"帮我导入""我是诊所新人""开始"，或每学期开始时使用； 传入 --card 获取一页参考卡。
Fetch and follow Ramp's published agent playbooks inside Geetorus, with mandatory approval gates for spend, incorporatio...
Ramp Automation: manage corporate card transactions, reimbursements, users, and expense tracking via the Ramp platform
Reduce Ramp integration workload and operating cost without losing financial completeness. Use when polling, storage, re...
Collect a minimal, safe Ramp API diagnostic bundle centered on trace IDs and reproducible contract evidence. Use when es...
Verify Ramp OAuth, environment, pagination, and monetary parsing with a bounded read-only transaction call. Use when che...
Implement a shared Ramp request budget with rolling-window throttling, bounded retries, pagination, and 504 recovery. Us...
Analyzes vendor spend data from Ramp and exports to connected systems. Use when user asks to "analyze vendor spend", "bu...
Run accessibility and visual design review
Run accessibility and visual design review on components. Use when reviewing UI code for WCAG compliance and design issu...
AgentDB integration specialist for RAN ML systems with vector storage, pattern recognition, and distributed training coo...
Causal inference and discovery for RAN optimization with Graphical Posterior Causal Models (GPCM), intervention effect p...
DSPy-based mobility optimization with temporal patterns, handover management, and 15% improvement target. Uses program s...
"Comprehensive RAN optimization with swarm coordination, cognitive consciousness, and 15-minute closed-loop autonomous c...