By 2lab-ai
Implements Spec-Trace-Verify (STV) methodology for traced development: transforms requirements into specs and vertical traces with contract tests, automates bundling/execution of unfinished scenarios, implements code to pass tests, debugs via traces, and verifies PRs with 3D checks for completeness, correctness, and coherence.
npx claudepluginhub 2lab-ai/oh-my-claude --plugin stv유저의 요구가 불명확할때 트리거. 애매한 요청, 다의적 지시, 범위 불분명한 작업에서 Context Brief를 생성하여 명확화한다.
Trigger this skill in any situation where code behaves differently from expectations like "why does this happen", "find the bug", "form a hypothesis", "follow the callstack", "trace back from the result". Even without the explicit word "debugging", trigger on symptom reports.
Autonomous work execution on STV-traced scenarios. Selects unfinished scenarios from trace.md, implements via stv:work, loops until done or user input needed.
Create Excalidraw diagram JSON files that make visual arguments. Use when the user wants to visualize workflows, architectures, or concepts.
Problem space exploration mode. Stance, not workflow. Read-only codebase investigation before committing to spec. Triggers on 'explore this', 'investigate', 'understand the problem', 'what are we dealing with', 'before we spec this'.
Trigger when 유저가 뭔가 일을 시키거나, 하이 레벨 컨셉을 이야기 할 경우, 유저의 지시에 여러 가지 암묵지가 느껴질 경우.
Propose new features when all trace scenarios are complete or backlog is too small. Reviews completed work and project context, then applies stv:new-task to create spec + trace for chosen feature.
STV Phase 1: Proposal (WHY) -> Feature interview -> spec.md. PRD + Architecture decisions in one pass. Uses decision-gate to minimize questions. Supports non-linear flow (Actions not Phases) and Update vs New decision tree.
Meta-skill for designing methodologies, skills, and processes from experience. Triggers on "I want to turn this into a methodology", "organize this pattern", "systematize my approach", "make this into a skill", "structure this as a process". Use when the user mentions real-world experience and wants to structure/systematize/formalize it. Not top-down design from theory, but bottom-up distillation that strips away the unnecessary from what actually worked.
STV Phase 2: spec.md -> vertical trace + RED contract tests. Traces every API scenario through all layers with 7-section format and parameter transformation arrows. Supports Delta Specs change tracking for trace evolution over time.
This skill should be used when the user asks to "visualize data", "render a chart", "plot numbers", "show a graph in terminal", "create a bar chart", "make a sparkline", "draw a heatmap", or needs to display numeric data as terminal charts using chartli. Also triggers on "chartli", "terminal chart", "ASCII chart", "braille chart".
Triggers on "check the PR", "is it implemented per the issue", "compare spec vs implementation", "compare JIRA and PR", "verify", "validate". Final checkpoint before PR merge using 3-dimensional verification (Completeness, Correctness, Coherence).
Decide what to work on next by scanning docs/*/trace.md for unfinished scenarios, then routing to what-we-have-to-work or plan-new-task.
Bundle unfinished trace scenarios into up to three candidate work chunks, present options with rationale, and get user confirmation before starting do-work execution.
STV Phase 3: Implementation (GREEN) + Trace Verify loop. Implements code to pass contract tests, then verifies implementation matches trace document. Supports non-linear flow — returning to spec/trace when implementation reveals errors in earlier artifacts.
____ _ _ __ ____ __ _____ _ _
/ __ \| | | | | \/ \ \ / / / ____| | | |
| | | | |__| |_____| \ / |\ \_/ /_____| | | | __ _ _ _ __| | ___
| | | | __ |_____| |\/| | \ /______| | | |/ _` | | | |/ _` |/ _ \
| |__| | | | | | | | | | | | |____| | (_| | |_| | (_| | __/
\____/|_| |_| |_| |_| |_| \_____|_|\__,_|\__,_|\__,_|\___|
[!CAUTION] EXPERIMENTAL PROJECT - This plugin runs autonomous AI loops that can consume significant tokens. Mind your token usage!
/ultraworkand/deepworkwill iterate until completion. Use--max-iterationsto set limits. You have been warned.
Claude Code plugin for AI-powered iterative development loops.
Inspired by oh-my-opencode and Ralph Wiggum.
/plugin marketplace add 2lab-ai/oh-my-claude
/plugin install oh-my-claude@oh-my-claude
/plugin install powertoy@oh-my-claude
Required: Run
/oh-my-claude:setupafter installation.
oh-my-claude uses your Gemini CLI and Codex CLI subscriptions (not API keys).
# 1. Run setup to check dependencies
/oh-my-claude:setup
# 2. Login to each service
gemini auth login # Opens browser for Google auth
codex auth # Opens browser for OpenAI auth
# 3. Verify everything works
/oh-my-claude:setup
Once authenticated, agents use your existing subscriptions:
Ralph loop with 3 specialized AI agents for autonomous development.
[!IMPORTANT] Requires YOLO mode:
claude --dangerously-skip-permissions
/ultrawork "Build REST API for users"
Agents:
Loop exits when task is genuinely complete.
Same as ultrawork, but requires 9.5+ score from all three reviewers (GPT-5.2, Gemini-3, Opus-4.5) before completion.
/deepwork "Critical security fix" --max-iterations 50
Save work context in one tool and resume in another.
# In Claude Code: save your work
/save
# In Gemini CLI or Codex: resume the work
/load
Cross-tool workflow example:
/save when done/load to continue./docs/tasks/save/To enable cross-tool commands:
./install-cross-session-commands.sh
This installs /save, /load, /list-saves, /check to:
~/.gemini/commands/ (Gemini CLI)~/.codex/prompts/ (Codex)| Command | Description |
|---|---|
/ultrawork | Multi-agent autonomous work loop |
/deepwork | Work loop with triple AI review gate (GPT-5.2 + Gemini-3 + Opus-4.5, all ≥9.5) |
/save | Save work context |
/load <id> | Load saved context |
/list-saves | List all saved contexts |
/check [all|id] | Verify archived saves completion |
/cancel-work | Cancel active loop |
/setup | Verify dependencies |
| Hook | Description |
|---|---|
| auto-title.sh | Auto-generate session titles (Claude Haiku) |
| play-sound.sh | Play sound on session end (macOS) |
Bundled MCP servers:
| Server | Package |
|---|---|
| gemini | @2lab.ai/gemini-mcp-server |
| claude | @2lab.ai/claude-mcp-server |
| codex | codex mcp-server |
Q: Will this burn my tokens?
A: Yes. That's the feature, not a bug.
/\_/\
( o.o ) "I'm helping!"
> ^ < - Your AI, iteration 47
| Version | Changes |
|---|---|
| 1.0.22 | Context window optimization - total plugin under 4k tokens |
MIT
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Use this agent when you need expert assistance with React Native development tasks including code analysis, component creation, debugging, performance optimization, or architectural decisions. Examples: <example>Context: User is working on a React Native app and needs help with a navigation issue. user: 'My stack navigator isn't working properly when I try to navigate between screens' assistant: 'Let me use the react-native-dev agent to analyze your navigation setup and provide a solution' <commentary>Since this is a React Native specific issue, use the react-native-dev agent to provide expert guidance on navigation problems.</commentary></example> <example>Context: User wants to create a new component that follows the existing app structure. user: 'I need to create a custom button component that matches our app's design system' assistant: 'I'll use the react-native-dev agent to create a button component that aligns with your existing codebase structure and design patterns' <commentary>The user needs React Native component development that should follow existing patterns, so use the react-native-dev agent.</commentary></example>
Team-oriented workflow plugin with role agents, 27 specialist agents, ECC-inspired commands, layered rules, and hooks skeleton.
UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.