Chalk Labs
Need help deploying ralph?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/1molchuan-ralph
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/ralph
What's inside
- Skill name
ralph- Description
- 持久化执行-验证-修复循环,直到任务完成
- License
- MIT
- Instructions
- 50 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# oh-my-ccg Ralph Mode
"The boulder never stops." Persistent loop that keeps working until verification passes.
## Activation
Trigger: "ralph", "don't stop"
## Loop Structure
```
Start (iteration 0)
│
├─ Execute: Run the task (executor agent)
├─ Verify: Check results (verifier agent)
│ ├─ Tests pass?
│ ├─ Build succeeds?
│ └─ LSP clean?
│
├─ All pass? → COMPLETE ✅
└─ Any fail? → Fix issues → Next iteration
└─ Max iterations (10)? → STOP with report
```
## Implementation Steps
1. Initialize ralph state: iteration=0, maxIterations=10
2. Execute the current task using executor agent
3. Run verification:
- `npm test` or equivalent
- `tsc --noEmit`
- LSP diagnostics check
4. If verification passes: mark complete, deactivate ralph
5. If verification fails:
- Increment iteration
- Analyze failures with debugger agent
- Apply fixes
- Return to step 2
6. If max iterations reached: stop, report remaining issues
## State
Tracked in `.oh-my-ccg/state/ralph-state.json`:
- iteration, maxIterations
- lastVerification (tests, build, lsp, issues)
- active flag
## Integration
- Works inside autopilot (auto-impl uses ralph per task)
- Works standalone for any execution task
- Stop hook prevents Claude from stopping while ralph is activeFrom 1molchuan/oh-my-ccg, MIT.
More from 1molchuan/oh-my-ccg
- 0.423score
oh-my-ccg-init
1molchuan
初始化 oh-my-ccg 环境 — 验证 MCP 服务器、Codex、Gemini
SkillDFreshness: D★ 1Claude Code +9 - 0.420score
deepinit
1molchuan
深度代码库初始化,生成分层 AGENTS.md 文档
SkillDFreshness: D★ 1Claude Code +9 - 0.420score
doctor
1molchuan
诊断和修复 oh-my-ccg 安装问题
SkillDFreshness: D★ 1Claude Code +9 - 0.420score
help
1molchuan
oh-my-ccg 帮助与使用指南
SkillDFreshness: D★ 1Claude Code +9 - 0.420score
note
1molchuan
保存会话笔记到记事本,防止上下文压缩丢失
SkillDFreshness: D★ 1Claude Code +9 - 0.420score
oh-my-ccg-impl
1molchuan
RPI 实施阶段 — 按零决策计划机械执行
SkillDFreshness: D★ 1Claude Code +9 - 0.420score
oh-my-ccg-research
1molchuan
RPI 研究阶段 — 需求转化为约束集
SkillDFreshness: D★ 1Claude Code +9 - 0.420score
oh-my-ccg-review
1molchuan
独立双模型交叉审查(随时可用)
SkillDFreshness: D★ 1Claude Code +9 - 0.420score
team
1molchuan
并行团队执行,N 个协调 Worker 协作
SkillDFreshness: D★ 1Claude Code +9 - 0.420score
trace
1molchuan
显示 Agent 流程追踪时间线与摘要
SkillDFreshness: D★ 1Claude Code +9 - 0.420score
autopilot
1molchuan
全自动 RPI 执行 — 从想法到可运行代码
SkillDFreshness: D★ 1Claude Code +9 - 0.420score
setup
1molchuan
oh-my-ccg 初始安装向导
SkillDFreshness: D★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 1
- Open issues
- 1
- Last commit (this folder)
- Feb 23, 2026 (8 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/1molchuan/oh-my-ccg
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from 1molchuan
- 0.423score
oh-my-ccg-init
1molchuan
初始化 oh-my-ccg 环境 — 验证 MCP 服务器、Codex、Gemini
SkillDFreshness: D★ 1Claude Code +9 - 0.420score
doctor
1molchuan
诊断和修复 oh-my-ccg 安装问题
SkillDFreshness: D★ 1Claude Code +9 - 0.420score
help
1molchuan
oh-my-ccg 帮助与使用指南
SkillDFreshness: D★ 1Claude Code +9 - 0.420score
note
1molchuan
保存会话笔记到记事本,防止上下文压缩丢失
SkillDFreshness: D★ 1Claude Code +9 - 0.420score
oh-my-ccg-impl
1molchuan
RPI 实施阶段 — 按零决策计划机械执行
SkillDFreshness: D★ 1Claude Code +9 - 0.420score
deepinit
1molchuan
深度代码库初始化,生成分层 AGENTS.md 文档
SkillDFreshness: D★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get ralph running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
ralph skill. Agent Mart. https://agentmart.dev/skills/1molchuan-ralph (last updated 2026-10-24)