Skip to content
Agentmart
Submit a tool

autopilot

全自动 RPI 执行 — 从想法到可运行代码

Skill by 1molchuan

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying autopilot?

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.

Book a call

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-autopilot

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.

We use your email only for this newsletter. Privacy

About

全自动 RPI 执行 — 从想法到可运行代码

No 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/autopilot

What's inside

Skill name
autopilot
Description
全自动 RPI 执行 — 从想法到可运行代码
License
MIT
Instructions
58 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# oh-my-ccg Autopilot

Full automatic RPI cycle: research → plan → impl → review.

## Activation
Trigger: "autopilot", "auto" + requirement description

## Workflow

### Phase 1: Initialize
- Use `rpi_state_write` MCP tool to create RPI state with requirement
- Verify Codex + Gemini availability via `ask_codex(prompt="ping")` and `ask_gemini(prompt="ping")` MCP calls
- Use `mode_state_write` MCP tool to start autopilot state tracking

### Phase 2: Auto-Research
- Run explore agent for codebase context
- Launch multi-model exploration **in parallel via MCP tools**:
  - `ask_codex(agent_role="analyst", background=true)` — backend constraints
  - `ask_gemini(agent_role="designer", background=true)` — frontend constraints
- Collect results via `check_job_status`
- Synthesize constraints automatically
- Present constraint summary to user for quick confirmation

### Phase 3: Auto-Plan
- Suggest /clear if context > 80%
- Run planner agent with constraints
- Cross-validate with dual-model **parallel MCP calls**:
  - `ask_codex(agent_role="planner", background=true)` — plan validation
  - `ask_gemini(agent_role="designer", background=true)` — frontend validation
- Generate zero-decision task list
- Update state via `rpi_state_write` MCP tool

### Phase 4: Auto-Impl
- Suggest /clear if context > 80%
- Route tasks via MCP tools:
  - Frontend tasks → `ask_gemini` for prototype, then executor rewrites
  - Backend tasks → `ask_codex` for prototype, then executor rewrites
- Use Team mode if multiple independent tasks
- Use Ralph mode for each task (execute→verify→fix)
- Continue until all tasks pass verification
- Update state via `rpi_state_write` MCP tool after each task

### Phase 5: Auto-Review
- Run dual-model cross-review via **parallel MCP calls**:
  - `ask_codex(agent_role="code-reviewer", background=true)`
  - `ask_gemini(agent_role="designer", background=true)`
- Fix Critical findings automatically
- Present final report to user

## Context Management
- Monitor context usage after each phase
- Prompt user for /clear when approaching 80%
- State persists in .oh-my-ccg/state/ across /clear (managed via MCP tools)

## Cancellation
Use /oh-my-ccg:cancel to stop autopilot at any point.

From 1molchuan/oh-my-ccg, MIT.

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
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from 1molchuan

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 autopilot 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.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying autopilot?

CallGet help
Cite this page

autopilot skill. Agent Mart. https://agentmart.dev/skills/1molchuan-autopilot (last updated 2026-10-24)