Skip to content
Agentmart
Submit a tool

oh-my-ccg-impl

RPI 实施阶段 — 按零决策计划机械执行

Skill by 1molchuan

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying oh-my-ccg-impl?

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-oh-my-ccg-impl

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

RPI 实施阶段 — 按零决策计划机械执行

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/oh-my-ccg-impl

What's inside

Skill name
oh-my-ccg-impl
Description
RPI 实施阶段 — 按零决策计划机械执行
License
MIT
Instructions
67 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# oh-my-ccg Implementation Phase

You are executing the RPI Impl phase. Execute the plan mechanically.

## Prerequisites
- RPI state must be in PLAN phase (or resuming IMPL)
- Tasks must be defined in state/artifacts

## Workflow

### Step 1: Restore State
Use the **oh-my-ccg-tools** MCP server's `rpi_state_read` tool.
Load the task list and current progress.

### Step 2: Assess Parallelism
Check task dependencies:
- If multiple independent tasks exist → use Team mode for parallel execution
- If tasks are sequential → execute one by one with executor agent

### Step 3: Execute Tasks
For each task (or batch of parallel tasks):

1. **Route to appropriate model for prototype** (via MCP tools):
   - Frontend tasks → call `ask_gemini(agent_role="designer")` for prototype, then executor rewrites to production
   - Backend tasks → call `ask_codex(agent_role="architect")` for prototype, then executor rewrites to production
   - General tasks → executor implements directly (no external model needed)

2. **Executor implements**:
   - Read task spec completely
   - Explore existing code patterns
   - Rewrite prototype to production quality (NEVER apply external model output directly)
   - Run type checks and tests

3. **Side-effect review** (MANDATORY before moving to next task):
   - Verify changes stay within task scope
   - Check no unintended dependencies affected
   - Confirm interfaces match expectations

### Step 4: Cross-Review
After all tasks complete, run dual-model cross-review using MCP tools **in parallel**:

- `ask_codex(agent_role="code-reviewer", background=true)` — reviews logic/security
- `ask_gemini(agent_role="designer", background=true)` — reviews patterns/maintainability

Collect both results via `check_job_status`, then:
- Fix any Critical findings immediately
- Log Warnings for review phase

### Step 5: Verify
Run verifier agent:
- All tests pass
- Build succeeds
- No type errors
- Constraints satisfied

### Step 6: Update State
Use `rpi_state_write` MCP tool to:
- Mark tasks complete in state
- Transition phase to "impl"
- If all tasks done → prompt for `/oh-my-ccg:review`

### Ralph Integration
If ralph mode is active:
- Execute → Verify → Pass? → Complete
- Execute → Verify → Fail? → Fix → Repeat (up to max iterations)

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 oh-my-ccg-impl 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 oh-my-ccg-impl?

CallGet help
Cite this page

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