AGENT SKILL

gptpro-plan

Create a manual ChatGPT Pro planning second-opinion bridge. Use when the user invokes /ccg:gptpro-plan.

License 许可
MIT
最近更新
2026-10-01
Stars
★ 2
Forks
0

01 前言 Front Matter

name
gptpro-plan
description
Create a manual ChatGPT Pro planning second-opinion bridge. Use when the user invokes /ccg:gptpro-plan.

02 资源文件 1

03 SKILL.md 正文

CCG GPT Pro Plan

This is a Codex + Gemini + GPT Pro planning workflow.

Load and follow skills/ccg-gptpro-bridge/SKILL.md.

Behavior

  • Treat the argument as a planning task or plan-review input.
  • Run Gemini before GPT Pro using the bundled Gemini preview helper with --prompt-template plan.
  • Follow the Gemini Gate Before GPT Pro from skills/ccg-gptpro-bridge/SKILL.md: require a real CCG_GEMINI_RESPONSE_FILE, read a non-empty Gemini response from it, stop and do not create a GPT Pro bridge session if it is missing or empty, and do not invent Gemini findings.
  • Include Codex's planning context, the Gemini response file path, and a concise Gemini findings summary in the GPT Pro prompt.
  • Include the original CCG 需求完整性评分(0-10) with 目标明确性(0-3), 预期结果(0-3), 边界范围(0-2), 约束条件(0-2), 总分:X/10, and 判定:>=7 继续;<7 停止并提出补充问题.
  • Require GPT Pro to output a Planning Readiness Scorecard for plan maturity, ambiguity, risk, testability, and whether Codex should proceed.
  • Build a single-round planning prompt by default.
  • Expected manual questions: 1.
  • Maximum manual questions: 2.
  • Round 2 only for blocker re-check or revised plan comparison.
  • Use scripts/gptpro_bridge.py --mode plan --detach-preview --open-preview --gemini-response-file <CCG_GEMINI_RESPONSE_FILE> --gemini-summary-file <summary-file>.
  • Read the saved response file only after the user manually saves it.
  • Summarize and synthesize Codex, Gemini, and GPT Pro findings in Chinese.
  • Preserve the Plan-only Boundary: score readiness only; do not let the GPT Pro score become an execution trigger.
  • Codex remains final owner.
  • Do not automate ChatGPT web login.
  • Do not read ChatGPT web DOM.
  • Do not extract ChatGPT Output programmatically.

Plan-only Boundary

  • /ccg:gptpro-plan is planning-only.
  • Do not execute implementation.
  • Do not apply code changes except writing or updating CCG plan artifacts and GPT Pro bridge artifacts.
  • Do not run implementation tasks, mutate product code, commit, push, create a pull request, or continue into /ccg:execute behavior.
  • After the user saves GPT Pro output, synthesize Codex, Gemini, and GPT Pro planning findings only.
  • Produce or revise the plan, report the plan location and key decisions in Chinese, then stop.
  • Stop after producing or updating the plan.
  • If the user wants execution, require a separate /ccg:execute <plan> or /ccg:codex-exec <plan> request.

Manual Handoff Barrier

  • After creating the bridge artifacts, show only handoff metadata.
  • Do not paste the full generated prompt into chat.
  • Show the preview URL, session directory, prompt file path, response file path, and status file path.
  • Tell the user to open the preview page and use the preview page Copy Prompt button, then manually submit the prompt to ChatGPT Pro and manually save the response.
  • End the current assistant turn after the handoff. Do not continue the planning analysis in the same turn.
  • Continue only after status.json shows response_saved=true and response.md is non-empty.

04 同仓库更多 Skills

jed-zed
jed-zed/ccg-codex-workflow

verify-security

安全校验关卡。自动扫描代码安全漏洞,检测危险模式,确保安全决策有文档记录。当用户提到安全扫描、漏洞检测、安全审计、代码安全、OWASP、注入检测、敏感信息泄露时使用。在新建模块、安全相关变更、攻防任务、重构完成时自动触发。

★ 2
jed-zed
jed-zed/ccg-codex-workflow

verify-quality

代码质量校验关卡。检测复杂度、重复代码、命名规范、函数长度等质量指标。当用户提到代码质量、复杂度检查、代码异味、重构建议、lint检查、代码规范时使用。在复杂模块、重构完成时自动触发。

★ 2
jed-zed
jed-zed/ccg-codex-workflow

verify-module

模块完整性校验关卡。扫描目录结构、检测缺失文档、验证代码与文档同步。当用户提到模块校验、文档检查、结构完整性、README检查、DESIGN检查时使用。在新建模块完成时自动触发。

★ 2
jed-zed
jed-zed/ccg-codex-workflow

verify-change

变更校验关卡。分析代码变更,检测文档同步状态,评估变更影响范围。当用户提到变更检查、文档同步、代码审查、提交前检查、diff分析时使用。在设计级变更、重构完成时自动触发。

★ 2
jed-zed
jed-zed/ccg-codex-workflow

gen-docs

文档生成器。自动分析模块结构,生成 README.md 和 DESIGN.md 骨架。当用户提到生成文档、创建README、创建DESIGN、文档骨架、文档模板时使用。在新建模块开始时自动触发。

★ 2
jed-zed
jed-zed/ccg-codex-workflow

ccg

CCG command index for Codex. Use when the user invokes /ccg, asks what CCG commands are available, or gives a CCG plan/task without choosing a subcommand.

★ 2