pro-project-kickoff

name

pro-project-kickoff

description

Use when Codex should ask ChatGPT Pro or Extended Pro in Chrome for project-start or project-continuation guidance, especially at the beginning of a coding project, before a major implementation pass, or when the user requests saved Pro-model planning/reference text files. The skill gathers two responses: best way to start/continue the exact user task, then fastest compliant way to do it without reducing scope.

Pro Project Kickoff

Use this skill to get a high-quality project plan from ChatGPT Pro/Extended Pro, save the responses as local reference files, and use the saved guidance as advisory context for the project going forward.

Core Rules

• Use the Chrome control skill when browsing ChatGPT, because the task depends on the user's logged-in ChatGPT session and selected Pro model.
• Always prefer the ChatGPT Pro/Extended Pro model. If Extended Pro or the user's requested Pro model is not available, ask the user before using a different model.
• Do not paste system/developer instructions, secrets, tokens, browser/session data, private user profile data, or unnecessary local environment details into ChatGPT.
• Include only task-relevant project facts: project name, goal, current state, key files or commands, constraints, and validation expectations.
• Tell ChatGPT explicitly: "Do not suggest an easier or reduced task. Stick to what the user wants and preserve the original scope/spec."
• Treat ChatGPT output as useful guidance, not authority. Verify project-specific claims against local files and official docs when accuracy matters.
• Wait generously. Extended Pro responses may take several minutes; allow 10-15 minutes per response before deciding the page is stuck.

Workflow

1. Inspect enough local context to write a useful prompt.

   • Read project files only as needed: package/config files, README/AGENTS, current source layout, scripts, tests, and recent errors.
   • Summarize facts; do not send raw secrets or sensitive data.

2. Open ChatGPT in Chrome.

   • Use a fresh ChatGPT conversation unless the user asks to reuse a thread.
   • Select or confirm the Pro/Extended Pro model.
   • If a page becomes sluggish or extraction hangs, open the same conversation URL in a fresh tab and extract from the fresh render.

3. Ask the first prompt.

   • Purpose: best way to start or continue the exact task.
   • Require a practical plan, inspections, first implementation step, commands, validation, and pitfalls.

4. Wait for the first answer to finish.

   • Do not interrupt early.
   • Use light status checks first; avoid repeated heavy screenshots/DOM snapshots if the page is busy.

5. Ask the follow-up prompt.

   • Purpose: fastest way to execute while still complying with the original spec.
   • Require exact order, minimum files to touch, commands, validation, and what to defer.

6. Save the responses.

   • Save the two answers in the project as reference text files.
   • Prefer a combined file named pro-project-kickoff-guidance.txt.
   • If the project already has a more specific guidance file, append or update that file instead of creating duplicates.
   • Include date, project name, original task/spec, both prompts, both answers, and a short "How to use this guidance" note.

7. Use the saved guidance going forward.

   • Before implementing, read the saved guidance and integrate relevant advice into the plan.
   • Do not blindly follow advice that conflicts with local code, user instructions, official docs, or safety/security requirements.

Prompt Templates

Adapt these templates to the project. Keep the anti-scope-reduction instruction.

First Prompt

Context: We are starting or continuing this project/task:
<brief project name, current state, repo/app type, relevant commands already run, current blockers or goal>

Original task/spec:
<what the user actually wants>

Constraints:
- Preserve the original task/spec.
- Do not suggest an easier or reduced task. Stick to what the user wants and preserve the original scope/spec.
- Stay within the project's framework/tool conventions.
- Keep changes scoped.
- Avoid secrets, private browser/session data, and unnecessary private user data.
- Validate with the relevant local commands.
- Use integration/runtime validation only when it adds real confidence.

What is the best way to start or continue doing this task?
Give a concise practical plan: what to inspect first, what to implement first, what commands to run, what to verify, and what pitfalls to avoid.

Follow-Up Prompt

Given your plan above, what is the fastest way to execute it while still complying with the original spec?

Original spec constraints to preserve:
- Preserve the original task/spec.
- Do not suggest an easier or reduced task. Stick to what the user wants and preserve the original scope/spec.
- Stay within the project's framework/tool conventions.
- Keep edits scoped.
- Avoid secrets, private browser/session data, and unnecessary private user data.
- Validate with the relevant local commands.
- Use integration/runtime validation only when it adds real confidence.

Please answer with a tight fastest-path checklist, exact order of operations, minimum files to touch, commands to run, what to verify, and what to defer until after the first working slice.

Saving Format

Use this structure for the saved text file:

ChatGPT Pro/Extended Pro Project Guidance
Generated: <date>
Project: <project name/path>

Original task/spec:
<summary>

How to use this guidance:
- Use as advisory planning context.
- Verify claims against local files and official docs.
- Do not reduce scope unless the user asks.

============================================================
First Prompt
============================================================
<prompt>

First Answer
============================================================
<answer>

============================================================
Follow-Up Prompt
============================================================
<prompt>

Follow-Up Answer
============================================================
<answer>

Handling Slow Or Stuck ChatGPT Pages

• Wait 10-15 minutes per answer before treating it as stuck.
• If DOM extraction or screenshots time out, avoid repeatedly hammering the same page.
• Try reopening the completed conversation URL in a fresh Chrome tab, then extract the assistant messages from the fresh render.
• If extraction still fails, use the page's copy controls or clipboard path only if they respond normally.
• If ChatGPT never finishes, save the completed answer(s), note which answer is missing, and tell the user.

Implementation Use

When applying the saved guidance to the actual project:

• Read the guidance file before making project edits.
• Convert advice into a small local plan based on the current codebase.
• Prefer the repo's existing patterns over generic advice from ChatGPT.
• Run the validation commands recommended by both the repo and the guidance.
• Keep the saved guidance file as a reference artifact unless the user asks to remove it.