# README Generator Runbook

## Project Context To Prepare
- Project goal
- Current repository or workflow context
- Project purpose
- Tech stack
- Setup commands
- Features

## Input Template
Project:

Goal:

Current context:

Constraints:

Available files, notes, or data:

Expected output:
- README draft
- Install and quick start
- Commands
- Notes for the author

## Starter Inputs
### First useful run
Use this when you know the goal but still need a structured first draft.

Update the Agent Archive README after adding install kits and evaluations.

Context:
- Current state:
- Constraints:
- Audience:
- Success criteria:

### Project handoff run
Use this when the output will be pasted into a ticket, PR, document, or project brief.

Goal: produce README draft for a real project.
Source material:
- 
Constraints:
- 
Review needs:
- Go deep on the risks and constraints listed above.
- Mark assumptions.
- Flag missing context.

### Boundary check
Use this when the request may be under-specified and you want the agent to narrow it safely.

Write complete onboarding docs for a repo without reading its config.

Before producing the final answer, identify missing required context and propose a stronger prompt if needed.

## Setup Context Notes
- Prepare package scripts, setup steps, environment variables, core features, and validation commands.
- Include the target audience, output destination, and any examples of acceptable or unacceptable work.
- Name what should remain out of scope so the agent does not broaden the task.

## Good Input Example
Next.js app for browsing AI agents.

Goal: produce README draft for a real project.
Constraints: keep the result specific, structured, and ready for handoff.

## Weak Input Example
Help me with README Generator.

## Weak Input Diagnostics
### Help me with README Generator.
- Why it fails: It does not name the project, source material, constraints, audience, or success criteria.
- Stronger input: Update the Agent Archive README after adding install kits and evaluations. Include current context, constraints, expected output, and review criteria.

### Make this better.
- Why it fails: The agent cannot tell whether better means clearer, safer, faster, more complete, or easier to hand off.
- Stronger input: Improve the output for New repo docs. Optimize for README draft, keep assumptions explicit, and list the changes made.

## Expected Output Shape
- The README in Markdown, ready to paste: purpose, requirements, install, quick start, commands, configuration, limitations, roadmap, license
- Copy-pasteable usage for every named feature, command, and flag
- Known limitations stated plainly; roadmap items not presented as features
- Notes for the author outside the README: assumptions and what to verify

## Output Checklist
- Every feature, command, flag, and limitation the user named is documented with exact usage
- Uses only the names, commands, versions, and URLs given
- No invented badges, metrics, users, or benchmarks
- Length matches what the user asked for
- Assumptions are listed under notes for the author

## Failure Modes
- The input lacks the project context the agent needs
- A risk or constraint the user named gets a generic line instead of a concrete failure mode and check
- Unrequested extras crowd out depth on what the user asked for
- The agent invents facts, numbers, or approvals that were not provided

## Handoff Tips
- Paste relevant project files, notes, or constraints before asking for the final output.
- Ask for a first draft, then request a stricter revision using the checklist.
- Keep the generated output with the project ticket, PR, proposal, or team document.