Set up PRD-driven development infrastructure for a new project, including directory structure, templates, and roadmap.
SkillScore43Maintained
On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.
◆Product Management pack
Last verified 8/20/2026
What it changes
Passed 5 of 12 test cases with the skill, and 4 of 12 without it.
Without skill35%
With skill43%
Checks it passed that the model alone missed
Includes git init in the setup steps.
Lists remaining TODO placeholders in CLAUDE.md.
Identifies CLAUDE.md as an existing file conflict.
and 9 more in the full report
7 fixed3 passed either way8 still failing5 broke
Pass-rate lift
+9 pp
Tokens
+48%
Agent turns
0%
Response time
-64%
Model gemini-3.6-flashMeasured 8/20/2026v110 of 23 cases passed with skill · 12 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 7
Prompt
We are bootstrapping 'CloudSync' from scratch without an existing git repository and need a public GitHub repo created. Which CLI commands should be scheduled for Step 6 after approval?
What was checked, without and with the skill
Checked
Without skill
With skill
Includes git init in the setup steps.
Missed
Passed
Includes gh repo create CloudSync --public --source=. --push in the post-approval commands.
Missed
Passed
case-08 · gemini-3.6-flash · 8/20/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md166 linessingle file
Bootstrap PRD
Set up PRD-driven development infrastructure for a new project. This skill handles two workflows: PRD-first (PRD files already exist, scaffold the project around them) and scaffold-first (no PRD yet, create template files to be filled in). The skill detects which situation applies and adapts.
Your task
Work through the steps below in order. Each step has a hard stop — do not proceed past a CHECKPOINT without explicit user approval.
Step 1: Detect existing PRD files
Check whether docs/prd/ exists and contains any .md files.
If PRD files exist → enter PRD-first mode:
Read all .md files in docs/prd/ to understand the project
Extract: project name, description, tech stack, personas, and any quick-start commands mentioned
Skip to Step 3 (no need to gather information the PRD already contains)
If no PRD files exist → enter scaffold-first mode:
Proceed to Step 2 to gather project information
Step 2: Gather project information (scaffold-first mode only)
Ask the user for the following. Skip anything already provided in the conversation context.
Project name (e.g., "Acme Dashboard")
One-paragraph description of what the project does and who it serves
Tech stack — framework, database, frontend approach, linter, test framework
Key personas — 1-3 user types with a sentence each
Quick-start commands — how to start the app, run tests, run the linter
If the user provides a framework name, pre-fill quick-start commands from this lookup table (the user can override):