Prd 01 Idea Intake
Convert a rough product idea, user feedback, or operations request into a structured product problem brief. Use at the very beginning of PRD work. Do not use to write rules, page specs, backend config, or final PRD.
Install
$ agentstack add skill-baobao2333-prd-agent-kit-prd-01-idea-intake ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-baobao2333-prd-agent-kit-prd-01-idea-intake) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
PRD Idea Intake
Purpose
Turn an unclear idea into a structured brief that separates facts from assumptions. This skill expands the idea enough for product discussion, but it must not over-design the solution.
Inputs
- Raw idea or request.
- Existing context, if available.
- User, operations, business, or internal stakeholder feedback.
Process
- Restate the idea in one paragraph.
- Identify the likely problem being solved.
- Identify who is affected.
- Identify the trigger scenario.
- Identify why this might matter now.
- Separate known facts from assumptions.
- List only the minimum questions that block the next step.
Do not
- Do not write a full PRD.
- Do not create page-level specs.
- Do not invent backend systems.
- Do not add rankings, audits, permissions, AI automation, analytics, or notifications unless the idea directly requires them.
- Do not use vague claims such as “improve user experience” without naming the concrete friction.
Output format
# 00 Intake Brief: {Feature Name}
## 1. One-line idea
{One sentence}
## 2. Problem statement
{What problem is being solved, not what feature is being built}
## 3. Affected users / roles
| Role | Why affected | Current pain |
|---|---|---|
## 4. Trigger scenario
| Scenario | Trigger | Desired outcome |
|---|---|---|
## 5. Facts, assumptions, and unknowns
| Type | Item | Why it matters |
|---|---|---|
| Fact | | |
| Assumption | | |
| Decision needed | | |
## 6. Non-obvious risks noticed early
| Risk | Why it may matter | Later skill to handle |
|---|---|---|
## 7. Handoff to next stage
Recommended next skill: `prd-02-business-boundary`Definition of done
A good intake brief makes the idea debatable. It should expose the problem and uncertainty without pretending the solution is already fixed.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: baobao2333
- Source: baobao2333/prd-agent-kit
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.