Install
$ agentstack add skill-baobao2333-prd-agent-kit-prd-05-page-interaction ✓ 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.
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 Page Interaction
Purpose
Describe what each page or component must communicate and how it behaves. This skill supports design and frontend development without pretending to replace design work.
Inputs
- Flow model.
- Rule model.
- Known product pages or entry points.
Process
- Identify required pages, modules, or components.
- Define information hierarchy for each.
- Define visible fields and their source meaning.
- Define button states and disabled reasons.
- Define copy for success, failure, empty, loading, and confirmation states.
- Identify interactions that need design attention.
Interaction writing rules
- Do not specify pixel-perfect UI unless provided by the user.
- Do not invent visual style.
- Do specify information priority, state, and user feedback.
- Each button must have enabled, disabled, loading, success, and failure behavior when relevant.
- Each empty state must explain why it is empty and what the user can do next, if anything.
Output format
# 04 Page & Interaction Spec: {Feature Name}
## 1. Page / component list
| Page or component | Purpose | Entry | Depends on rule / state |
|---|---|---|---|
## 2. Page spec
### {Page Name}
#### Purpose
{What this page helps the user understand or do}
#### Information hierarchy
| Priority | Content | Notes |
|---|---|---|
#### Fields
| Field | Meaning | Display condition | Empty / abnormal display |
|---|---|---|---|
#### Actions
| Action | Enabled condition | Disabled condition | Success result | Failure result |
|---|---|---|---|---|
#### States
| State | Display | User can do |
|---|---|---|
| Loading | | |
| Empty | | |
| Normal | | |
| Error | | |
| No permission | | |
| Expired / ended | | |
#### Copy
| Scenario | Copy | Notes |
|---|---|---|
## 3. Design attention points
| Point | Why it matters | Required decision |
|---|---|---|
## 4. Handoff to next stage
Recommended next skill: `prd-06-admin-config`
Definition of done
The page spec is complete when design knows what must be represented and frontend knows what states must be implemented.
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.