Install
$ agentstack add skill-baobao2333-prd-agent-kit-prd-04-flow-modeler ✓ 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 Flow Modeler
Purpose
Translate rule logic into flows that show how users, systems, and states move through the feature.
Inputs
- Rule model.
- Scope boundary.
- Known entry points and target pages, if available.
Process
- Identify entry points.
- Write the happy path.
- Write system judgment flow behind the happy path.
- Write exception paths.
- Write state transitions.
- Identify where user-facing feedback is required.
- Identify where system logging or operations visibility may be needed, but do not define full analytics here.
Flow rules
- Separate user behavior from system behavior.
- Include failure outcomes, not just success outcomes.
- Include empty, expired, permission-denied, duplicate, and network-failure states when relevant.
- Do not introduce new scope unless the rule model requires it.
- If the flow exposes missing rules, mark them as
Rule gapand send them back toprd-03-rule-modeler.
Output format
# 03 Flow Model: {Feature Name}
## 1. Entry points
| Entry | User condition | Display condition | Destination |
|---|---|---|---|
## 2. User happy path
```mermaid
flowchart TD
A[User sees entry] --> B[User opens feature]
B --> C[User performs core action]
C --> D[User receives result]
3. System judgment flow
flowchart TD
A[Receive user action] --> B{Check feature status}
B -->|Available| C{Check user eligibility}
B -->|Unavailable| X[Return unavailable state]
C -->|Eligible| D[Execute action]
C -->|Not eligible| Y[Return reason]
D --> Z[Update state and return success]
4. State transition table
| Object | From state | Trigger | To state | Notes | |---|---|---|---|---|
5. Exception flows
| Exception | Trigger | System behavior | User-facing response | Rule gap? | |---|---|---|---|---|
6. Handoff to next stage
Recommended next skill: prd-05-page-interaction
## Definition of done
The flow model is complete when engineering and QA can see the feature path without relying on narrative interpretation.
## Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- **Author:** [baobao2333](https://github.com/baobao2333)
- **Source:** [baobao2333/prd-agent-kit](https://github.com/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.