AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Prd Generator

skill-patonkikh-apes-prd-generator · by patonkikh

>

No reviews yet
0 installs
43 views
0.0% view→install

Install

$ agentstack add skill-patonkikh-apes-prd-generator

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-patonkikh-apes-prd-generator)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

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 →
Are you the author of Prd Generator? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

PRD Generator

Purpose

Produce a Product Requirements Document (PRD) for a defined feature or MVP scope with goals, requirements, and success metrics.

Input: Feature scope, product vision (optional), prioritization results (optional), constraints Output: PRD document following standard structure with functional and non-functional requirements Examples: See [examples.md](examples.md) for worked input/output.


Workflow

Step 1: Define scope

Confirm:

  • Feature or MVP boundary (what is in/out)
  • Target persona and problem statement
  • Success metrics (from vision or define new)
  • Constraints (timeline, platform, compliance)

Step 2: Write executive summary

One paragraph covering: what, for whom, why now, expected outcome.

Step 3: Document requirements

Functional requirements:

  • Numbered list (FR-001, FR-002...)
  • Each requirement: actor, action, outcome
  • Priority: Must / Should / Could

Non-functional requirements:

  • Performance, security, scalability, accessibility
  • Numbered (NFR-001...)

Step 4: Define user flows

Describe 2–3 primary flows:

  • Happy path
  • Key edge case
  • Error/recovery path

Use step-by-step format, not wireframes.

Step 5: Specify success metrics

| Metric | Baseline | Target | Measurement method | |--------|----------|--------|-------------------|

Step 6: List dependencies and risks

  • Technical dependencies
  • External integrations
  • Open questions

Step 7: Validate

Run Validation checklist.


Decision Rules

| Condition | Action | |-----------|--------| | Scope undefined or "everything" | Stop; request MVP boundary or run feature-prioritization | | Requirement describes implementation | Rewrite as user-facing behavior | | No success metrics | Define at least 2 from vision or problem statement | | Conflicting requirements | Flag conflict; ask user to resolve | | NFRs missing for user-facing product | Add security, performance, accessibility minimums |


Validation

  • [ ] Executive summary ≤ 1 paragraph
  • [ ] Scope in/out explicitly stated
  • [ ] ≥3 functional requirements with IDs and priorities
  • [ ] ≥2 non-functional requirements
  • [ ] ≥2 primary user flows documented
  • [ ] Success metrics have baseline, target, measurement
  • [ ] Dependencies and risks listed
  • [ ] No implementation details (tech stack, API design) unless requested

Anti-patterns

  • PRD as spec — database schemas and API endpoints in a product PRD.
  • No priorities — all requirements marked Must.
  • Orphan requirements — FRs not traceable to user problem.
  • Missing NFRs — only functional requirements listed.
  • Unbounded scope — "and other features as needed."

Best Practices

  • Trace each FR to a user problem or goal.
  • Use INVEST criteria when writing requirements (preview for user-story-generator).
  • Keep PRD at "what" level; defer "how" to technical design.
  • Include explicit out-of-scope section.
  • Version the PRD with date and change summary.

Output Structure

# PRD: [Feature/MVP Name]
**Version:** 1.0 | **Date:** [date]

## Executive Summary
[One paragraph]

## Scope
- **In scope:**
- **Out of scope:**

## Target User
[Persona reference or summary]

## Functional Requirements
| ID | Requirement | Priority | Rationale |
|----|-------------|----------|-----------|

## Non-Functional Requirements
| ID | Requirement | Priority |
|----|-------------|----------|

## User Flows
### Flow 1: [Name]
1. [Step]

## Success Metrics
| Metric | Baseline | Target | Method |
|--------|----------|--------|--------|

## Dependencies
- [Dependency]

## Risks & Open Questions
| Item | Impact | Owner |
|------|--------|-------|

## Revision History
| Version | Date | Changes |
|---------|------|---------|

Next Skills

| Outcome | Recommended Skill | |---------|-------------------| | Break PRD into epics | product/epic-generator | | Write user stories | product/user-story-generator | | Need acceptance criteria | product/acceptance-criteria-generator | | Visualize user journey | product/story-mapping | | Ready for technical design | architecture/solution-architecture |

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.