Install
$ agentstack add skill-barkleesanders-claude-code-starter-compound-prd ✓ 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.
About
PRD Generator
Create detailed Product Requirements Documents that are clear, actionable, and suitable for implementation.
The Job
- Receive a feature description
- Self-clarify: Ask yourself 3-5 critical questions and answer them based on context
- Generate a structured PRD based on your answers
- Save to
/tasks/prd-[feature-name].md
Important:
- Do NOT ask the user questions. Answer them yourself using available context.
- Do NOT start implementing. Just create the PRD.
Step 1: Self-Clarification
Before generating the PRD, ask yourself these questions and write your answers. This ensures you've thought through the problem:
- Problem/Goal: What problem does this solve? Why now?
- Core Functionality: What are the 2-3 key actions this enables?
- Scope/Boundaries: What should this explicitly NOT do?
- Success Criteria: How do we verify it's working?
- Constraints: What technical/time constraints exist?
Format Your Thinking:
## Self-Clarification
1. **Problem/Goal:** [Your answer based on the request and codebase context]
2. **Core Functionality:** [Your answer]
3. **Scope/Boundaries:** [Your answer - be conservative, prefer smaller scope]
4. **Success Criteria:** [Your answer - must be verifiable]
5. **Constraints:** [Your answer - note any mentioned constraints like "no DB migrations"]
Use context from: the request, AGENTS.md, existing code patterns, and any reports/analysis provided.
Step 2: PRD Structure
Generate the PRD with these sections:
1. Introduction/Overview
Brief description of the feature and the problem it solves.
2. Goals
Specific, measurable objectives (bullet list).
3. Tasks
Each task needs:
- Title: Short descriptive name
- Description: What needs to be done
- Acceptance Criteria: Verifiable checklist of what "done" means
Each task should be small enough to implement in one focused session.
Format:
### T-001: [Title]
**Description:** [What to implement]
**Acceptance Criteria:**
- [ ] Specific verifiable criterion
- [ ] Another criterion
- [ ] Quality checks pass
- [ ] **[UI tasks only]** Verify in browser
Important:
- Acceptance criteria must be verifiable, not vague. "Works correctly" is bad. "Button shows confirmation dialog before deleting" is good.
- For any task with UI changes: Always include browser verification as acceptance criteria.
4. Functional Requirements
Numbered list of specific functionalities:
- "FR-1: The system must allow users to..."
- "FR-2: When a user clicks X, the system must..."
Be explicit and unambiguous.
5. Non-Goals (Out of Scope)
What this feature will NOT include. Critical for managing scope.
6. Technical Considerations (Optional)
- Known constraints or dependencies
- Integration points with existing systems
- Performance requirements
7. Success Metrics
How will success be measured?
8. Open Questions
Remaining questions or areas needing clarification.
Writing for Agents
The PRD reader may be an AI agent. Therefore:
- Be explicit and unambiguous
- Avoid jargon or explain it
- Provide enough detail to understand purpose and core logic
- Number requirements for easy reference
- Use concrete examples where helpful
Output
- Format: Markdown (
.md) - Location:
/tasks/ - Filename:
prd-[feature-name].md(kebab-case)
Example PRD
# PRD: Task Priority System
## Introduction
Add priority levels to tasks so users can focus on what matters most.
## Goals
- Allow assigning priority (high/medium/low) to any task
- Provide clear visual differentiation between priority levels
- Enable filtering by priority
## Tasks
### T-001: Add priority field to database
**Description:** Add priority column to tasks table for persistence.
**Acceptance Criteria:**
- [ ] Add priority column: 'high' | 'medium' | 'low' (default 'medium')
- [ ] Generate and run migration successfully
- [ ] Quality checks pass
### T-002: Display priority indicator on task cards
**Description:** Show colored priority badge on each task card.
**Acceptance Criteria:**
- [ ] Each task card shows colored badge (red=high, yellow=medium, gray=low)
- [ ] Priority visible without hovering
- [ ] Quality checks pass
- [ ] Verify in browser
### T-003: Add priority selector to task edit
**Description:** Allow changing task priority in edit modal.
**Acceptance Criteria:**
- [ ] Priority dropdown in task edit modal
- [ ] Shows current priority as selected
- [ ] Saves on selection change
- [ ] Quality checks pass
- [ ] Verify in browser
## Functional Requirements
- FR-1: Add `priority` field to tasks table
- FR-2: Display colored priority badge on each task card
- FR-3: Include priority selector in task edit modal
## Non-Goals
- No priority-based notifications
- No automatic priority assignment
## Success Metrics
- Users can change priority in <2 clicks
- High-priority tasks immediately visible
Checklist
Before saving the PRD:
- [ ] Completed self-clarification (answered all 5 questions)
- [ ] Tasks are small and specific (completable in one session each)
- [ ] Acceptance criteria are verifiable (not vague)
- [ ] Functional requirements are numbered and unambiguous
- [ ] Non-goals section defines clear boundaries
- [ ] Saved to
/tasks/prd-[feature-name].md
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: barkleesanders
- Source: barkleesanders/claude-code-starter
- 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.