agentleFS
wonderslifewonderslife/pdd-skills/pdd-extract-features/SKILL.md

pdd-extract-features

Skill41 starsChanged 8 months agoMITView on GitHub

Extract feature point matrix from PRD document system. Call this Skill when users want to extract feature points from PRD. This skill is based on business analysis results, automatically identifies and extracts feature points, generates standardized feature point matrix, and provides input for development specification generation. 支持中文触发:提取功能点、功能点矩阵、从PRD提取、功能点分析、PDD提取。

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After feature point matrix generation is complete, manual review is required.

    line 227

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

PDD-Extract Features - Feature Point Extraction Skill

1. Skill Overview

1.1 Core Positioning

Extract feature points from business analysis results and PRD documents, generate standardized feature point matrix.

1.2 Skill Boundaries

  • Input: Business analysis report, PRD document
  • Output: feature-matrix.md (feature point matrix)
  • Not responsible for: Specification writing, code implementation

2. Feature Point Classification

2.1 Classification by Complexity

ComplexityCodeDescriptionDevelopment TimeManual Involvement
Core BusinessP0Core business processes, involving multi-party approval3-5 daysHigh
Important FeaturesP1Important business features, with alternatives1-2 daysMedium
Auxiliary FeaturesP2Auxiliary features, easy to implement0.5 dayLow

2.2 Classification by Operation Type

TypeCodeDescription
CreateCCreate, add new data
ReadRRead, query/details
UpdateUUpdate, modify data
DeleteDDelete, remove data
BatchBBatch, batch operations
ApproveAApprove, approval workflow
ExportEExport, data export
FlowFFlow, state transition

2.3 Classification by AI Role

AI RoleCodeDescriptionManual Involvement
LeaderAI-LAI-led implementationLow
CollaboratorAI-CAI and human collaborationMedium
ReviewerAI-RAI-assisted reviewHigh

3. Feature Point Extraction Process

Step 1: Analyze Business Use Cases

Extract use cases from business analysis report:

  • Primary actors
  • Use case name
  • Basic flow
  • Extended flow

Step 2: Identify Feature Operations

Identify operations for each use case:

| Use Case | Operation | Operation Type | Complexity | AI Role |
|------|------|---------|--------|--------|
| UC-001 Transfer Application | Initiate Application | C | P0 | AI-C |
| UC-001 Transfer Application | View Application | R | P1 | AI-L |
| UC-001 Transfer Application | Modify Application | U | P1 | AI-C |

Step 3: Identify Pages/Interfaces

| Feature Point | Page Path | API Path | Method |
|--------|---------|---------|------|
| FP-001 Initiate Application | form.vue | /apply | POST |
| FP-002 View Application | detail.vue | /apply/{id} | GET |

Step 4: Generate Feature Point Matrix

# [Module Name] Feature Point Matrix

## 1. Feature Point Summary

| Feature Point ID | Feature Name | Page/Interface | Operation Type | Complexity | AI Role | Dependencies |
|---------|---------|----------|---------|--------|--------|---------|
| FP-001 | Initiate Transfer Application | form.vue | C | P0 | AI-C | - |
| FP-002 | View Transfer Application | detail.vue | R | P1 | AI-L | FP-001 |
| FP-003 | Modify Transfer Application | form.vue | U | P1 | AI-C | FP-001 |
| FP-004 | Delete Transfer Application | list.vue | D | P1 | AI-C | FP-001 |
| FP-005 | Approve Transfer Application | approval.vue | A | P0 | AI-C | FP-001 |

Step 5: Feature Point Details

Generate details for each P0 feature point:

## 2. Feature Point Details

### FP-001: Initiate Transfer Application

**Basic Information**:
| Item | Content |
|------|------|
| Feature Point ID | FP-001 |
| Feature Name | Initiate Transfer Application |
| Belonging Use Case | UC-001 |
| Operation Type | C (Create) |
| Complexity | P0 |

**Feature Description**:
Applicant fills out transfer application form, after submission enters approval workflow.

**Preconditions**:
- User has logged in
- User has permission to initiate application

**Postconditions**:
- Application record has been created
- Status changes to "Pending Review"
- Notify approver

**Input Fields**:
| Field Name | Type | Required | Description |
|--------|------|------|------|
| companyName | String | Yes | Enterprise name |
| transferType | Enum | Yes | Transfer type |
| evaluationValue | Decimal | Yes | Evaluation value |
| floorPrice | Decimal | Yes | Transfer floor price |
| attachments | File[] | Yes | Attachments |

**Output Information**:
| Information | Description |
|------|------|
| applyId | Application ID |
| applyNo | Application number |
| status | Application status |

**Business Rules**:
- Transfer floor price >= Evaluation value * 90%
- Must upload related attachments
- Same enterprise same type can only have one ongoing application

**Test Strategy**:
- Positive: Normal submission of application
- Exception: Floor price below limit, missing attachments, duplicate submission

4. Feature Point Matrix Template

# [Module Name] Feature Point Matrix

## Matrix Information
| Item | Content |
|------|------|
| Module Number | [Number] |
| Module Name | [Name] |
| Generation Date | [Date] |
| Version | v1.0 |

## Feature Point Summary Table

### 1.1 Statistics by Complexity
| Complexity | Count | Feature Point IDs |
|--------|------|---------|
| P0 | N | FP-xxx |
| P1 | N | FP-xxx |
| P2 | N | FP-xxx |

### 1.2 Statistics by Operation Type
| Operation Type | Count | Feature Point IDs |
|---------|------|---------|
| C (Create) | N | FP-xxx |
| R (Read) | N | FP-xxx |
| U (Update) | N | FP-xxx |
| D (Delete) | N | FP-xxx |
| A (Approve) | N | FP-xxx |

## Detailed Feature Point List

| Feature Point ID | Feature Name | Page/Interface | Operation | Complexity | AI Role | Dependencies | Test Strategy |
|---------|---------|----------|------|--------|--------|------|---------|
| FP-001 | [Name] | [Path] | C | P0 | AI-C | - | [Strategy] |

5. Guardrails

5.1 Must Follow

  • Feature point ID must be globally unique
  • Each feature point must have a clear operation type
  • Must mark feature point dependencies
  • P0 feature points must have detailed descriptions

5.2 Avoid

  • ❌ Feature point missing critical business operations
  • ❌ Dependencies forming cycles
  • ❌ Complexity assessment inconsistent with reality

6. Collaboration with Other Skills

Collaborating SkillCollaboration MethodInput DataExpected Output
pdd-baSequentialBusiness analysis reportUse cases and processes
pdd-generate-specSequentialFeature point matrixspec.md

7. Manual Review Standards

This Skill follows PDD framework manual review standards.

7.1 Review Checkpoint

After feature point matrix generation is complete, manual review is required.

7.2 Review Content

Review ItemDescription
Feature Point CompletenessWhether all business features are covered
Complexity AssessmentWhether P0/P1/P2 is reasonable
Test StrategyWhether complete
DependenciesWhether correct

7.3 Review Granularity

  • Batch Review: Quick overview of the whole, mark content requiring detailed review
  • Critical Feature Point Detailed Review: P0 priority, complex state transitions, external system integration, sensitive data processing

7.4 Review Results

  • Output File: review-features.md
  • Result Type: passed / rejected / conditional

7.5 Critical Feature Point Definition

  • P0 priority feature points
  • Involving complex state transitions
  • Involving external system integration
  • Involving sensitive data processing

8. PDD Implementation Standards Reference

This Skill follows PDD framework implementation standards, see pdd-framework-design.md Chapter 9.

9. Version History

VersionDateChange Content
2.12026-03-22Added manual review standards, PDD implementation standards reference
2.02026-03-21Enhanced complexity assessment standards, added AI role classification
1.0EarlyInitial version

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.