pdd-verify-feature
Skill41 starsChanged 8 months agoMITView on GitHub
Verify whether feature implementation meets development specifications and acceptance criteria. Invoke this Skill when users want to verify implemented features. This skill adopts a three-dimensional verification model of Completeness, Correctness, and Coherence to ensure feature implementation meets specification requirements. 支持中文触发:验证功能、验收功能、功能验收、验证实现、PDD验证。
1 other project uses a version of this.
Adopted by
Most recently taken up by
- wonderslife/pdd-skills-v3their own version, first seen Oct 13, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- wonderslife/pdd-skills-v3★ 15same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository24 other files it gives its agents.
- expert-activitiSkill
- expert-arch-enforcerSkill
- expert-auto-refactorSkill
- expert-code-qualitySkill
- expert-entropy-auditorSkill
- expert-mysqlSkill
- expert-ruoyiSkill
- official-doc-writerSkill
- pdd-baSkill
- pdd-code-reviewerSkill
- pdd-doc-changeSkill
- pdd-doc-gardenerSkill
- pdd-entropy-reductionSkill
- pdd-extract-featuresSkill
- pdd-generate-specSkill
- pdd-implement-featureSkill
- pdd-mainSkill
- pdd-pr-batchSkill
- pdd-pr-createSkill
- pdd-pr-mergeSkill
- pdd-pr-reviewSkill
- software-architectSkill
- software-engineerSkill
- system-architectSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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
- Distinctive: line 20
Verify whether feature implementation meets development specifications and acceptance criteria to ensure delivery quality.
- Distinctive: line 281
When complete verification is not possible:
- Distinctive: line 345
Processing Timing: After all features in module are completed, process quality improvement tasks uniformly
≈ “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.
Files
PDD-Verify Feature - Feature Verification Skill
1. Skill Overview
1.1 Core Positioning
Verify whether feature implementation meets development specifications and acceptance criteria to ensure delivery quality.
1.2 Three-Dimensional Verification Model
Verification Dimensions:
Completeness:
Definition: Whether all functions required by specifications have been implemented
Verification Points:
- Whether interfaces are complete
- Whether fields are comprehensive
- Whether business rules are covered
Correctness:
Definition: Whether implementation conforms to specification definitions
Verification Points:
- Whether interface logic is correct
- Whether data processing is accurate
- Whether business rules are correct
Coherence:
Definition: Whether frontend and backend, documentation and code are consistent
Verification Points:
- Whether frontend and backend interfaces are consistent
- Whether documentation and code are consistent
- Whether naming conventions are unified1.3 Issue Classification
| Level | Symbol | Description | Handling Method |
| Critical | 🔴 | Must be fixed, otherwise acceptance fails | Re-verify after fixing |
| Warning | 🟡 | Recommended to fix, does not affect acceptance pass | Record, pending future processing |
| Suggestion | 🔵 | Optional optimization | Record, as future improvement item |
2. Verification Process
Step 1: Collect Verification Materials
Verification Materials:
Code Files:
- Backend Code: Controller, Service, Mapper
- Frontend Code: Vue Components, API Interfaces
- Database Scripts: SQL Files
Specification Documents:
- spec.md: Development Specifications
- checklist.md: Acceptance Criteria
Others:
- Business Analysis Report
- PRD DocumentStep 2: Completeness Verification
### 2.1 Interface Completeness Check
| Specification Required Interface | Actual Implementation | Status |
|--------------|---------|------|
| POST /api/xxx | ✓ Implemented | 🟢 |
| GET /api/xxx/{id} | ✓ Implemented | 🟢 |
| PUT /api/xxx | ✗ Not Implemented | 🔴 |
| DELETE /api/xxx/{id} | ✓ Implemented | 🟢 |
### 2.2 Field Completeness Check
| Specification Required Field | Actual Implementation | Status |
|--------------|---------|------|
| companyName | ✓ String | 🟢 |
| evaluationValue | ✓ BigDecimal | 🟢 |
| floorPrice | ✗ Missing | 🔴 |Step 3: Correctness Verification
### 3.1 Interface Logic Correctness
| Check Item | Verification Result | Status |
|-------|---------|------|
| Application Submission Interface Logic | Correct | 🟢 |
| State Transition Logic | Correct | 🟢 |
| Permission Verification Logic | Missing | 🔴 |
### 3.2 Business Rule Correctness
| Business Rule | Specification Requirement | Implementation Status | Status |
|---------|---------|---------|------|
| Transfer Floor Price >= Valuation * 90% | Must Verify | Verified | 🟢 |
| Must Upload Attachments | Must Verify | Not Verified | 🔴 |Step 4: Coherence Verification
### 4.1 Frontend-Backend Consistency
| Interface/Field | Backend Definition | Frontend Definition | Status |
|----------|---------|---------|------|
| companyName | String | String | 🟢 |
| evaluationValue | BigDecimal | Number | 🟢 |
| floorPrice | BigDecimal | String | 🟡 |
### 4.2 Documentation-Code Consistency
| Documentation Description | Code Implementation | Status |
|---------|---------|------|
| Interface Path: /api/apply | @RequestMapping("/apply") | 🟢 |
| Response Structure: {code, msg, data} | AjaxResult | 🟢 |3. Verification Checklist
3.1 Interface Verification
Interface Verification Items:
- [ ] Whether interface path conforms to specifications
- [ ] Whether request method is correct
- [ ] Whether request parameters are complete
- [ ] Whether response structure conforms to specifications
- [ ] Whether error codes are correct3.2 Business Logic Verification
Business Logic Verification Items:
- [ ] Whether state transitions are correct
- [ ] Whether business rules are executed
- [ ] Whether validation logic is complete
- [ ] Whether exception handling is appropriate3.3 Data Verification
Data Verification Items:
- [ ] Whether field types are correct
- [ ] Whether field lengths are sufficient
- [ ] Whether required fields are validated
- [ ] Whether data formats are correct3.4 Permission Verification
Permission Verification Items:
- [ ] Whether permission annotations exist
- [ ] Whether data permissions are configured
- [ ] Whether button permissions are controlled3.5 Frontend-Backend Consistency Verification
Consistency Verification Items:
- [ ] Whether interface paths are consistent
- [ ] Whether field names are consistent
- [ ] Whether data types are consistent
- [ ] Whether validation rules are consistent4. Output Specifications
4.1 Acceptance Report Template
# [Feature Name] Acceptance Report
## Basic Information
| Item | Content |
|------|------|
| Feature ID | FP-xxx |
| Acceptance Date | yyyy-MM-dd |
| Acceptance Person | AI/Manual |
| Acceptance Result | Pass/Fail |
## Three-Dimensional Verification Results
### Completeness
| Verification Item | Result | Issue Count |
|-------|------|-------|
| Interface Completeness | 🟢 Pass | 0 |
| Field Completeness | 🟡 Pass | 2 |
| Business Rule Coverage | 🔴 Fail | 1 |
### Correctness
| Verification Item | Result | Issue Count |
|-------|------|-------|
| Interface Logic | 🟢 Pass | 0 |
| Business Rules | 🟢 Pass | 0 |
| Data Processing | 🟡 Pass | 1 |
### Coherence
| Verification Item | Result | Issue Count |
|-------|------|-------|
| Frontend-Backend Consistency | 🟢 Pass | 0 |
| Documentation-Code Consistency | 🟢 Pass | 0 |
| Naming Conventions | 🟡 Pass | 1 |
## Issue List
### 🔴 Critical Issues
| No. | Issue Description | Location | Suggested Fix |
|------|---------|------|---------|
| 1 | [Issue] | [File] | [Suggestion] |
### 🟡 Warning Issues
| No. | Issue Description | Location | Suggested Fix |
|------|---------|------|---------|
| 1 | [Issue] | [File] | [Suggestion] |
### 🔵 Suggestion Issues
| No. | Issue Description | Location | Suggested Fix |
|------|---------|------|---------|
| 1 | [Issue] | [File] | [Suggestion] |
## Acceptance Conclusion
- [ ] **Passed Acceptance**: All Critical issues have been fixed
- [ ] **Conditionally Passed**: Critical issues recorded, pending fix
- [ ] **Failed Acceptance**: Unfixed Critical issues exist
## Signature
| Role | Signature | Date |
|------|------|------|
| AI Verification | | |
| Manual Review | | |5. Verification Heuristics
5.1 Common Omission Checks
Omission Checks:
- [ ] Whether pagination parameters are handled
- [ ] Whether sorting parameters are handled
- [ ] Whether export functionality is implemented
- [ ] Whether import functionality is implemented
- [ ] Whether batch operations are handled5.2 Common Error Checks
Error Checks:
- [ ] Null pointer exception handling
- [ ] Array bounds checking
- [ ] Type conversion checking
- [ ] Date format checking
- [ ] Number precision checking5.3 Degraded Processing Strategy
When complete verification is not possible:
Degraded Strategy:
1. Code Review Degradation:
- Missing tests -> Perform code review
- Missing documentation -> Reference existing code
2. Partial Verification:
- Core functions verified first
- Non-core functions can be marked "pending verification"
3. Record Unverified Items:
- Clearly mark unverified content
- Record reasons and risks6. Guardrails
6.1 Mandatory Verification Items
- All Critical issues must be fixed
- Acceptance report must be complete
- Three-dimensional verification must be covered
6.2 Avoidance Items
- ❌ Skip any Critical issues
- ❌ Verbal acceptance without documentation
- ❌ Degraded processing without risk explanation
7. Collaboration with Other Skills
| Collaborative Skill | Collaboration Method | Input Data | Expected Output |
| pdd-code-reviewer | Sequential | Review Report | Issue List |
| pdd-implement-feature | Loop | Acceptance Failed | Fixed Code |
| pdd-main | Sequential | Acceptance Report | Final Delivery Confirmation |
8. Version History
| Version | Date | Changes |
| 4.1 | 2026-03-22 | Added checkpoint resume and error handling specification references |
| 4.0 | 2026-03-21 | Adopted three-dimensional verification model (Completeness/Correctness/Coherence) |
9. Checkpoint Resume and Error Handling Specifications
This Skill follows PDD framework implementation specifications, see pdd-framework-design.md Chapter 9.
9.1 Checkpoint Resume
- State File:
.pdd-state.json - Trigger Method: User issues "continue execution" command
- State Content: Current stage, completed features, pending features
9.2 Error Handling
- Retry Limit: Maximum 3 times for the same feature
- Exceeded Limit: Pause process, await manual decision
- Failure Record: Record to
dev-specs/FP-{Module}-{Sequence}/review-report.md
9.3 Quality Improvement Tasks
- Processing Timing: After all features in module are completed, process quality improvement tasks uniformly
- Output File:
dev-specs/FP-{Module}-{Sequence}/improvement-tasks.md
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
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.

