gap-analysis
Skill14 starsChanged 37 days agoMITView on GitHub
Compare design documents against implementation and compute a Match Rate with a gap list (PDCA Check phase). Use after implementation or before PR to verify design conformance.
21 other projects use a version of this.
Adopted by
Most recently taken up by
- DatasiteAI/mcp-skillstheir own version, first seen Nov 3, 2026
- MarieLynneBlock/arcanum-artifextheir own version, first seen Nov 1, 2026
- Happy-Technologies-LLC/happy-platform-skillstheir own version, first seen Nov 1, 2026
- richardochristjia/skillstheir own version, first seen Nov 1, 2026
- TanStack/aitheir own version, first seen Oct 22, 2026
- adeerkhan/vitruviustheir own version, first seen Oct 20, 2026
Other versions21 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 21
- TanStack/ai★ 3.3ksame name
- magnus919/agent-skills★ 172same name
- zrosenfield/sharepoint-ai-skills★ 96same name
- Happy-Technologies-LLC/happy-platform-skills★ 41same name
- agent-ix/quoin★ 20same name
- afonsoft/skills★ 14same name
- adeerkhan/vitruvius★ 10same name
- DatasiteAI/mcp-skills★ 5same name
- kevinlin/skills★ 5same name
- MarieLynneBlock/arcanum-artifex★ 4same name
11 more not listed
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 repository44 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- adaptSkill
- animateSkill
- auditSkill
- bolderSkill
- brainstormSkill
- build-fixSkill
- business-panelSkill
- checkpointSkill
- clarifySkill
- colorizeSkill
- composition-patternsSkill
- confidence-checkSkill
- config-doctorSkill
- critiqueSkill
- delightSkill
- design-auditSkill
- devils-advocateSkill
- distillSkill
- eval-harnessSkill
- feature-plannerSkill
- fix-prSkill
- frontend-designSkill
- grill-with-docsSkill
- hardenSkill
- impeccableSkill
- layoutSkill
- learnSkill
- optimizeSkill
- overdriveSkill
- polishSkill
- pytest-runnerSkill
- python-best-practicesSkill
- quieterSkill
- react-best-practicesSkill
- sc-helpSkill
- security-auditSkill
- shapeSkill
- tddSkill
- typesetSkill
- ui-ux-pro-maxSkill
- uv-packageSkill
- verifySkill
- web-design-guidelinesSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 20 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 24
Do NOT use for: Simple code review, design document creation, bug fixes
- Very specific: line 161
Update .pdca-status.json on analysis completion:
“Common” is measured: kept by at least 6 in 10 of the 20 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Gap Analysis Skill
Analyze discrepancies between design documents and actual implementation code to calculate Match Rate.
When to Use
Use proactively when:
- Post-implementation design comparison needed
- "Does it match design?", "Is it correct?", "Verify" requests
- Pre-PR/code review verification
- PDCA Check phase execution
Triggers: gap analysis, design-implementation comparison, verify, validate, verify implementation, compare design, check implementation, design vs code
Do NOT use for: Simple code review, design document creation, bug fixes
Usage
/gap-analysis user-auth # Analyze user-auth feature gaps
/gap-analysis # Analyze current PDCA state featureAnalysis Workflow
Step 1: Document & Code Discovery
1. Find design document
- docs/02-design/features/{feature}.design.md
- docs/02-design/{feature}.design.md
- docs/design/{feature}.md
2. Find implementation code
- src/features/{feature}/
- src/{feature}/
- app/{feature}/
- lib/{feature}/Step 2: Comparison Items
2.1 API Comparison
| Item | Design | Implementation | Status |
| Endpoint URL | Design spec | Actual route | ✅/❌ |
| HTTP Method | GET/POST/PUT/DELETE | Actual method | ✅/❌ |
| Request Params | Schema definition | Actual type | ✅/❌ |
| Response Format | Design schema | Actual response | ✅/❌ |
| Error Codes | Defined errors | Actual errors | ✅/❌ |
2.2 Data Model Comparison
| Item | Design | Implementation | Status |
| Entity List | Design ERD | Actual models | ✅/❌ |
| Field Definitions | Schema | Type definitions | ✅/❌ |
| Relationships | Design relations | Actual relations | ✅/❌ |
2.3 Feature Comparison
| Item | Design | Implementation | Status |
| Feature List | Requirements | Actual functions | ✅/❌ |
| Business Logic | Design flow | Actual logic | ✅/❌ |
| Error Handling | Design cases | Actual handling | ✅/❌ |
2.4 Convention Compliance
| Item | Rule | Actual | Status |
| Naming | PascalCase/camelCase | Actual naming | ✅/❌ |
| Folder Structure | Design structure | Actual structure | ✅/❌ |
| Import Order | Rule | Actual order | ✅/❌ |
Step 3: Match Rate Calculation
Match Rate = (Matched Items / Total Comparison Items) × 100
Status Determination:
├─ >= 90% → ✅ PASS (Proceed to Report phase)
├─ 70-89% → ⚠️ WARN (Act phase - auto fix)
└─ < 70% → ❌ FAIL (Design review required)Step 4: Gap Classification
## Gap Classification
### 🔴 Missing (Design O, Implementation X)
Items in design but not implemented
→ Implementation required
### 🟡 Added (Design X, Implementation O)
Items implemented but not in design
→ Update design document or remove code
### 🔵 Changed (Design ≠ Implementation)
Items where design differs from implementation
→ Synchronization needed (fix design or implementation)Output Format
# Gap Analysis Report: {feature}
## Analysis Overview
- **Target**: {feature}
- **Design Doc**: docs/02-design/features/{feature}.design.md
- **Implementation Path**: src/features/{feature}/
- **Analysis Time**: YYYY-MM-DD HH:mm
## Match Rate
| Category | Score | Status |
|----------|:-----:|:------:|
| API Match | 85% | ⚠️ |
| Data Model | 100% | ✅ |
| Feature Implementation | 80% | ⚠️ |
| Convention | 90% | ✅ |
| **Total** | **88%** | ⚠️ |
## Gap List
### 🔴 Missing (Implementation Required)
| Item | Design Location | Description |
|------|----------------|-------------|
| Password Reset | design.md:45 | POST /auth/forgot-password not implemented |
### 🟡 Added (Documentation Required)
| Item | Implementation Location | Description |
|------|------------------------|-------------|
| Social Login | src/auth/social.ts | Feature added not in design |
### 🔵 Changed (Synchronization Required)
| Item | Design | Implementation | Impact |
|------|--------|----------------|--------|
| Response Format | { data: [] } | { items: [] } | High |
## Recommended Actions
### Immediate Actions (matchRate < 90%)
1. Implement or remove Missing items from design
2. Synchronize Changed items
### Documentation Updates
1. Reflect Added items in design documentPDCA Status Update
Update .pdca-status.json on analysis completion:
{
"feature": "{feature}",
"phase": "check",
"matchRate": 88,
"gaps": {
"missing": 1,
"added": 1,
"changed": 1
},
"lastAnalysis": "2025-01-31T10:00:00Z",
"iteration": 0
}Next Steps Guidance
matchRate >= 90%:
→ "Gap analysis passed! Generate completion report with /pdca report {feature}."
matchRate < 90%:
→ "Gaps detected. Start auto-correction? (Act phase)"
→ On user approval, proceed with gap-based fixes
→ Auto re-analysis after fixesRelated Skills
/feature-planner- Plan phase/verify- General verification (Gap Analysis specializes in design-implementation comparison)
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.

