feature-completeness
Skill0 starsChanged 5 months agoMITView on GitHub
Traces a feature end-to-end (UI, hook, service, API, controller, database) to verify every link is wired. Use after completing a multi-layer feature or when asked whether a feature is fully connected.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- dotnet/fsharptheir own version, first seen Oct 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- dotnet/fsharp★ 4.3ksame 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 repository38 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- api-contract-validationSkill
- architecture-scannerSkill
- auto-approve-policySkill
- auto-learningSkill
- backend-patternsSkill
- branch-syncSkill
- browser-testSkill
- browseSkill
- build-checkSkill
- cache-refreshSkill
- codebase-explainerSkill
- coding-standardsSkill
- commit-styleSkill
- context-switchingSkill
- continuous-learningSkill
- db-preflightSkill
- env-preflightSkill
- eval-harnessSkill
- file-indexSkill
- frontend-patternsSkill
- function-extractSkill
- idev-initSkill
- import-graphSkill
- lessons-learnedSkill
- post-creation-verifySkill
- pre-ship-verifySkill
- project-mapSkill
- self-reviewSkill
- session-resumeSkill
- skill-benchmarkSkill
- skilloptSkill
- smart-contextSkill
- strategic-compactSkill
- task-journalSkill
- tdd-workflowSkill
- test-coverageSkill
- test-mapSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 8 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
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
- Very specific: line 9
Verify that a newly created feature is fully wired end-to-end — from UI component through hooks/services to API endpoint to backend …
- Distinctive: line 12
After completing a multi-layer feature (FE + BE)
- Distinctive: line 13
After creating a new page/container that calls an API
- Distinctive: line 14
When user reports "it builds but doesn't work"
- Distinctive: line 225
Do NOT run for single-file changes — only for multi-layer features
- Distinctive: line 226
Do NOT trace into external libraries — stop at the project boundary
- Distinctive: line 227
Do NOT check every CRUD operation individually — check the pattern once
- Distinctive: line 228
Do NOT block on database table not existing — warn and continue
- Distinctive: line 229
Do NOT re-read files already checked by other skills — use cached results
≈ “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
Feature Completeness Skill
Purpose
Verify that a newly created feature is fully wired end-to-end — from UI component through hooks/services to API endpoint to backend controller/service/database. Catches disconnected pieces that compile but don't actually work together.
Activation
- After completing a multi-layer feature (FE + BE)
- After creating a new page/container that calls an API
- When user reports "it builds but doesn't work"
How It Works
This skill traces the full request path from UI to database and back, verifying each connection point. It's technology-agnostic — it detects the layers from the architecture-scanner cache.
Phase 1: Identify the Feature Chain
For a full-stack feature, the chain is:
Generic chain (adapts to any stack):
UI Layer → User sees/clicks something
↓
State/Hook Layer → Manages data fetching/mutation
↓
Service Layer → Makes HTTP call to API
↓
API Layer → Receives request, routes to handler
↓
Business Layer → Processes logic, validates, transforms
↓
Data Layer → Reads/writes database
↓
Database → Table exists with correct schemaStack-specific chains:
React + .NET:
Component → useQuery/useMutation → service.ts → API URL →
Controller.cs → Service.cs → Repository → DbContext → SQL Table
React + Express:
Component → useQuery/useMutation → service.ts → API URL →
router.ts → controller.ts → service.ts → Prisma/Sequelize → SQL Table
React + FastAPI:
Component → useQuery/useMutation → service.ts → API URL →
router.py → service.py → SQLAlchemy → SQL Table
Vue + Django:
Component → composable → api.ts → API URL →
views.py → serializer.py → model.py → SQL TablePhase 2: Trace Each Link
For each link in the chain, verify it exists and connects correctly:
Link 1: UI → Hook/State
Check: Does the component import and call the hook?
Grep component file for hook name (e.g., useGetOrders)
Verify: hook is called, return value is used (data, isLoading, error)
Fail if: hook is imported but never called, or return values are ignoredLink 2: Hook → Service
Check: Does the hook call the service function?
Read hook file → find queryFn or mutationFn
Verify: service function is imported and called with correct params
Fail if: service function doesn't exist or signature doesn't matchLink 3: Service → API URL
Check: Does the service make an HTTP call to the correct URL?
Read service file → find axios/fetch call
Verify: URL matches a known backend route (check architecture-scanner cache)
Fail if: URL has no matching backend route (a recurring bug class — see the
lessons-learned skill's log for project-specific instances)Link 4: API URL → Controller
Check: Does the backend controller have a matching route?
Grep controllers for the URL path
Verify: HTTP method matches (GET/POST/PUT/DELETE)
Fail if: no controller route matchesLink 5: Controller → Service
Check: Does the controller call the service method?
Read controller method → find service call
Verify: service interface is injected and method exists
Fail if: service method doesn't exist or parameters don't matchLink 6: Service → Repository/DB
Check: Does the service access the database?
Read service method → find repository/DB calls
Verify: entity type is correct, query filters are present
Fail if: repository for this entity isn't registered (a recurring bug class —
see the lessons-learned skill's log for project-specific instances)Link 7: Database → Table
Check: Does the database table exist?
Check DbContext for DbSet declaration
Check for database change script in .claude/idev/database-changes/
Warn if: DbSet exists but no table creation script foundPhase 3: Report Results
Feature Completeness: Orders CRUD
Chain: UI → Hook → Service → API → Controller → Service → DB
✓ Link 1: OrdersTabContainer → useGetOrders (called, data used)
✓ Link 2: useGetOrders → ordersService.getAll (imported, called)
✓ Link 3: getAll → GET api/orders/get-all (URL found in architecture cache)
✓ Link 4: api/orders/get-all → OrdersController.GetAll (route match)
✓ Link 5: GetAll → _orderService.GetAll (injected, method exists)
✓ Link 6: GetAll → _repository.GetAllAsync (IGenericRepository<Order> registered)
⚠ Link 7: DbSet<Order> exists, DB table pending DBA execution
Result: Feature is wired end-to-end. Blocked on: database table creation.Phase 4: Common Disconnection Points
Issues this skill catches that compile but fail at runtime:
1. Component renders but shows no data
→ Hook is called but service function returns wrong URL (404)
2. Service call succeeds but data shape is wrong
→ FE type doesn't match BE DTO fields (api-contract-validation catches this)
3. Controller receives request but service throws
→ Service depends on unregistered repository (post-creation-verify catches this)
4. Everything works but wrong data appears
→ Query filter missing the tenant filter column (multi-tenancy leak; e.g., a ClientId column)
→ Query missing the soft-delete flag check (e.g., a RecordStatusId column)
5. Feature works for create but not update/delete
→ Only some CRUD operations were wired
→ Missing mutation hooks or service functions
6. Page loads but route doesn't work
→ Component created but route not registered in the project's route registration file (e.g., Routes.tsx)Phase 5: Completeness Checklist
Auto-generated based on detected stack:
Full-Stack CRUD Feature
□ FE Types: Request/Response interfaces defined
□ FE Service: All CRUD functions (getAll, getById, create, update, delete)
□ FE Hooks: useQuery for reads, useMutation for writes
□ FE Container: Imports hooks, handles loading/error/empty states
□ FE Route: Page registered in router (if new page)
□ BE Entity: Created with all required fields
□ BE DTOs: Return, Create, Update DTOs + mapping extensions
□ BE Interface: Service interface with all methods
□ BE Service: Implementation with error handling
□ BE Controller: All route handlers
□ BE DI: Service + Repository registered
□ BE DbContext: DbSet declared
□ DB: Table creation script exists
□ Contract: FE types match BE DTOs
□ Chain: All 7 links verified connectedPhase 6: Integration
Complete feature creation workflow:
1. lessons-learned → prevention steps
2. Create BE files (entity, DTOs, service, controller)
3. post-creation-verify → registrations
4. build-check → BE compiles
5. Create FE files (types, service, hooks, container)
6. build-check → FE compiles
7. api-contract-validation → FE↔BE types match
8. feature-completeness → end-to-end chain verified ← THIS SKILL
9. self-review → code quality
10. Report to userAnti-Patterns
- Do NOT run for single-file changes — only for multi-layer features
- Do NOT trace into external libraries — stop at the project boundary
- Do NOT check every CRUD operation individually — check the pattern once
- Do NOT block on database table not existing — warn and continue
- Do NOT re-read files already checked by other skills — use cached results
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.

