Run any Skill in Manus
with one click
with one click
Run any Skill in Manus with one click
Get Started$pwd:
$ git log --oneline --stat
stars:1,338
forks:158
updated:February 24, 2026 at 04:09
File Explorer
SKILL.md
Fix Prisma schema compilation errors
Fix Interface and Controller compilation errors
Fix Provider, Collector, Transformer compilation errors
Fix Test compilation errors
Validate Prisma schema against requirements specification (read-only)
Validate Controllers and DTOs against requirements (read-only)
| name | add-feature |
| description | Implement new feature with self-testing loop until 100% pass |
| argument-hint | [feature-description] |
| allowed-tools | Read, Edit, Write, Bash, Grep, Glob |
Implement a new feature and iterate until all tests pass (100% success rate).
NEVER use:
as keyword (type assertion)any type$ARGUMENTS
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
ā Phase 1: Implementation ā
ā - Controller ā
ā - Provider ā
ā - Collector/Transformer ā
ā - Interface ā
āāāāāāāāāāāāāāāāā¬āāāāāāāāāāāāāāāāāāāāāā
ā
ā¼
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
ā Phase 2: Test Design ā
ā - Happy path tests ā
ā - Error case tests ā
ā - Edge case tests ā
āāāāāāāāāāāāāāāāā¬āāāāāāāāāāāāāāāāāāāāāā
ā
ā¼
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
ā Phase 3: Test Loop ā
ā while (pass_rate < 100%) { ā
ā run tests ā
ā analyze failures ā
ā fix code ā
ā } ā
āāāāāāāāāāāāāāāāā¬āāāāāāāāāāāāāāāāāāāāāā
ā
ā¼
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
ā Complete ā
ā All tests pass! ā
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
See: flow-implement.md
Analyze Requirements
$ARGUMENTSCreate/Update Interface
Create/Update Collector
Create/Update Transformer
Create/Update Provider
Create/Update Controller
Verify Build
npm run build:main
See: flow-test-design.md
Design comprehensive test scenarios including:
See: flow-test-loop.md
REPEAT:
1. Build tests
npm run build:test
2. Run tests
npm run test -- --include "{feature}"
3. If all pass ā DONE
4. If failures:
a. Analyze failure reason
b. Determine if test code issue or business logic issue
c. Fix the appropriate code
d. Go to step 1
UNTIL: 100% pass rate
ā Success Criteria:
npm run build:main passesnpm run build:test passesnpm run test passes with 100% success rateā Failure (requires manual intervention):
When complete, provide:
## Feature Implementation Complete
### Summary
- Feature: {description}
- Files created/modified: X
- Test scenarios: Y
- Pass rate: 100%
### Files Changed
- src/api/structures/I{Entity}.ts
- src/controllers/{path}/{Controller}.ts
- src/providers/{provider}.ts
- src/collectors/{Collector}.ts
- src/transformers/{Transformer}.ts
- test/prepare/prepare_random_{entity}.ts
- test/generate/generate_random_{entity}.ts
- test/features/api/{entity}/*.ts
### Test Results
- Total: X tests
- Passed: X
- Failed: 0