review-implementation
Validates code implementation against project requirements and quality gates.
Install
mkdir -p .claude/skills/review-implementation && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12459" && unzip -o skill.zip -d .claude/skills/review-implementation && rm skill.zipInstalls to .claude/skills/review-implementation
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Perform a fresh-context review of completed work against PRD, tests, and conventions.Key capabilities
- →Check PRD compliance for implemented work
- →Verify test coverage for new code
- →Review code quality against conventions
- →Perform migration safety checks
- →Conduct security checks for hardcoded secrets and tenant isolation
How it works
The skill conducts a fresh-context review of completed work by checking against PRD requirements, test coverage, code quality standards, migration safety, and security best practices. It uses shell commands to inspect the codebase and run tests.
Inputs & outputs
When to use review-implementation
- →Validate PR against PRD
- →Check test coverage
- →Perform migration safety check
About this skill
Skill: Review Implementation
Perform a fresh-context review of completed work against PRD, tests, and conventions.
When to Use
- After implementation is complete, before creating a PR
- As a quality gate before merging
- When reviewing someone else's changes
Process
1. Gather Context
# See all changes
git diff main...HEAD --stat
git log main...HEAD --oneline
# Read the PRD (if one exists)
ls PRDs/
2. PRD Compliance Check
- All requirements from PRD are implemented
- No scope creep — nothing beyond PRD spec
- Architecture matches PRD diagrams
- All phases from implementation plan are complete
3. Test Coverage Check
# Run relevant tests
./bin/run-server-tests
./bin/run-sdk-tests
# Verify test files were added/updated
git diff main...HEAD --name-only | grep -i test
- Every new mutation/query has a corresponding test
- Every model change has a migration test
- Tests use
assertResponseNoErrors+assertDictEqualpattern - No
pytestusage anywhere in new code -
mock.ANYused for dynamic fields (id, timestamps) - Carrier tests follow 4-method pattern (if carrier work)
4. Code Quality Check
Review each changed file for:
- Uses
import karrio.lib as lib(not legacy utilities) - Functional style (list comprehensions, map/filter)
- No bare exceptions, mutable defaults,
anytypes - Django:
OwnedEntityfor tenant-scoped, N+1 prevention - GraphQL:
utils.Connection[T]for lists, proper decorators - No manually edited auto-generated files
5. Migration Safety Check (if applicable)
- Operations ordered correctly
- Data migrations preserve existing data
- No
RunSQL— Django operations only - Works across SQLite, PostgreSQL, MySQL
6. Security Check
- No hardcoded secrets
- Tenant isolation (queries filtered by org)
- Input validation at boundaries
Output Format
## Review Summary
### Status: PASS / NEEDS CHANGES
### Findings
1. [PASS] PRD compliance — all requirements met
2. [FAIL] Missing test for delete mutation
3. [WARN] Consider using mixin for shared logic
### Required Actions
- Add test for delete mutation
When not to use it
- →Before implementation is complete
- →When a PR is already merged
Limitations
- →Requires a PRD for compliance checks
- →Relies on existing test scripts for coverage verification
- →Assumes specific code quality conventions
How it compares
This skill provides a structured, multi-faceted review process for completed work, ensuring compliance and quality before merging, unlike a simple code review.
Compared to similar skills
review-implementation side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| review-implementation (this skill) | 0 | 5mo | Review | Intermediate |
| property-based-testing | 1 | 2mo | No flags | Advanced |
| netalertx-code-standards | 1 | 2mo | Review | Intermediate |
| test | 0 | 1mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
property-based-testing
trailofbits
Provides guidance for property-based testing across multiple languages and smart contracts. Use when writing tests, reviewing code with serialization/validation/parsing patterns, designing features, or when property-based testing would provide stronger coverage than example-based tests.
netalertx-code-standards
netalertx
NetAlertX coding standards and conventions. Use this when writing code, reviewing code, or implementing features.
test
FalkorDB
Run FalkorDB's test suites - Rust unit tests, Python e2e/function/MVCC/concurrency tests, openCypher TCK compliance tests, and flow tests. Use when asked to run, narrow down, or debug a failing test, or to decide which suite covers a change.
api-test-generator
mikopbx
Генерация полных Python pytest тестов для REST API эндпоинтов с валидацией схемы. Использовать при создании тестов для новых эндпоинтов, добавлении покрытия для CRUD операций или валидации соответствия API с OpenAPI схемами.
generate-validation-notebook
monte-carlo-data
Generate SQL validation notebooks for dbt changes. Pass a GitHub PR URL or local dbt repo path.
mock-interviewer
std2main
模拟硅谷大厂 Senior Engineer 进行技术面试，支持语音交互和实时代码审计。