Skip to content
cccskills
FreePublished on GitHub

add-code-review

Code review: IoC, RESTful, Contracts, Security (OWASP), Clean Architecture, SOLID.

The English summary is being prepared. Showing the original description.

See how to install

Files included (2)

  • SKILL.md8.9 KB
  • source.json602 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

Code Review

Skill for validating implemented code against project standards.

Use for: Validate code, identify violations, auto-fix (autopilot) Do not use for:

  • Implementing new features (use add-backend-development / add-frontend-development)
  • Planning or specifying work (use add-planning / add-feature-specification)
  • Codebase discovery or architecture analysis (use add-feature-discovery / add-architecture-discovery)

Reference: Always consult CLAUDE.md for general project standards.


MANDATORY RULE: TodoWrite

BEFORE starting any review, you MUST create a todo list using TodoWrite.

The code-review agent MUST create todos for each validation category and for each changed file. This ensures:

  1. Progress visibility for the user
  2. No validation is forgotten
  3. Traceability of fixes

Reference Skills

Load BEFORE reviewing:

  • Backend: {{skill:add-backend-development/SKILL.md}}
  • Database: {{skill:add-database-development/SKILL.md}}
  • Frontend (Code): {{skill:add-frontend-development/SKILL.md}}
  • Frontend (UI): {{skill:add-ux-design/SKILL.md}}
  • Security: {{skill:add-security-audit/SKILL.md}}

Validation Categories

1. Spec Compliance (CRITICAL)

Spec vs implementation gap = the root cause of features that "pass review" but diverge from what was planned.

Sources (lookup):

{"sources":{"contracts":"docs/features/${FEATURE_ID}/plan.md (prose: routes, services, DTOs, queues)","tick_state":"docs/features/${FEATURE_ID}/tasks.md → ## Acceptance Checklist"}}

Validation procedure:

  1. READ contracts from plan.md prose (routes, services, DTOs, queues)
  2. READ tick state from tasks.md → ## Acceptance Checklist (each item ends with (RFNN/RNNN) reference)
  3. For EACH contract item:
    1. Locate implementation with file:line
    2. Validate EXISTENCE and BEHAVIOR:
      • Route exists AND accepts correct params?
      • Service is generic as spec OR hardcoded?
      • DTO has all specified fields?
    3. Cross-reference: do items cover ALL RF/RN from about.md?
    4. Status: COMPLIANT | DIVERGENT (exists but differs) | MISSING

Examples:

TypeSpecCodeFix
DIVERGENTPOST /billing/webhook/:providerPOST /webhook (fixed route)Refactor route to accept :provider param
DIVERGENTWebhookNormalizerService (generic)StripeWebhookService (hardcoded)Extract generic interface, rename service
MISSINGWebhookSignatureGuardNo guard foundImplement guard or document explicit scope exclusion

Spec Compliance scoring:

  • COMPLIANT (all items match): full points
  • DIVERGENT (functional but differs): -1 per item
  • MISSING (not implemented): -2 per item, blocks merge if RF-linked

2. Architecture Contract (MOST CRITICAL)

Architecture violation = CRITICAL BLOCKER. Fix BEFORE any other validation.

Source: CLAUDE.md → ## Architecture Contract.

Validation steps:

For EACH new/modified file:

  1. Identify the file's layer/package
  2. Grep imports of @org/* (or project alias)
  3. Verify against Import rules from the contract
  4. Verify the artefact is in the correct package (Placement)

Examples:

ViolationFix
interfaces imports databaseMove artefact or adjust import
Service-contract DTO in databaseMove DTO to interfaces
domain imports anythingRemove import — domain has zero deps

3. IoC Configuration (CRITICAL)

Code without correct IoC does NOT work at runtime.

Checklist by component type (lookup)

{"iocChecklist":{"Service":{"decorator":"@Injectable()","providers":"feature module","exports":false,"controllers":false,"indexTs":false},"Repository":{"decorator":"@Injectable()","providers":"db module","exports":"db module","controllers":false,"indexTs":"libs/"},"Handler":{"decorator":"@Injectable()","providers":"feature module","exports":false,"controllers":false,"indexTs":"NEVER"},"Guard":{"decorator":"@Injectable()","providers":"feature/global","exports":false,"controllers":false,"indexTs":false},"Controller":{"decorator":"@Controller()","providers":false,"exports":false,"controllers":"feature module","indexTs":false}}}

Files to verify for IoC

FileCheck
apps/backend/src/app.module.tsimports[] contains module
[feature].module.tsproviders[], controllers[], imports[]
libs/app-database/src/app-database.module.tsproviders[], exports[] for repos
libs/app-database/src/index.tspublic repo exports
libs/app-database/src/types/Database.tsnew table types
libs/domain/src/index.tsnew entity/enum exports

Common IoC Errors

ErrorCauseFix
Nest can't resolve dependencies of XX not in providers[] or X's dependency not registeredAdd X and its dependencies to providers[]
X is not a providerMissing @Injectable() or not registeredAdd decorator and register in providers[]
Module X not foundModule not imported in AppModuleAdd to AppModule.imports[]
Repository not foundRepo not exported in db module exports[]Add to AppDatabaseModule exports[]
404 on endpointController not registered or module not importedCheck controllers[] and AppModule.imports[]

4. RESTful Compliance (CRITICAL)

RuleCorrectWrong
HTTP methodGET read, POST create, DELETE removePOST for read
URL/users (noun)/getUsers (verb)
Status201 POST, 204 DELETE200 for all

5. Contract Validation (CRITICAL)

Frontend ↔ Backend:

BackendFrontend
Datestring
Enumunion type

Sync required / optional fields between backend and frontend.

JSONB rules:

  • NO double parse
  • NO double stringify
  • Kysely handles automatically

6. Security (OWASP)

CategoryCheck
Injectionparametrized queries
Authguards applied
Data Exposureno secrets in logs
Access Controlfilter by account_id
XSSoutputs sanitized

Multi-tenant:

  • EVERY query filters account_id
  • account_id from JWT, not body

7. SOLID Principles

  • SRP: one class, one responsibility
  • OCP: open for extension, closed for modification
  • LSP: subtypes substitutable
  • ISP: specific interfaces over general
  • DIP: depend on abstractions

8. Code Quality

  • No any type
  • DTOs follow naming
  • No console.log (use logger)
  • No commented code
  • No unused imports
  • Exception handling

9. Database

  • Migration created
  • Has up and down
  • Kysely types updated
  • Entity exported
  • Repository exported

10. Environment

  • New vars in .env.example
  • Example values not real
  • Use IConfigurationService, not process.env

Score

Weights and status (lookup):

{"weights":{"specCompliance":20,"archContract":20,"ioc":15,"restful":10,"contracts":15,"security":15,"solid":10,"quality":10,"database":5}} {"status":{"8-10":"APPROVED","6-7":"NEEDS ATTENTION","4-5":"NEEDS FIXES","0-3":"CRITICAL"}}


Process

Phase 1: Load Context & Create Todos

  1. bash .codeadd/scripts/status.sh
  2. Read reference skills (backend, database, frontend, security)
  3. Read CLAUDE.md
  4. Identify ALL changed files
  5. Create TodoWrite (see MANDATORY RULE) covering each validation category and changed file

Phase 2: Validate

For EACH changed file, validate in order, marking each todo in_progress → completed:

  1. Spec Compliance — see §1
  2. Architecture Contract — see §2 (CRITICAL BLOCKER if violated; fix before continuing)
  3. IoC Configuration — see §3
  4. RESTful Compliance — see §4
  5. Contract Validation — see §5
  6. Security (OWASP) — see §6
  7. SOLID Principles — see §7
  8. Code Quality — see §8
  9. Database — see §9

Phase 3: Fix (autopilot)

  1. For each issue found:
    • Create specific todo: "Fix [issue] in [file]"
    • Mark as in_progress
    • Apply fix
    • Mark as completed
  2. Verify build compiles
  3. Document before/after

Phase 4: Report

Generate the review report at docs/features/${featureId}/review.md. The exact output template (score table, issue format, build status) is owned by the consuming command (add.review) — this skill validates; the command formats.


Rules

Do:

  • Create TodoWrite BEFORE starting review and update it during each phase
  • Load reference skills BEFORE review
  • Run status.sh FIRST
  • Auto-fix in autopilot
  • Verify build
  • Document before/after

Don't:

  • Start review without creating TodoWrite
  • Skip Architecture Contract validation (MOST critical)
  • Skip IoC validation
  • Report without fixing (autopilot)
  • Ignore skill patterns
  • Accept "works" as justification
  • Leave non-compiling code
  • Forget to verify AppModule.imports[] or barrel exports in libs/

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

007

Free

Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code review, incident response, and infrastructure security for any project.

The English summary is being prepared. Showing the original description.

aibot88/sec_skill_store5Updated May 27, 2026

Guides the creation of agile user stories and Gherkin feature files. Use when the user wants to create a user story, write acceptance criteria, define Gherkin scenarios, or author BDD feature files. This should trigger for requests such as Create a user story; Write a user story; I need to write a user story. Part of cursor-rules-java project

The English summary is being prepared. Showing the original description.

aibot88/sec_skill_store5Updated May 27, 2026

Facilitates conversational discovery to create Architectural Decision Records (ADRs) for non-functional requirements using the ISO/IEC 25010:2023 quality model. Use when the user wants to document quality attributes, NFR decisions, security/performance/scalability architecture, or design systems with measurable quality criteria. This should trigger for requests such as Create ADR for Non-functional requirements; Document Non-functional requirements; Capture Non-functional requirements; Generate Non-functional requirements in an ADR. Part of cursor-rules-java project

The English summary is being prepared. Showing the original description.

aibot88/sec_skill_store5Updated May 27, 2026

Run a health check on an existing project: dependency audit, security scan, test runner detection, CI/CD evaluation, and missing configuration analysis. Maps the three execution gates (pre/in/post) from /10x-bootstrapper to an assessment framework for existing codebases. Reads optional context/foundation/stack-assessment.md from /10x-stack-assess to focus checks on identified gaps. Writes context/foundation/health-check.md with findings, prioritized fixes, and an agent-readiness verdict. Use when the user has an existing project and wants to verify its health before working with an agent. Trigger phrases: "health check", "check my project", "audit my project", "is my project healthy", "sprawdź projekt", "audyt projektu", "health-check", "project health". Use AFTER /10x-stack-assess (brownfield chain), BEFORE agent onboarding (m1-l4).

The English summary is being prepared. Showing the original description.

aibot88/sec_skill_store5Updated May 27, 2026

You MUST use this when building projects end-to-end. Orchestrates all 12 team roles — automatically switches between CTO, architect, PM, engineers, SRE, security, DBA, QA, and EM based on the current phase of work. Starts with brainstorming before any implementation.

The English summary is being prepared. Showing the original description.

aibot88/sec_skill_store5Updated May 27, 2026

Use when you need to add or configure Maven plugins in your pom.xml — including quality tools (enforcer, surefire, failsafe, jacoco, pitest, spotbugs, pmd), security scanning (OWASP), code formatting (Spotless), version management, container image build (Jib), build information tracking, and benchmarking (JMH) — through a consultative, modular step-by-step approach that only adds what you actually need. This should trigger for requests such as Add Maven plugins in pom.xml; Improve Maven plugins in pom.xml. Part of cursor-rules-java project

The English summary is being prepared. Showing the original description.

aibot88/sec_skill_store5Updated May 27, 2026

See all skills by aibot88

Report a problem with this skill