S Skillteca
Receber por email
Explorar Categorias Coleções Newsletter
← Voltar para o catálogo

process-code-review

Segurança Autor: aiskillstore

Process code review findings interactively - fix or skip issues from monty-code-review output. Presents issues in severity order, applies fixes, runs quality checks, and updates review documents with status markers.

367estrelas
Atualizado há 4 meses
Ver no GitHub ↗

Como adicionar

/plugin marketplace add aiskillstore/marketplace

O comando exato pode variar conforme o repositório. Confira o README no GitHub.

Para o autor da skill

Cole no README do seu repo

Mostra que sua skill está catalogada na Skillteca, gera backlink e tráfego rastreável.

[![Skillteca](https://www.skillteca.com.br/api/badge/process-code-review/svg)](https://www.skillteca.com.br/skills/process-code-review)

Skills relacionadas

Ver todas de Segurança →

security-research

63k

Habilidade de pesquisa de segurança em Modo Equipe que orquestra 3 caçadores de vulnerabilidades e 2 engenheiros de PoC para auditar um código, provar explorabilidade, classificar causas raiz e calibrar a severidade. É utilizada para revisão de segurança, pesquisa de vulnerabilidades, auditoria de explorabilidade e validação de modelo de ameaças.

Segurança por code-yeongyu

security-scanning-security-dependencies

41.2k

You are a security expert specializing in dependency vulnerability analysis, SBOM generation, and supply chain security. Scan project dependencies across multiple ecosystems to identify vulnerabilities, assess risks, and provide automated remediation strategies.

Segurança #ai #git por sickn33

vulnerability-scanner

41.2k

Advanced vulnerability analysis principles. OWASP 2025, Supply Chain Security, attack surface mapping, risk prioritization.

Segurança #ai #git por sickn33

dependency-management-deps-audit

41.2k

You are a dependency security expert specializing in vulnerability scanning, license compliance, and supply chain security. Analyze project dependencies for known vulnerabilities, licensing issues, outdated packages, and provide actionable remediation strategies.

Segurança #ai #git por sickn33

Alerta por categoria

Receba novas skills de Segurança toda segunda

1 email curto, só com as skills novas de Segurança. 4 minutos de leitura, sem spam, cancela com 1 clique.

Você confirma o email no primeiro envio. Sem spam. Cancela com 1 clique.

Ler descrição completa

Process Code Review Skill

When to Use This Skill

  • After running /monty-code-review:code-review to generate a review document.
  • When you have a *_review.md file with severity-tagged issues to process.
  • When you want systematic, tracked resolution of code review findings.
  • When reviewing a colleague's code review document and fixing issues one-by-one.

This skill is the second step in the code review workflow:

Step 1: /monty-code-review:code-review → Creates *_review.md
Step 2: /process-code-review:process-review *_review.md → Fix/skip issues
Step 3: /backend-atomic-commit:pre-commit → Run pre-commit checks and fix issues

Example Prompts

Basic Usage

  • "Process the wellbeing_service_review.md file and help me fix the issues."
  • "Use your process-code-review skill on optimo_core/docs/code_reviews/api_review.md"
  • "Go through the code review findings in this file and fix or skip each one."

With Arguments

  • /process-code-review:process-review myfile_review.md - Interactive mode (default)
  • /process-code-review:process-review --dry-run myfile_review.md - Preview only, no changes
  • /process-code-review:process-review --auto myfile_review.md - Auto-fix all issues
  • /process-code-review:process-review --auto --severity=NIT myfile_review.md - Auto-fix only NITs
  • /process-code-review:process-review --severity=BLOCKING api_review.md - Process only BLOCKING issues

Processing Workflow

When this skill is active and you are asked to process a review document:

1. Parse Review Document

Read the review file and extract all issues. Look for:

  • Severity tags: [BLOCKING], [SHOULD_FIX], [NIT]
  • Issue titles: Following the severity tag
  • Location: File path and line numbers
  • Code snippets: Current problematic code
  • Problem description: Explanation of the issue
  • Proposed fix: Suggested code or approach

Common patterns to look for:

### [BLOCKING] Issue Title

**Location:** path/to/file.py:L120-L145

**Current code:**
...

**Problem:**
...

**Proposed fix:**
...

2. Create Todo List

Use TodoWrite to track all issues:

  • Group by severity: BLOCKING first, then SHOULD_FIX, then NIT
  • Mark each as pending initially
  • Update status as you process each issue

Example todo list structure:

[BLOCKING] C1. N+1 Query Pattern - pending
[BLOCKING] C2. Missing Org Scoping - pending
[SHOULD_FIX] S1. Performance Issue - pending
[NIT] N1. Docstring Missing - pending

3. Present Issues One-by-One

For each issue, starting with highest severity, display:

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[SEVERITY] Issue Title (N of M)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Location: file.py:L120-L145

Current Code:
    <code snippet from review>

Problem:
    <description of issue>

Proposed Fix:
    <suggested code or approach>

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Then ask: Fix this issue or skip it?

Wait for user response before proceeding.

4. Handle User Response

If User Says "Fix" / "Yes" / "Proceed"

  1. Read the source file to understand current state
  2. Apply the proposed fix using Edit tool
  3. Run quality checks on the modified file:
  4. .bin/ruff check <file> --fix
  5. .bin/ruff format <file>
  6. Update the review document to mark the issue as FIXED:

``markdown ### [BLOCKING] Issue Title Status: ✅ FIXED (YYYY-MM-DD) ``

  1. Update TodoWrite to mark as completed
  2. Move to the next issue

If User Says "Skip" / "Ignore" / "No"

  1. Do NOT modify the source file
  2. Ask for optional reason (or use "Deferred")
  3. Update the review document to mark the issue as IGNORED:

``markdown ### [BLOCKING] Issue Title Status: ⏭️ IGNORED (YYYY-MM-DD) Reason: [User's reason or "Deferred"] ``

  1. Update TodoWrite to mark as completed (skipped)
  2. Move to the next issue

5. Quality Checks

After each fix, run quality checks:

  • ruff check <file> --fix - Auto-fix linting issues
  • ruff format <file> - Format code
  • ty check <file> - Type check (baseline acceptable)
  • python manage.py check - Django system checks (if applicable)

If quality checks reveal additional issues, fix them before moving on.

6. Summary After Processing

When all issues are processed, provide a summary:

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Review Processing Complete
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Total Issues: 13
  ✅ Fixed: 8
  ⏭️ Skipped: 3
  📅 Deferred: 2

Files Modified:
  - optimo_core/services/wellbeing_service.py
  - optimo_core/schemas/wellbeing.py

Next Steps:
  Run /backend-atomic-commit:pre-commit to run pre-commit checks and fix issues.
  Review document remains uncommitted (working documentation).
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Status Markers

Use these markers when updating review documents:

| Status | Marker | Meaning | |--------|--------|---------| | Open | (no marker) | Issue not yet addressed | | Fixed | ✅ FIXED | Issue has been resolved in code | | Ignored | ⏭️ IGNORED | Issue intentionally skipped | | Won't Fix | 🚫 WON'T FIX | Issue acknowledged but will not be fixed | | Deferred | 📅 DEFERRED | Issue to be addressed in future work |

Always include the date: Status: ✅ FIXED (2025-01-15)

Severity Priority Order

Process issues in this order:

  1. [BLOCKING] - Must fix before merge
  2. Correctness issues
  3. Security flaws
  4. Data integrity problems
  5. Multi-tenant boundary violations
  1. [SHOULD_FIX] - Important but not blocking
  2. Performance issues
  3. Missing tests
  4. Confusing control flow
  1. [NIT] - Minor style/structure issues
  2. Docstring improvements
  3. Variable naming
  4. Code organization

Quality Gates

Before marking a review as complete, verify:

  1. All [BLOCKING] issues are either Fixed or explicitly Ignored with documented reason
  2. All [SHOULD_FIX] issues are addressed or have a documented deferral reason
  3. Linting passes: .bin/ruff check --fix
  4. Formatting is correct: .bin/ruff format
  5. Type checks pass baseline: .bin/ty check
  6. Relevant tests still pass

Handling Arguments

Parse arguments to adjust behavior:

Available Flags

| Flag | Description | |------|-------------| | --dry-run | Show all issues and proposed fixes without modifying any files | | --auto | Apply all fixes without prompting (use with caution) | | --severity=<LEVEL> | Filter to only process issues of specified severity | | (no flags) | Interactive mode - prompt for each issue (default) |

Severity Filter Values

  • --severity=BLOCKING - Only process BLOCKING issues
  • --severity=SHOULD_FIX - Only process SHOULD_FIX issues
  • --severity=NIT - Only process NIT issues

Examples

# Preview all issues without making changes
/process-code-review:process-review --dry-run api_review.md

# Auto-fix everything (careful!)
/process-code-review:process-review --auto api_review.md

# Auto-fix only minor issues, prompt for important ones
/process-code-review:process-review --auto --severity=NIT api_review.md

# Focus on critical issues only
/process-code-review:process-review --severity=BLOCKING api_review.md

# Dry-run to see only BLOCKING issues
/process-code-review:process-review --dry-run --severity=BLOCKING api_review.md

Combining Flags

Flags can be combined:

  • --dry-run --severity=BLOCKING: Preview only BLOCKING issues
  • --auto --severity=NIT: Auto-fix only NITs (safe for minor style fixes)

File Modification Rules

  • Source files: Modify to apply fixes
  • Review document: Update with status markers only
  • This skill does NOT commit: After processing, run /backend-atomic-commit:pre-commit to run pre-commit checks on staged changes

Strictness Guidelines

  • For [BLOCKING] issues: Be thorough, ver
Compartilhar X LinkedIn