Controlflow Review (Grade A) logo

Controlflow Review (Grade A)Security-tested data-ai skill for Claude AI. Grade A. Use when asked to review code, a diff, or a completed phase, especially when the result should emphasize bugs, regressions, validation status, and

— (0)
Daniel NikulshynReviewed by Daniel Nikulshyn·Updated July 2026

Overview

Controlflow Review is a security-tested data-ai skill for Claude AI that adds a layer over native code review capabilities. It's used to review code, diffs, or completed phases, focusing on bugs, regressions, validation status, and security. The skill compares implementation to a plan, if one exists, and checks for scope drift. It also performs proactive vulnerability and error searches, providing evidence-backed findings with severity, confidence, and file/line evidence.

Key features

  • Plan-vs-implementation scope-drift comparison
  • Evidence-backed finding discipline
  • Proactive vulnerability/error search
  • Severity and confidence labeling
  • File/line evidence and validation method

Pricing

Model
Free
Category
Skills
Rating
No reviews yet

Use cases

Code Review

Use Controlflow Review to review code changes, focusing on bugs, regressions, and security issues.

Diff Review

Use Controlflow Review to review diffs, comparing implementation to a plan and checking for scope drift.

Completed Phase Review

Use Controlflow Review to review completed phases, ensuring correctness, security, and data integrity.

Pros & Cons

Pros

  • Adds plan-vs-implementation comparison to native code review
  • Provides evidence-backed findings with severity and confidence
  • Proactively searches for vulnerabilities and errors
  • Prioritizes correctness, security, and data integrity

Cons

  • Requires a plan to exist for full functionality
  • May not be suitable for all types of code reviews
  • Depends on native /code-review or security-review for mechanical pass

Reviews

Sign in to leave a review.

No reviews yet. Be the first!

Q&A

Are there code bases or review scenarios where Controlflow Review isn’t suitable?

The skill is less useful when no implementation plan exists, or for reviews that only need mechanical/style checks, since those are delegated to the native /code‑review or security‑review passes.

Asked by Adaeze Uche · Jul 27, 2026

What types of issues can Controlflow Review automatically detect that native reviews might miss?

It proactively searches for bugs, regressions, data‑integrity problems, and security defects, providing file/line evidence and confidence scores, especially for scope drift such as missing or extra phases relative to the plan.

Asked by Xiomara Delgado · May 12, 2026

How does Controlflow Review complement Claude’s native /code‑review or security‑review?

Controlflow Review runs after the native review, consuming its mechanical and style results. It adds plan‑vs‑implementation drift analysis, proactive vulnerability hunting, and severity/confidence labeling, without duplicating linting or formatting checks.

Asked by Margaret Whitfield · Apr 19, 2026

Do I need to have a pre‑written plan for Controlflow Review to work effectively?

Yes. The skill’s core feature is comparing implementation to a plan, so it provides full scope‑drift detection and evidence‑backed findings only when a plan file (e.g., plans/<task‑slug>/plan.md) is present.

Asked by Damian Wysocki · Apr 17, 2026

Ask a question

Skills alternatives

Using Git Worktrees (Grade A) logo
Using Git Worktrees (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktre

— (0)
Free
Ga4 Bigquery Schema (Grade A) logo
Ga4 Bigquery Schema (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. GA4 BigQuery Export Schema Reference — complete field reference, nested structures, query patterns, and performance tips

— (0)
Free
Meta Capi (Grade A) logo
Meta Capi (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Meta Conversions API (CAPI) Setup Reference — architecture, event types, customer information hashing, deduplication, implementation examples, AEM

— (0)
Free
Callees (Grade A) logo
Callees (Grade A)Skills

Security-tested development skill for Claude AI. Grade A. Lista o que uma funcao/metodo chama (call graph direto)

— (0)
Free
Test Module Name (Grade A) logo
Test Module Name (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Name Haskell test modules after the module under test with a Spec suffix in the same namespace. Use when writing or reviewing Haskell test module

— (0)
Free
Board Of Directors (Grade A) logo
Board Of Directors (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Simulate a 5-member expert board deliberation for major decisions. Use when evaluating plans, architecture choices, feature designs, or any decisi

— (0)
Free
Advpl Mvc Avancado (Grade A) logo
Advpl Mvc Avancado (Grade A)Skills

Security-tested development skill for Claude AI. Grade A. MVC avançado via PE (Pontos de Entrada) — adicionar grids customizadas em telas MVC padrão (CNTA300/MATA070/MATA440/MATA460/FINA040 via *STRU)

— (0)
Free
D
Docs Writer (Grade A)Skills

Security-tested devops skill for Claude AI. Grade A. **WORKFLOW SKILL** — Maintains repository documentation accuracy and freshness across the docs site, agent files, and changelog. WHEN: "update docs

— (0)
Free