Provides high-rigor architectural review focusing on security, decoupling, and software principles.
Install
mkdir -p .claude/skills/qa-forecast-bio && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17337" && unzip -o skill.zip -d .claude/skills/qa-forecast-bio && rm skill.zipInstalls to .claude/skills/qa-forecast-bio
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.
Use for paranoid, language-agnostic architectural code review — applies SOLID, DRY/KISS/YAGNI, decoupling, OWASP/NIST security, and quantitative complexity thresholds (cyclomatic > 15 fails) via the ADIHQ framework. Output is a strictly formatted Severity / Dimension / Location / Violation / Mandated Refactor matrix. Trigger when the user asks for "QA review", "architectural review", "review my PR rigorously", "/qa", or wants a hard pass on a diff or design.Key capabilities
- →Evaluate code against Dependency Inversion principles
- →Identify and reject architectural anti-patterns like God Objects
- →Enforce SOLID principles (SRP, OCP, LSP, ISP, DIP)
- →Reduce complexity by enforcing DRY, KISS, YAGNI principles
- →Apply naming conventions for variables and functions
- →Enforce security frameworks like OWASP/NIST for input handling and cryptography
How it works
The skill acts as a Quality Assurance System Architect, evaluating code against strict, language-agnostic software engineering principles and security frameworks, then outputting a structured review matrix.
Inputs & outputs
When to use qa
- →Perform architectural code review
- →Evaluate system design for security
- →Audit PRs for anti-patterns
About qa
Acts as a paranoid architectural reviewer. Evaluates code against SOLID, DRY, and security standards, providing a structured matrix of violations and refactors.
Use for paranoid, language-agnostic architectural code review — applies SOLID, DRY/KISS/YAGNI, decoupling, OWASP/NIST security, and quantitative complexity thresholds (cyclomatic > 15 fails) via the ADIHQ framework. Output is a strictly formatted Severity / Dimension / Location / Violation / Mandate
When not to use it
- →When subjective judgment is acceptable for code review
- →When immediate functional output is prioritized over long-term viability
- →When code is intended to violate architectural principles
Limitations
- →The skill prioritizes long-term system viability, structural modularity, and security.
- →It applies quantitative complexity thresholds.
- →Output is a strictly formatted Severity / Dimension / Location / Violation / Mandated Refactor matrix.
How it compares
This skill provides an automated, rigorous, and structured architectural code review based on predefined engineering principles and security standards, unlike manual or less formal reviews.
Compared to similar skills
qa side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| qa (this skill) | 0 | 3mo | No flags | Advanced |
| reviewing-code | 21 | 9mo | No flags | Intermediate |
| pr-review | 6 | 3mo | Review | Intermediate |
| code-review-checklist | 3 | 1mo | No flags | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by forecast-bio
View all by forecast-bio →You might also like
reviewing-code
CaptainCrouton89
Systematically evaluate code changes for security, correctness, performance, and spec alignment. Use when reviewing PRs, assessing code quality, or verifying implementation against requirements.
pr-review
pytorch
Review PyTorch pull requests for code quality, test coverage, security, and backward compatibility. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".
code-review-checklist
vudovn
Code review guidelines covering code quality, security, and best practices.
fix-review
sickn33
Verify fix commits address audit findings without new bugs
django-verification
affaan-m
Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.
agent-reviewer
ruvnet
Agent skill for reviewer - invoke with $agent-reviewer