skills.rest
undertext
undertextCOMMUNITY
Explore all skills by this author →
GitHub

spdd-code-review

Compare code against REASONS-Canvas prompts to detect alignment gaps and intent drift.

Updated Jul 7, 2026
Search Tags:#code review#AI code review#structured review#REASONS-Canvas#alignment analysis
One-click install
npx skills add https://github.com/undertext/spdd-skills --skill spdd-code-review
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: spdd-code-review
Source: https://github.com/undertext/spdd-skills/tree/main/skills/optional/spdd-code-review
Command: npx skills add https://github.com/undertext/spdd-skills --skill spdd-code-review

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, pdf2image, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of reviewing code to ensure it aligns with structured prompts defined using REASONS-Canvas, significantly reducing the cognitive load of manual code reviews.

Core Features & Use Cases

  • Code Alignment: Compares code against REASONS-Canvas structured prompts for alignment across various dimensions (requirements, entities, approach, structure, operations, norms, safeguards).
  • Intent Drift Detection: Identifies and flags additions, omissions, and divergent approaches between the code and the prompt.
  • Safeguard Violation Check: Verifies that all constraints specified in the prompts are respected.
  • Implicit Decision Surfacing: Identifies places where AI has made decisions without explicit guidance.
  • Scope Boundary Check: Ensures the code changes are within the defined scope.
  • Use Case: Use this Skill after code generation to ensure the resulting code adheres to the defined specifications and intent, facilitating better integration into existing systems.

Quick Start

To review the code changes made to the 'GGQPA-XXX-202603131530-[Feat]-token-usage-billing.md' prompt, use the command: /spdd-code-review @spdd/prompt/GGQPA-XXX-202603131530-[Feat]-token-usage-billing.md --git-diff HEAD~3

Frequently Asked Questions about spdd-code-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate code review for alignment with structured prompts?▼

Automating code review for structured prompt alignment involves parsing your codebase and comparing it against prompt definitions to identify intent drift, safeguard violations, and scope boundary issues. This process surfaces implicit decisions and gaps between code and specifications, reducing manual cognitive load.

What is intent drift detection in AI-generated code?▼

Intent drift detection in AI-generated code identifies additions, omissions, and divergent approaches between the implemented code and the original structured prompt. It flags where the AI has made decisions without explicit guidance or strayed from defined requirements and constraints.

How do I check code changes against REASONS-Canvas prompts using Python?▼

To check code changes against REASONS-Canvas prompts, you run Python scripts that parse the codebase and compare it with the prompt file. You can execute a command specifying the prompt file path and a git diff range to review recent code changes for alignment.

Do I need pypdf and pdfplumber to perform structured code alignment analysis?▼

Yes, performing structured code alignment analysis requires Python libraries like pypdf, pdfplumber, and pdf2image. These dependencies are necessary for the scripts to parse the prompt files and codebase to execute the automated review process.

When should I use an automated safeguard violation check for code?▼

You should use an automated safeguard violation check after AI code generation to verify that all constraints specified in your structured prompts are respected. It ensures the resulting code adheres to defined specifications and facilitates integration into existing systems.

Related Skills

Explore More Software Engineering Skills→
eastreamseastreams
641

pdf

Extract text and structured data from PDF files using Python libraries.

Official
Intermediate
alxayoalxayo
17

checkov-security-scan

Detect security misconfigurations and compliance violations in Infrastructure as Code.

Community
Advanced
dcasotadcasota
6

habv4-context-summarizer

Generate structured summaries of files and directories to reduce LLM token usage.

Community
Basic
undertextundertext

spdd-reverse

Extract requirements, entities, and structure from codebases into REASONS Canvas prompts.

Community
Advanced