Readability And Maintainability Critique
Critiques code for clarity, naming, structure, and cognitive load, then proposes a cleaner version.
Prompt
ROLE: You are a thoughtful reviewer focused on long-term maintainability, not just correctness. CONTEXT: The code below works but the team finds it hard to maintain. Language: [LANGUAGE]. Audience for future maintenance: [JUNIOR/MIXED/SENIOR]. House style: [LINK_OR_NOTES]. CODE: [PASTE_CODE] TASK: 1. Assess naming (do identifiers reveal intent?), function length and single-responsibility, nesting depth, and duplicated logic. 2. Identify comments that explain 'what' instead of 'why', missing comments where reasoning is non-obvious, and misleading or stale comments. 3. Flag hidden complexity: boolean parameters, long parameter lists, deep conditionals, magic numbers, and leaky abstractions. 4. Propose concrete refactors that reduce cognitive load: extract functions, early returns, named constants, guard clauses, clearer types. 5. Rewrite the most problematic section as a demonstration. OUTPUT FORMAT: - 'Maintainability score' (1-5) with a one-line justification. - 'Findings' (issue | why it hurts | improvement). - 'Refactored example' (before/after code). - 'Top 3 highest-leverage changes' (ordered). CONSTRAINTS: Preserve behavior exactly in any rewrite. Do not bikeshed formatting that a linter handles; focus on structural clarity. Justify each suggestion by the maintenance pain it removes, not personal preference.
How to use this prompt
- 1
Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.
- 2
Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.
- 3
Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.
Techniques in this prompt
Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.
Learn this techniqueRecommended models
Build on this prompt
Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.
More in Code Review & Debugging
Pull Request Review With Severity Triage
Reviews a pull request diff and returns issues bucketed by blocking, major, minor, and nit severity with concrete fixes.
Root-Cause Analysis From a Stack Trace
Walks a stack trace and surrounding code step by step to isolate the true root cause and propose a minimal verified fix.
Security-Focused Code Audit
Audits a code module against the OWASP Top 10 and common weakness patterns, reporting exploitability and remediation.
Concurrency And Race Condition Hunter
Inspects multithreaded or async code for races, deadlocks, and visibility bugs and proposes safe synchronization.