LLM Prompts I Run to Continuously Improve My Codebase
Source: Dev.to
Instead of asking LLMs to generate large chunks of code, I use them as codebase janitors: small, focused tasks that run often and compound over time.
Below are copy‑pasteable prompts I regularly use.
Prompts
1. Remove Dead Code
Find unused files, functions, exports, imports, and variables.
Explain why each is safe to remove and note any risk.2. Improve Naming
Rename variables, functions, and classes to better reflect intent.
Optimize for clarity and readability, not brevity.3. Reduce Cyclomatic Complexity
Identify overly complex functions and simplify logic.
Prefer early returns, smaller functions, and clearer control flow.4. Close Coverage Gaps
Scan test coverage output.
Find uncovered lines and write focused unit tests that validate behavior.5. Document the Why
Add documentation explaining *why* this code exists and what tradeoffs were made.
Do not describe what the code does line‑by‑line.6. Identify Responsibility Leaks
Find functions or components doing more than one job.
Suggest how to split responsibilities cleanly.7. Improve Error Handling
Review error handling paths.
Ensure errors are meaningful, actionable, and consistently handled.8. Normalize Patterns
Identify inconsistent patterns (naming, structure, async handling).
Recommend a single, consistent approach.9. Flag Hidden Coupling
Detect tight coupling between modules or layers.
Suggest abstractions or boundaries to reduce blast radius.10. Improve Readability Without Refactors
Improve formatting, ordering, and small structure changes only.
No architectural rewrites.Why This Works
These prompts are:
- Small
- Repeatable
- Low risk
- High leverage
This turns LLMs into continuous improvement agents, not code generators.
A Note on Code Review
When generating changes like this, commit frequently and keep each change small. This makes reviews easier, limits blast radius, and ensures you can always roll back to a known‑good state if something goes wrong.
Agents with GitHub
GitHub is moving in this exact direction—surfacing agent‑based workflows directly from their homepage and integrating them across issues, PRs, and code review.
Code Acceleration
The pace of development is accelerating. To keep up, we need to reduce friction wherever possible. As the volume of code we write and review skyrockets, readability becomes non‑negotiable—and these prompts help reinforce it.