For automated GitHub pull-request reviews, configure the repository’s .gemini/config.yaml and add a project-specific .gemini/styleguide.md. For an interactive IDE review, use Gemini Code Assist’s Rules; Gemini CLI has separate settings. These are distinct configuration surfaces, not one shared switch. Check product availability first: Google says Gemini Code Assist IDE Extensions and Gemini CLI stopped serving individual, Google AI Pro, and Google AI Ultra tiers on June 18, 2026, directing affected users to Antigravity and Antigravity CLI.
Choose where you want Gemini to review code
Start with the workflow, because each Gemini surface has its own configuration:
As an Amazon Associate I earn from qualifying purchases.
- GitHub pull requests: repository-root
.gemini/config.yamlcontrols review behavior, while.gemini/styleguide.mdsupplies repository conventions. See Google’s GitHub customization documentation. - IDE prompts: persistent Rules in Gemini Code Assist settings guide interactive requests. Google describes Rules as preferences considered with every prompt or request; they are separate from the GitHub style guide. See Chat with Gemini Code Assist.
- Gemini CLI: user settings live in
~/.gemini/settings.json; workspace settings live in<project>/.gemini/settings.jsonand take precedence over user settings. These are CLI settings, not the GitHub review schema. See the Gemini CLI settings documentation.
For individual, Google AI Pro, and Google AI Ultra accounts, Google documents that Gemini Code Assist IDE Extensions and Gemini CLI stopped serving those tiers on June 18, 2026, with affected users directed to Antigravity and Antigravity CLI. Enterprise and GitHub availability may have different eligibility; the announcement does not establish their terms. Check Google’s Gemini Code Assist code features overview and your account’s current product access before following IDE or CLI setup steps.
Do these 3 things before closing this tab:
1Repair Windows errors before they cause bigger problems2Scan for outdated or missing drivers - takes under a minute3Clear out junk files and repair common Windows errorsConfigure GitHub pull-request reviews
Set repository review controls
At the repository root, create a .gemini directory. Put automated review controls in .gemini/config.yaml. This example follows the documented configuration shape; confirm the live schema before adopting it, since defaults and supported options can change:
#1 Best Overall
code_review:
disable: false
comment_severity_threshold: MEDIUM
max_review_comments: -1
pull_request_opened:
code_review: true
summary: false
help: false
include_drafts: trueThe documented severity choices are LOW, MEDIUM, HIGH, and CRITICAL. Google documents MEDIUM as the default threshold and -1 as the default maximum, meaning unlimited comments. In the example, review runs when a pull request opens, summaries and help are off, and drafts are included. Thresholds reflect Gemini’s assessment, not TypeScript compiler diagnostics. The schema and controls are documented in Google’s GitHub customization guide and config.yaml reference.
Tell it what counts as a useful TypeScript finding
Create .gemini/styleguide.md in the same directory. Use it to describe review priorities and conventions rather than restating generic formatting preferences. The following are suggested project instructions, not built-in Google settings:
Rank #2
- TypeScript implements a superset of syntax for strictly typed development, facilitating deep static analysis and enhanced development environment integration. The compiler translates source into standard script formats, ensuring parity across any runtime.
- TypeScript is ideal for front-end developers, full-stack engineers, and software architects who build large-scale web applications. It serves those looking to improve code excellence, reduce bugs through static checking, and maintain complex projects more.
- Lightweight, Classic fit, Double-needle sleeve and bottom hem
- Prioritize correctness, security, runtime failure, and regression risks in the changed code.
- Flag
anyusage or type assertions only when they plausibly conceal a bug or weaken a relevant boundary. - Inspect changed asynchronous paths for unhandled promise rejection, incorrect ordering, or missing resource cleanup when applicable.
- Check whether tests cover the behavior changed by the pull request.
- Skip comments that merely restate formatting or established project conventions, and make each finding actionable.
Keep these instructions aligned with the repository’s actual standards. Review Gemini’s comments against the code and test suite; Google’s configuration material does not promise complete detection or establish a measured TypeScript-review accuracy level.
Free tools Windows power users keep installed
One-click scans. No signup required.
Reduce noise or control when reviews run
Choose the threshold and comment cap together: a higher threshold filters lower-severity findings, while a cap limits how many comments appear. Draft inclusion and optional summary/help behavior apply to the pull-request-opened event configuration.
| Goal | Configuration choice | Trade-off |
|---|---|---|
| Surface more lower-impact issues | Lower comment_severity_threshold, such as LOW |
More comments can mean more noise. |
| Reserve comments for consequential findings | Raise the threshold, for example to HIGH |
Lower-severity issues will not be posted. |
| Limit review-comment volume | Set max_review_comments to a finite cap |
Findings beyond the cap may be omitted. |
| Exclude draft pull requests from this event | Set include_drafts: false |
Drafts receive no review through that event configuration. |
| Orient readers when a pull request opens | Enable summary or help selectively |
These add pull-request comments beyond issue findings. |
Google documents the threshold options and event settings in its config.yaml reference. The configuration determines what Gemini is asked to report; it does not establish that a finding is correct.
Set IDE Rules for interactive reviews
In Gemini Code Assist settings, add persistent Rules for review requests. Google describes Rules as preferences applied with every prompt or request, including coding style, output format, technology stack, and language. A focused rule can ask for TypeScript feedback limited to concrete correctness risks, with severity, file and line location, rationale, and a proposed fix. Keep it distinct from .gemini/styleguide.md, which is for GitHub repository reviews.
Because Google documents a June 18, 2026 service change for individual, Google AI Pro, and Google AI Ultra users, confirm that the relevant IDE extension is currently available to your account before relying on this workflow.
The Tool Desk
Outbyte PC Repair FREEClear out junk files and repair common Windows errorsFree Scan →Outbyte Driver Updater FREEFix the driver behind crashes, sound loss and screen glitchesFind Drivers →Use a focused prompt for an interactive TypeScript diff
For a manual review request, provide the diff or relevant context and give a direct task. Google’s general prompting guidance recommends direct instructions and, for long context, putting context before the specific request. This template is an editorial example, not a Google-prescribed prompt or a proven accuracy guarantee:
Best Value
Review this TypeScript diff for actionable correctness, security, runtime, and regression issues. Check changed async/error paths and whether tests cover changed behavior. Report only findings tied to specific lines, ordered by severity; for each, explain the impact and suggest a minimal fix. If you find no actionable issue, say so. Do not rewrite the code.
Google’s prompt design strategies cover general instruction techniques. Its guidance does not establish a measured review-accuracy improvement for this template.
What the available guidance does—and does not—establish
Google’s sources explain configuration options and prompting practices, but they do not provide a controlled benchmark or accuracy percentage for Gemini TypeScript code reviews. Treat automated comments as review suggestions to verify, not as a substitute for tests or human judgment. A separate Google example shows how prompt text for a TypeScript review command can be adapted, but it does not establish review effectiveness: Build a personal AI coding assistant with Gemma.
PC Slower Than It Used to Be?
A free scan shows the junk files, broken settings and background clutter dragging Windows down - then fixes them in one click.Free scan · Windows 10 & 11Outdated Drivers Are Slowing You Down
One free scan finds every outdated or missing driver and matches the right update for your exact hardware.Free scan · exact hardware matchQuick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
