MoonshotAI / MoonshotAI/kimi-cli
[Feature Request]: Add /review slash command for code review workflow
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 11.4k
- Forks
- 1.3k
- Avg merge
- 9h 47m
- Merged PRs (30d)
- 2
Description
What feature would you like to see?
A /review slash command that reviews the current codebase, recent changes, or a specific file/diff — similar to the /review command in Claude Code and Codex.
Why?
Code review is a high-frequency developer workflow. Having a built-in /review command would allow users to quickly get AI feedback on:
- Uncommitted changes in the working directory
- A specific file or set of files
- The most recent commit or PR diff
This reduces friction compared to manually prompting the agent with "please review these changes."
Proposed behavior
/review # Review uncommitted changes (git diff)
/review <file> # Review a specific file
/review --commit # Review the most recent commit
/review --pr # Review the current PR diff (if applicable)
The agent should analyze the diff/code and provide structured feedback covering:
- Correctness / potential bugs
- Code style and readability
- Performance concerns
- Security issues
- Suggestions for improvement
Prior art
- Claude Code:
/reviewanalyzes working tree changes and provides inline feedback. - Codex:
/reviewsupports reviewing diffs and specific files.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
The issue does not name files or existing command entry points. Start by locating slash-command dispatch and the code that reads git diffs or pull-request context; compare those paths with the proposed /review modes. Done means the command handles the listed targets and produces structured feedback for correctness, style, performance, security, and improvements.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- git, python
- Domain
- cli, developer-experience
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100