Automatically reviews and fixes code in a loop until all issues are resolved.
Install
mkdir -p .claude/skills/roborev-refine && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11798" && unzip -o skill.zip -d .claude/skills/roborev-refine && rm skill.zipInstalls to .claude/skills/roborev-refine
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Iterative review-fix loop for the current branch — reviews via daemon, fixes inline, re-reviews until passing or max iterations reachedKey capabilities
- →Perform iterative review-fix loops on the current branch
- →Re-review code after each fix to verify resolution
- →Sort findings by severity (HIGH, MEDIUM, LOW)
- →Group edits by file to minimize context switches
- →Run project's test suite to verify fixes
- →Commit changes and record comments on reviews
How it works
The skill initiates an iterative loop that reviews the current branch, fixes identified findings, commits the changes, and then re-reviews. This cycle continues until all reviews pass or a maximum iteration limit is reached.
Inputs & outputs
When to use roborev-refine
- →Iteratively fix code review findings
- →Refine branch changes until validation passes
- →Automate the fix-and-retest development cycle
- →Verify code quality after multiple fix passes
About roborev-refine
Performs an automated loop of reviewing, fixing, and re-reviewing code on the current branch. It ensures that identified issues are resolved and verified through multiple iterations.
Iterative review-fix loop for the current branch — reviews via daemon, fixes inline, re-reviews until passing or max iterations reached
When not to use it
- →When the user is presenting or pasting existing review results
- →When the user only wants a single review without fixing
- →When the task is not explicitly invoked with /roborev-refine
Limitations
- →Requires explicit invocation with /roborev-refine
- →Does not expose `roborev refine --all-branches` or `roborev refine --list`
- →Refuses to run on the default branch without a `--since` commit
How it compares
This skill automates a continuous review-fix-re-review cycle, ensuring that code changes are validated iteratively, unlike a single-pass fix or review.
Compared to similar skills
roborev-refine side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| roborev-refine (this skill) | 0 | 2mo | Review | Advanced |
| moai-workflow-loop | 1 | 2mo | No flags | Advanced |
| resolve-conflicts | 81 | 8mo | Review | Intermediate |
| python-testing-patterns | 77 | 2mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
moai-workflow-loop
modu-ai
Ralph Engine - Automated feedback loop with LSP diagnostics and AST-grep integration for continuous code quality improvement. Use when implementing error-driven development, automated fixing, or continuous quality validation workflows.
resolve-conflicts
antinomyhq
Use this skill immediately when the user mentions merge conflicts that need to be resolved. Do not attempt to resolve conflicts directly - invoke this skill first. This skill specializes in providing a structured framework for merging imports, tests, lock files (regeneration), configuration files, and handling deleted-but-modified files with backup and analysis.
python-testing-patterns
wshobson
Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.
error-handling-patterns
wshobson
Master error handling patterns across languages including exceptions, Result types, error propagation, and graceful degradation to build resilient applications. Use when implementing error handling, designing APIs, or improving application reliability.
claude-automation-recommender
anthropics
Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.
codex-claude-loop
bear2u
Orchestrates a dual-AI engineering loop where Claude Code plans and implements, while Codex validates and reviews, with continuous feedback for optimal code quality