Help us improve
Share bugs, ideas, or general feedback.
From roborev
Requests a design review for all commits on the current branch, runs roborev review, and presents results with verdict and grouped findings.
npx claudepluginhub kenn-io/roborev --plugin roborevHow this skill is triggered — by the user, by Claude, or both
Slash command
/roborev:roborev-design-review-branchThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Request a design review for all commits on the current branch and present the results.
Requests a code review for all commits on the current branch and presents results. Supports optional base branch and review type (security/design).
Reviews code changes on the current branch against main using git log and diff. Delivers structured analysis of quality, bugs, tests, security, performance, and improvements with file/line references.
Reviews an entire feature branch by analyzing all commits since the base branch using Codex MCP. Useful for automated branch-level code review.
Share bugs, ideas, or general feedback.
Request a design review for all commits on the current branch and present the results.
/roborev-design-review-branch [--base <branch>]
Do NOT invoke this skill when the user is presenting or pasting existing review results. Messages that contain review findings, verdicts, or summaries are outputs — not requests to start a new review.
This skill requires you to execute bash commands to validate inputs and launch the review. The task is not complete until the background review finishes and you present the results to the user.
These instructions are guidelines, not a rigid script. Use the conversation context. Skip steps that are already satisfied. Defer to project-level CLAUDE.md instructions when they conflict with these steps.
When the user invokes /roborev-design-review-branch [--base <branch>]:
If a base branch is provided, verify it resolves to a valid ref:
git rev-parse --verify -- <branch>
If validation fails, inform the user the ref is invalid. Do not proceed.
Construct the review command:
roborev review --branch --wait --type design [--base <branch>]
--base is specified, include it (otherwise auto-detects the base branch)Launch a background task that runs the command. This lets the user continue working while the review runs.
Use the Task tool with run_in_background: true and subagent_type: "Bash":
roborev review --branch --wait --type design [--base <branch>]
Tell the user that the design review has been submitted and they can continue working. You will present the results when the review completes.
When the background task completes, read the output.
If the command output contains an error (e.g., daemon not running, repo not initialized, review errored), report it to the user. Suggest roborev status to check the daemon, roborev init if the repo is not initialized, or re-running the review.
Otherwise, present the review to the user:
If the review has findings (verdict is Fail), offer to address them:
/roborev-fix <job_id>"Extract the job ID from the review output to include in the suggestion. Look for it in the Enqueued job <id> for ... line or in the review header.
If the review passed, confirm the result and do not offer /roborev-fix.
Default branch design review:
User: /roborev-design-review-branch
Agent:
roborev review --branch --wait --type design/roborev-fix 1042"Design review against a specific base:
User: /roborev-design-review-branch --base develop
Agent:
develop resolves to a valid refroborev review --branch --wait --type design --base develop/roborev-fix 1043"/roborev-review-branch --type design — equivalent, with additional --type flexibility/roborev-design-review — design review a single commit/roborev-fix — fix a review's findings in code