internal/skills/codex/roborev-design-review/SKILL.md
Request a design review for a commit and present the results
npx skillsauth add roborev-dev/roborev roborev-design-reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Request a design review for a commit and present the results.
$roborev-design-review [commit] [--panel <name>|none]
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 the commit and run the review. The task is not complete until the 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 [commit] [--panel <name>|none]:
If a commit ref is provided, verify it resolves to a valid commit:
git rev-parse --verify -- <commit>^{commit}
If validation fails, inform the user the ref is invalid. Do not proceed.
Construct and execute the review command:
roborev review [commit] --wait --type design [--panel <name>|none]
--panel <name> is specified, include it (fans out to the named config panel); --panel none forces a single-agent reviewThe --wait flag blocks until the review completes.
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 you pass --panel <name>, or a default_panel is configured for explicit
reviews, the review fans out to a panel of reviewers. In that case the
Enqueued job <id> is the synthesis (parent) job that aggregates them, and
its verdict and findings are the synthesized result across the whole panel.
Present that synthesized verdict/findings, and offer fix on that parent id —
never an individual reviewer. roborev show prints a one-line reviewers summary
(e.g. 3 reviewers: bug P, security F) for a synthesis job. --panel none
forces a single-agent review, and automatic post-commit hook reviews stay
single-agent regardless of default_panel.
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. For a panel review this id is the synthesis parent.
If the review passed, confirm the result and do not offer $roborev-fix.
Default design review of HEAD:
User: $roborev-design-review
Agent:
roborev review --wait --type design$roborev-fix 1042"Design review of a specific commit:
User: $roborev-design-review abc123
Agent:
git rev-parse --verify -- abc123^{commit}roborev review abc123 --wait --type design$roborev-fix 1043"$roborev-review --type design — equivalent, with additional --type flexibility$roborev-design-review-branch — design review all commits on the current branch$roborev-fix — fix a review's findings in codedevelopment
Request a code review for a commit and present the results
development
Request a code review for all commits on the current branch and present the results
development
Add a comment to a roborev code review and close it
tools
Iterative review-fix loop for the current branch — reviews via daemon, fixes inline, re-reviews until passing or max iterations reached