dart-review-pr
GitHub用于在Codex中执行DART项目的PR审查或反馈处理工作流。支持默认审查模式，检查代码风格、测试及3D行为证据；也支持地址反馈模式，执行本地修复、合并分支并静默推送，全程需人工审批以确保安全合规。
Trigger Scenarios
Install
npx skills add dartsim/dart --skill dart-review-pr -g -y
SKILL.md
Frontmatter
{
"name": "dart-review-pr",
"description": "DART Review PR: review a PR or address review feedback"
}
dart-review-pr
Use this skill in Codex to run the DART dart-review-pr workflow. The editable
workflow source lives in .claude/commands/; this file is its generated adapter
in the shared .agents/skills/ catalog.
Invocation
- Claude Code/OpenCode:
/dart-review-pr <arguments> - Codex:
$dart-review-pr <arguments>
Treat the text after the skill name as $ARGUMENTS. When the workflow
references $1, $2, etc., map those to the positional values supplied by the
user.
Command Body
Review or respond to PR: $ARGUMENTS
Required Reading
@AGENTS.md @docs/onboarding/code-style.md @docs/onboarding/ai-tools.md (for AI-generated review handling) @docs/ai/verification.md
Workflow
Pick the sub-workflow from mode= in $ARGUMENTS, defaulting to review.
Review
gh pr view $1 && gh pr diff $1
Check code style, tests, docs, and focused commits. When a claim depends on 3D
structure or behavior, require the dart-verify-sim text oracle and
claim-relevant assessed visual/debug-layer evidence (or a justified
replacement), and inspect both rather than accepting a screenshot alone.
Record findings as read-only output; do not push, comment, resolve threads, or re-trigger review
without explicit maintainer/user approval for that external mutation.
Address Feedback
gh pr view $1 --comments
Apply minimal fixes locally and verify. For published PRs, prefer a new follow-up commit so reviewers can inspect each round; amend or force-push only after explicit maintainer/user approval and only when the user requests it or a clear reason exists (removing sensitive content, repairing branch history).
- Make the local fix silently (no reply), then run the relevant local gates,
including
pixi run lintbefore any commit. - Merge the latest base branch into the PR branch before any push, and follow
the base-merge, automated-review, and bot no-reply rules in
docs/onboarding/ai-tools.md. If the push is rejected because the remote head moved, fetch and compare it before retrying and validate an equivalent remote fix instead of pushing a duplicate. - Ask for explicit maintainer/user approval before any push, PR comment, thread
resolution, or review re-trigger. After approval, push silently, resolve only
reviewed and addressed thread IDs via GraphQL, and — when the approved push
addressed Codex comments — re-trigger once with
gh pr comment $1 --body "@codex review". - Apply the same no-inline-reply loop to
github-code-quality[bot]findings; do not re-trigger Codex solely for non-Codex bot findings unless Codex comments were also addressed. - Monitor CI (
gh pr checks $1) and repeat until no actionable comments remain. For draft PRs, mark ready after explicit approval once Codex is clean and local validation passes on the current head (defaultpixi run test-all, pluspixi run -e cuda test-allon Linux hosts with a visible NVIDIA CUDA runtime); merge still waits for required hosted checks.
Output
- PR number and whether the pass was a review or a feedback round
- Findings or fixes applied, with file/line references
- Which actions were local-only and which external mutations were explicitly approved
- Codex/CI state and any remaining blocker
Version History
- b9fbefc Current 2026-07-19 11:30
