Menu
DART Review PR: review a PR or address review feedback
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
DART Analyze: analyze repository evidence without editing
DART Architecture: the DART 7 multi-physics, multi-solver, multi-backend simulation pipeline and where each abstraction is owned
DART Audit Agent Compliance: audit and fix gaps when agents miss or cannot discover documented rules
DART Backport PR: backport a merged main PR to a release branch
DART Benchmark Packet: author or refresh a benchmark evidence packet for an owning plan
DART Branch Cleanup: analyze or clean stale repository branches
| name | dart-review-pr |
| description | DART Review PR: review a PR or address review feedback |
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.
/dart-review-pr <arguments>$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.
Review or respond to PR: $ARGUMENTS
@AGENTS.md @docs/onboarding/code-style.md @docs/onboarding/ai-tools.md (for AI-generated review handling) @docs/ai/verification.md
Pick the sub-workflow from mode= in $ARGUMENTS, defaulting to 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.
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).
pixi run lint before any commit.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.gh pr comment $1 --body "@codex review".github-code-quality[bot] findings;
do not re-trigger Codex solely for non-Codex bot findings unless Codex
comments were also addressed.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 (default pixi run test-all,
plus pixi run -e cuda test-all on Linux hosts with a visible NVIDIA CUDA
runtime); merge still waits for required hosted checks.