homerail-pr-review
GitHub执行 HomeRail 只读 PR 审查工作流,调用 Qwen、Kimi 和 GLM 进行独立代码审计并生成证据报告。适用于用户请求 GitHub PR 审查或需要基于证据的审计报告场景。
Trigger Scenarios
Install
npx skills add xiaotianfotos/homerail --skill homerail-pr-review -g -y
SKILL.md
Frontmatter
{
"name": "homerail-pr-review",
"description": "Run HomeRail's built-in read-only pull request review DAG. Use when the user\nasks to review a GitHub PR, requests an evidence-backed PR audit, or wants a\nreusable independent Qwen, Kimi, and GLM review with retained findings."
}
HomeRail PR Review
Use the concrete pr-review orchestration. Do not generate a replacement DAG
and do not substitute a single-agent review.
Manager Agent Path
When the user says 审查 PR #25, review PR 25, or equivalent:
- Resolve the repository from the current project or ask only when no repository is available.
- Call
run_pr_reviewwith onlyrepoinowner/nameform and integerpr. This tool resolves immutable.base.shaand.head.shaplus trusted base and head clone URLs in code. Never copy, infer, reverse, or manually substitute those fields. Do not usegh,curl,instantiate_dag_pattern, or genericcreate_and_runwhen this tool exists. - Return the real run id immediately and use
get_run_statusfor progress. - On completion, report the final published handoff and artifact paths. Never claim findings that are not present in the DAG evidence.
The workflow is read-only. It must never create a commit, approve a GitHub PR, submit a GitHub review, or merge anything. Its internal Quorum is evidence validation, not GitHub approval.
CLI Path
hr dag run-template pr-review \
--input '{"repo":"xiaotianfotos/homerail","pr":25}'
The CLI resolves trusted GitHub metadata, preserves explicitly pinned SHAs,
validates the final input contract, syncs the tracked Asset, and starts the run.
Clone URLs always come from GitHub metadata, never logical input. Add --wait
for CI or unattended operation, then retrieve fixed outputs with:
hr dag artifacts <run-id>
hr dag artifact <run-id> pr-review.json --output pr-review.json
hr dag artifact <run-id> pr-review.md --output pr-review.md
Evidence Contract
A useful run contains:
- three complete reviewer handoffs from Qwen, Kimi, and GLM;
- a deduplicated report that preserves every complete reviewer finding;
- three independent approve/request-changes/abstain votes;
- a deterministic gate requiring two approvals and zero retained findings;
- declared
pr-review.jsonandpr-review.mdartifacts; - Manager audit and metrics records for the run.
Treat a cancelled run with a published report as inconclusive, not as a clean
review. Infrastructure, contract, or artifact failures are errors and must not
be rendered as zero findings. Do not reconstruct a report by scraping raw
handoffs; consume only the Manager-validated declared artifacts.
Version History
- 7f1ebb2 Current 2026-08-12 20:53


