跳到正文
cccskills
免费在 GitHub 公开

review-triage-queue

Review OpenShell issues, pull requests, and failed main-branch checks, then build a local Markdown report with linked evidence and ranked recommendations. Saved progress helps resume an unfinished triage pass without changing GitHub.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Create a read-only, local triage queue report from OpenShell GitHub intake. Use to review the triage queue, scan incoming issues and community PRs, check main-branch CI failures, or resume a triage pass.

集成工具GitHub
查看安装方法

适用场景

  • Reviewing incoming issues and community pull requests
  • Checking failed CI runs on main
  • Prioritizing unresolved issues with supporting evidence
  • Resuming an unfinished triage pass

包含的文件(2)

  • SKILL.md5.7 KB
  • references/report-template.md1.6 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Review Triage Queue

Create a decision-focused, local Markdown report. Do not write to GitHub.

Local state

Use these ignored local paths under .agents/triage-duty/:

  • Checkpoint: state.local.yml
  • Reports: reports/<UTC timestamp>.md
  • Action records: actions/<UTC timestamp>.md
  • Inbox: inbox.md

Record first-run coverage. Update cursors only after a complete report; partial reads must not skip unread items. Search with overlap and deduplicate source items.

Keep the checkpoint minimal: repository, last successful scan, source and backlog cursors, explicit dispositions, and next triage issue. Action records are authoritative; reconcile the checkpoint from them before proceeding. Reports are immutable. Never store credentials, personal data, private reasons, or vulnerability details; never stage duty files.

Read unchecked inbox entries at the start of every review. Treat them as local follow-up prompts, not as independent evidence or authorization for an external action. When an entry materially informs the review, include it in the report's Local inbox follow-up section. After the dated report is written, mark that entry complete in the inbox with the report filename. Leave entries unchecked when they were not yet actionable or were not considered.

Gather intake

Follow Label Discovery, retrieving all pages of current label definitions. Identify the triage queue by its description. Read all pages of each source:

  • All open GitHub issues in the triage queue, ordered by most recently updated.
  • Newly opened community issues with no state:* label; exclude maintainer/core-contributor issues and already-routed work from label recommendations. This includes stale lifecycle labels.
  • Older open community issues meeting the same eligibility rule: measure first; audit all when there are at most 20, otherwise inspect the five oldest remaining candidates per run. Use a separate (created_at, number) backlog cursor, advanced only after inspection and reporting; wrap at the end. Advancing it must not drop pending recommendations. Age sets ordering only and never justifies closure.
  • Open non-draft Dependabot pull requests. Surface these explicitly so they do not age out or go stale while waiting for maintainer attention.
  • Newly opened non-draft community pull requests.
  • Failed CI runs on main.
  • Published repository documentation for applicable public answers.

Do not scan GitHub Discussions or a dedicated security-reporting source in v1. Route suspected vulnerabilities through SECURITY.md.

Treat an unlabelled issue as already routed when it has roadmap placement, a milestone, a Project item, or an explicit maintainer comment that assigns, schedules, or otherwise intentionally removes it from triage. Report that signal as context; never recommend adding the triage-queue label to it. If authorship or routing is uncertain, report the uncertainty instead of recommending a label.

Analyze and rank

Use repository-scoped object IDs: I<number> for issues, P<number> for PRs, and C<run_id> for GitHub Actions runs. Link each ID to its canonical source; attempts share the run ID. PRs are informational in v1.

Detect related signals across sources. Preserve each source as linked provenance. Group similar evidence into one recommendation; do not count a global fixed number of occurrences as the only evidence of repetition.

Recommend work for repeated questions, defects, documentation/support gaps, requested product changes, or likely duplicates. Treat documentation and support improvements as bug-fix or feature work when they address a demonstrated user need.

Classify recommendations as bug, feature, documentation/support improvement, duplicate, intake-gap routing, release blocker, or security finding. The agent may infer a release blocker only with concrete evidence, source links, and confidence. Keep critical for security findings and release blockers; use high, normal, or low for all other items. Set confidence to high, medium, or low, and explain uncertainty unless it is high.

Give new and carried pending/deferred recommendations separate five-item budgets. Preserve carried priorities and recheck live sources outside scan windows. Keep excess findings in overflow; only security findings and release blockers may exceed either cap. Never mark recommendations processed merely because they were reviewed; carry pending/deferred items until applied or rejected through apply-triage-action.

Resume an in-progress triage pass

When the on-duty engineer asks for the “next issue” without asking for a new queue review, resume from the latest local report's Triage queue order. Select the first item that has not been explicitly dispositioned in local duty state. Do not query live GitHub data to silently reorder an in-progress pass: newly opened or newly updated issues belong in the next queue review. Use triage-issue for assessment.

An engineer can explicitly request a refresh or the newest live issue; either request supersedes the continuation order. If the report has no remaining listed candidate, say so and offer a fresh queue review rather than choosing an item from an older overflow list.

Write the report

Create a dated immutable report using the report template. Use links and short paraphrases only. Record its first listed triage issue as next_triage_issue in the checkpoint.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Process one recommendation selected by ID from a local issue or CI triage report. Apply, reject, or defer it, record the outcome, and obtain separate confirmation before each change made on GitHub.

中文简介正在准备中。当前显示英语简介。

  • Apply one recommendation selected by its item ID
  • Reject a recommendation and record the reason
  • Defer a decision for the next queue review
NVIDIA/OpenShell1.7万2026年10月19日 更新

Turn a GitHub issue into a scoped implementation plan and, when authorized, code changes, tests, documentation, and a pull request that closes it. Check existing ownership and feedback to keep work aligned with acceptance criteria.

中文简介正在准备中。当前显示英语简介。

  • Creating an implementation plan from a GitHub issue
  • Implementing an authorized issue with focused tests
  • Updating documentation alongside behavior changes
NVIDIA/OpenShell1.7万2026年10月19日 更新

Maintain and validate OpenShell builds for Windows on x64 and ARM64 using MSVC, Microsoft's C++ toolchain. Check compilation, build executables, run tests on native hosts, and report artifacts and unsupported driver behavior.

中文简介正在准备中。当前显示英语简介。

  • Investigating Windows compilation failures
  • Building x64 and ARM64 release executables
  • Checking errors for unsupported drivers
NVIDIA/OpenShell1.7万2026年10月19日 更新

Create GitHub issues for OpenShell bugs, feature requests, and tasks using the gh command-line tool. Organize firsthand use cases, impact, and completion criteria into the project's templates, then return the created issue link.

中文简介正在准备中。当前显示英语简介。

  • Report an OpenShell bug you directly encountered
  • Request a feature for a specific OpenShell use case
  • Register an internal task with completion criteria
NVIDIA/OpenShell1.7万2026年10月19日 更新

Create GitHub pull requests with the gh command-line tool. Check linked issues, contributor permissions, branch conventions, and relevant tests, then prepare a title and description that follow the project's contribution rules.

中文简介正在准备中。当前显示英语简介。

  • Submit code changes for review
  • Open a draft pull request
  • Link a pull request to its issue
NVIDIA/OpenShell1.7万2026年10月19日 更新

Turn a design request into an OpenShell RFC, a proposal for review and discussion. The skill follows the project template, assigns an available number, and organizes motivation, alternatives, and open questions into a draft.

中文简介正在准备中。当前显示英语简介。

  • Drafting an architecture proposal
  • Organizing an API change proposal
  • Documenting a process change
NVIDIA/OpenShell1.7万2026年10月19日 更新

查看 NVIDIA 的全部技能

报告此技能的问题