agentleFS
NVIDIAKnown publisherNVIDIA/OpenShell/.agents/skills/review-triage-queue/SKILL.md

review-triage-queue

Skill17k starsChanged 18 days agoApache-2.0View on GitHub

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.

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a decision-focused, local Markdown report.

    line 10
  2. Very specific:

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

    line 14
  3. Distinctive:

    Follow Label Discovery, retrieving all pages of current label definitions.

    line 29
  4. Distinctive:

    All open GitHub issues in the triage queue, ordered by most recently updated.

    line 31
  5. Distinctive:

    Do not scan GitHub Discussions or a dedicated security-reporting source in v1.

    line 39
  6. Very specific:

    Use repository-scoped object IDs: I<number> for issues, P<number> for PRs, and C<run_id> for GitHub Actions runs.

    line 45
  7. Very specific:

    Create a dated immutable report using the report template.

    line 63

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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.

Download now (ZIP)

Trending

Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data

Week of Aug 30: 0 new projectsWeek of Sep 6: 0 new projectsWeek of Sep 13: 0 new projectsWeek of Sep 20: 0 new projectsWeek of Sep 27: 0 new projectsWeek of Oct 4: 0 new projectsWeek of Oct 11: 0 new projectsWeek of Oct 18: 0 new projects
Aug 2026Sep 2026Oct 2026
New projects taking a version of this file each week, over the 8 weeks our latest run read: only 0 in all, so this is a hint, not a trend.

Who's talking about NVIDIA/OpenShell

The biggest 5 of 77 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 77

Talked about on Bluesky, YouTube, the web and Hacker News (77 times).

On Bluesky · 41

36 more on Bluesky

On YouTube · 25

20 more on YouTube

On the web · 6

1 more on the web

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.