一键在 Manus 中运行任何 Skill

triage-scoreboard

星标47

分支3

更新时间2026年7月19日 03:45

Compute and render the living, ranked triage board of open work — mechanical + judgment dimensions into a composite rank, with evidence-readiness tags. Run on a schedule so the board is always current.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

nesquena

nesquena/steward-os

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

triage-scoreboard

When to load: generating or refreshing the triage scoreboard. Band A (read-only, deterministic where possible). Ideal as a scheduled job.

Steps

Pull live metadata for every open item (PRs/issues): CI status, mergeable/behind, size, age, author. Read repos from config.yaml.
Recompute mechanical dimensions fresh each run (disposable): CI, conflict state, behind-count, size bucket, contributor trust score (computed by contributor-trust from the trust ledger).
Merge in persisted judgment dimensions (scope_fit, criticality, risk, severity) from the prior board — these survive regeneration so human/agent assessments aren't lost.
Compute the composite = weighted sum of dimensions (weights from config; tune to match "what I'd pick up next"). Promote genuinely-breaking items to a severity spotlight at the top.
Tag evidence-readiness per item: which review streams have landed (automated review present? visual preview? deep-review dossier?). Compact ✓/· marker. Presence ≠ clean.
Render the living board sorted by composite + a curated "review these first" short-list. Persist the computed data as a machine-readable artifact for other jobs.
Commit following scheduled-job rules (idempotent, silent-on-no-op).

Pitfalls

Keep mechanical and judgment dims in separate storage — mechanical is re-derived and disposable; judgment is precious and persisted. Don't let a refresh wipe a human's assessment.
Evidence presence is not a verdict — ✓ means the evidence exists to review, not that it's clean. The authoritative gate still runs at merge.
Re-run cheaply — this should be incremental and idempotent; it's a read-only ranking, not an action.

Verification

Board re-renders with current data; judgment dims preserved across runs.
Composite ordering matches intuition for the top handful.
Evidence tags reflect actual review-stream presence.

同仓库更多 Skills

同仓库

issue-capture

nesquena/steward-os

Capture issue-shaped reports that have not reached the tracker yet. Divert suspected vulnerabilities, dedupe across every surface, and stage genuinely new actionable items in the pre-tracker queue. Never files or replies on the public tracker. Watcher role, Band A.

2026-07-2047

action-watchdog

nesquena/steward-os

Independently fact-check the autonomous actions the system took (issue closes, labels, capture marks, etc.) against live ground truth, and alarm on any mismatch. Run on a schedule. This is what makes Band-A public actions safe.

2026-07-2047

issue-triage

nesquena/steward-os

Triage tracker issues — initial reply under a confidence gate, label, milestone, sprint-candidate, and the dropped-ball "reporter waiting on us" surfacer. Use for ongoing issue-tracker hygiene.

2026-07-2047

pr-deep-review

nesquena/steward-os

Deep-review a routed PR and run the authoritative quality gate before merge. Reads the whole diff, reproduces, runs the layered gates fresh, bounces with a fix-spec or fixes mechanical blockers. Stages 3-4 of the PR lifecycle.

2026-07-1947

pr-triage

nesquena/steward-os

Screen and route an open pull request — fit/scope screen, marginal-benefit screen, and lane routing. Use at the front of the PR pipeline before any deep review. Stages 0-2 of the PR lifecycle.

2026-07-1947

contributor-trust

nesquena/steward-os

Aggregate the contributor trust ledger into a shrunk-and-decayed reliability score that weights review priority and gate intensity — never a reason to skip a gate. Band A, no LLM: classification happens upstream at close, this is arithmetic over an existing event log.

2026-07-1947

name	triage-scoreboard
description	Compute and render the living, ranked triage board of open work — mechanical + judgment dimensions into a composite rank, with evidence-readiness tags. Run on a schedule so the board is always current.

triage-scoreboard

When to load: generating or refreshing the triage scoreboard. Band A (read-only, deterministic where possible). Ideal as a scheduled job.

Steps

Pull live metadata for every open item (PRs/issues): CI status, mergeable/behind, size, age, author. Read repos from config.yaml.
Recompute mechanical dimensions fresh each run (disposable): CI, conflict state, behind-count, size bucket, contributor trust score (computed by contributor-trust from the trust ledger).
Merge in persisted judgment dimensions (scope_fit, criticality, risk, severity) from the prior board — these survive regeneration so human/agent assessments aren't lost.
Compute the composite = weighted sum of dimensions (weights from config; tune to match "what I'd pick up next"). Promote genuinely-breaking items to a severity spotlight at the top.
Tag evidence-readiness per item: which review streams have landed (automated review present? visual preview? deep-review dossier?). Compact ✓/· marker. Presence ≠ clean.
Render the living board sorted by composite + a curated "review these first" short-list. Persist the computed data as a machine-readable artifact for other jobs.
Commit following scheduled-job rules (idempotent, silent-on-no-op).

Pitfalls

Keep mechanical and judgment dims in separate storage — mechanical is re-derived and disposable; judgment is precious and persisted. Don't let a refresh wipe a human's assessment.
Evidence presence is not a verdict — ✓ means the evidence exists to review, not that it's clean. The authoritative gate still runs at merge.
Re-run cheaply — this should be incremental and idempotent; it's a read-only ranking, not an action.

Verification

Board re-renders with current data; judgment dims preserved across runs.
Composite ordering matches intuition for the top handful.
Evidence tags reflect actual review-stream presence.