Menü
Read the Monitor board health data, explain why each repo needs attention, and propose the next concrete action per repo. Use to turn monitoring signals into action, or as the input step of the self-evolution loop.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Deep-analyze a GitHub issue into a client-engagement estimate — classify scope, refine the plan (approach/deliverables/acceptance), and record an agent-refined estimate in _data/engagements.yml. Use when asked to "estimate", "quote", "scope", or "price" an issue or a repo's backlog, or to review/refine a draft the estimator produced.
Read the committed Actions analytics (_data/actions_usage.yml), explain the worst workflows (cost, effectiveness, waste), and drive the next action — dispatch the actions-review issue-filer or fix a workflow directly. Use when asked "where are Actions minutes going" or after the daily actions-usage refresh.
Run the dash drift gate and explain every failure in plain language with the exact fix. Use when CI drift-check fails or before opening a PR.
Run a focused improvement pass on a single project (code quality, docs, tests, error handling) using the matching .github/agents persona. Use when a repo needs maintenance attention or as the action step of the evolution loop.
Scaffold a new project and register it in the dash. Use when starting a new repo/app that should appear in the portfolio.
Adopt (or remove) a project directory that exists on disk under projects/ but is in neither .gitmodules nor the registry. Use when the drift gate flags a stray/unregistered project dir.
| name | triage-attention |
| description | Read the Monitor board health data, explain why each repo needs attention, and propose the next concrete action per repo. Use to turn monitoring signals into action, or as the input step of the self-evolution loop. |
_data/fleet_triage.yml — the committed daily open-state snapshot (every open issue, PR with CI status, failing workflow, per-repo attention score, prioritized inbox). Refreshed daily by daily-repo-analysis.yml; regenerate on demand with tools/dash triage. Prefer this for issue/PR/CI triage — it has the actual items.tools/dash-gen health (writes ephemeral _data/project_health.yml) — adds signals triage doesn't carry: stars, commit activity, security alerts, releases.by_repo is pre-sorted by attention score (or use health's attention_rank, 🔴 first, then 🟠). Start from fleet_triage's inbox — it is already the prioritized queue.attention.reasons and propose ONE next action:
status: archived.github-issue-creator skill at projects/skills/.github/skills/github-issue-creator/).sync-project-docs and refresh-portfolio in the self-evolution loop (unified-evolution.yml — dispatch-only, no schedule; trigger via tools/dash evolve or gh workflow run unified-evolution.yml).