portfolio-watchlisted

Show the recurring, read-only portfolio summary for the Seshat BI repo -- every governed scope's covered-dimension findings (source drift, contract/metric drift, dashboard-intent divergence, readiness, approvals, review), open blockers, human-attention flag, and ONE prioritized next action, plus a baseline diff against the last run (new/resolved/unchanged). Use when someone asks "run portfolio watch", "what changed since last week", "show me the recurring summary", or "which scopes need a human, and what changed". READ-ONLY and invoke-and-present only: it AGGREGATES evidence that shipped surfaces already produce (it runs NO new check, re-derives NOTHING); it persists a LOCAL baseline snapshot under `.seshat/watch/` so the next run can diff; it introduces NO new gate/rule/approval mechanism and emits NO fabricated health/confidence/priority score (every line is a shipped categorical status, a shipped finding enum, or a measured magnitude traced to a committed source).
Kemetra/Seshat-BI · ★ 2 · Code & Development · score 68

Install: claude install-skill Kemetra/Seshat-BI

# portfolio-watch Portfolio Watch answers one recurring question: *since we last looked, what changed, what still needs a human, and what is the one next thing to do per scope?* It is the baseline-diffable, multi-dimension EXTENSION of the point-in-time `retail-control-room` roll-up (F012) -- same read-only, aggregate-never-re-derive posture, plus a persisted snapshot and the drift/semantic-drift/dashboard-intent-divergence dimensions the control room does not fold in. ## Scope wall (read first) - **Aggregates, never re-derives.** Every finding is sourced from a shipped surface's already-committed output (`drift.py`/`drift_semantics.py`, `metric_drift.py`, `semantic_audit.py`/`report_intent.py`, `readiness_projection.py`/`readiness_classify.py`, `approval_inbox.py`, `review_integration.py`/`review_pack_export.py`). It runs NO new check and calls NONE of those surfaces' own comparators itself -- it reads what they already recorded and cites the path. - **No new gate / rule / approval mechanism.** This is a Tier-5 read/summarize/derive companion (roadmap binding rule), not another governance engine. `seshat check`'s rule inventory and exit behavior are unchanged by this skill's existence. - **No score, ever.** Only the four readiness spine statuses, the shipped categorical finding enums (relayed verbatim), and measured magnitudes (counts/rates/deltas) traced to a committed source appear anywhere. A health/confidence/priority/quality number is never emitte