po-resumelisted

Resume a PO session from a /po-handover file. Read the handover as a map, rebuild state from live measurement, re-arm monitors, and load the standard PO toolkit (dev-flow / issue-lane / herdr-event-watch plus your fleet's ledger and messaging conventions) into working awareness before doing any PO work. Triggers - "po-resume", "resume the PO session", "take over as PO". Argument - path to the handover file.
reoring/sds · ★ 2 · AI & Automation · score 75

Install: claude install-skill reoring/sds

# po-resume — PO session rotation (receiving side) **English** | [日本語](SKILL.ja.md) **Principle: the handover is a map, not a memory.** Inherit pointers and the in-flight list — never the previous session's beliefs. Re-measure everything live, in this order. ## Procedure (in order) ### 1. Read the handover The path given as argument (default: `<po-dir>/handover/<space>.md`). Take: ① in-flight items (gates / expected verdicts / promises), ② the monitor re-arm list, ③ the inbox baseline, ④ canonical pointers. ### 2. Read the canon (via the pointers) Operations doc → ledgers (model ledger, decision ledger) → flow canon (dev-flow doc, design principles). For large files, read the needed sections, not the whole file. ### 3. Load the standard toolkit into working awareness (mandatory — do not skip) A fresh session may *know* the skills exist without having them loaded into its *decisions*. Confirm each explicitly and state "toolkit confirmed" in the resume report: | Skill | Where it serves PO work | |---|---| | **dev-flow** | Stage management and gate checks — especially stage-5 hollow-green defenses (zero test diffs from the implementer / held-out test / real-boundary green) | | **issue-lane** | Lane assignment, teardown, audits. 1 issue = 1 lane, two-layer labels (tab × pane), lane dies with its issue, session rotation for degraded lanes (free refresh before paid boost) | | **herdr-event-watch** | Re-arming watchers (step 5) and event-driven supervision. INBOX is primar