القائمة
Review staged memory candidates from MEMORY_CANDIDATES.md. Surface each with promote/skip/supersede options. Does not auto-promote.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | digest |
| agent | none |
| description | Review staged memory candidates from MEMORY_CANDIDATES.md. Surface each with promote/skip/supersede options. Does not auto-promote. |
| allowed-tools | Read, Edit, Grep |
| user-invocable | true |
| triggers | ["digest","digest candidates","review memory candidates","process candidates","promote candidates","clean memory backlog","memory candidates"] |
Background curation tier. Reviews staged candidates and asks the principal to:
status: skipped, leave in ledger/close (auto, surface candidates)/body-check reports memory_candidate_backlog > 10/digest as part of her sweep)memory/MEMORY_CANDIDATES.md. Filter status: staged.type (decision / preference / doctrine / project / person / skill).status and digested_on fields.NEVER auto-promote. Only act on principal's word.
The capsule verb, invoked explicitly — reconcile from the live memory, write a resume-ready capsule, then stop. Mid-session checkpoint or completion capsule; a rolling best-effort version of the same write also runs automatically on every Stop event via daemons/stop-capsule-writer.mjs.
The resume verb, invoked explicitly — load the newest valid capsule by created_at, re-ground against live memory, then ACT on waiting_on. Mid-session or on explicit ask; the post-clear boot fires the same procedure automatically via daemons/resume-verb.mjs.
Run the volunteering ledger before declaring work done. Forces surfacing of what changed/didn't, what was noticed-but-not-fixed, what was guessed, and what tradeoffs were made on the principal's behalf. The standard - the principal should never be surprised later by something the agent knew at the time.
Capture a confident agent claim (Phase 1) or resolve one as right/wrong (Phase 2) in vault/memory/TRUST_DECAY.md. Builds the longitudinal record of agent calibration over time. Pairs with /honesty-check (which should reduce Phase 1 frequency) and /diagnose (which surfaces causes that often reveal Phase 2 events).
One evidence-gated pass that sequences /dream, /reconcile, /sweep-now, and /digest over your own vault, with a /system-check gate and a ledger-review pass over the measurement layer (Honesty Ledger, Trust Decay, Failure Modes). Stays exactly as human-gated as the legs it calls -- stages, never auto-applies. Skips a leg gracefully when there is nothing to do; every leg that runs leaves an evidence line.
Dispatch Hestia to run all 3 vault sweeps (DELEGATION_TRACKER stale items, HEAT_INDEX dormant flips, broken wikilinks) and append the result to HESTIA_SWEEP_LOG.