跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
浏览器与自动化

memory-curator

Use at session-close when a session captured several new memories, or on-demand, to consolidate, deduplicate, prune, and structure the beads memory store. Triggers on "curate memories", "clean up memories", "memory sweep".

DollarDill · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add DollarDill/beads-superpowers --skill memory-curator

技能说明


name: memory-curator description: Use at session-close when a session captured several new memories, or on-demand, to consolidate, deduplicate, prune, and structure the beads memory store. Triggers on "curate memories", "clean up memories", "memory sweep".

Memory Curator

Turn a session's raw bd remember notes into deduplicated, consolidated, well-structured memories — and prune the pile — using bd over text already in context. No runtime, no embeddings.

Announce at start: "I'm using the memory-curator skill to consolidate and structure the memory store."

When to Use

  • Session-close — when the session produced ~3+ new bd remember calls. Offered, never automatic.
  • On-demand — a full-store sweep: Skill(beads-superpowers:memory-curator).

When NOT to Use

  • Sessions with 0–2 new memories — not worth a pass.
  • Mid-task — run at a clean stopping point, not while work is in flight.

Memory taxonomy

Two classes; procedural memory (how-to / workflow) lives in the skills, never the memory store.

  • semantic — durable facts that stay true.
  • episodic — time-bound records of what happened.

The @type is the routing decision. Classify once; the type deterministically sets store, injection, and lifecycle.

@typestoreinjected at session start?lifecycle
semantic:lessonmemoryyes (salience≥4)durable; consolidate near-dups
semantic:root-causememoryyes (salience≥4)durable; consolidate
semantic:patternmemoryyes (salience≥4)durable; consolidate
semantic:correctionmemoryyesdurable (supersedes a wrong memory)
semantic:researchdeferred knowledge-beadnodeferred bead; pointer to a research doc (metadata.doc); bd supersede on replacement
semantic:designdeferred knowledge-beadnodeferred bead; pointer to an ADR/spec (metadata.doc); bd supersede on replacement
semantic:decisiondeferred knowledge-beadnodeferred bead; pointer to an ADR (metadata.doc); bd supersede on replacement
episodic:continuationmemorylatest onlysupersede on next
episodic:done / cleanup / reviewmemory → retirenoconsolidate into a semantic fact, then drop; age-out (>30d) safety net

Crisp routing definitions (the boundary that keeps determinism honest):

  • research / design / decision = a pointer whose detail lives in a doc/ADR you would re-open when relevant. Injecting it every session wastes context — route to a deferred knowledge-bead (§ Beads-native knowledge store).
  • lesson / root-cause / pattern / correction = a standalone, actionable rule you want surfaced unprompted so you don't repeat a mistake (e.g. "bd worktree default path is ./, not .worktrees/"). Stays an injected memory.
  • Escape hatch: if a research/design item is genuinely a standalone reusable rule, classify it as a lesson/pattern — you change the type, never the store directly.

Map a non-canonical prefix to the nearest canonical subtype — e.g. stress-test/plan-stress-test→design, bug→root-cause, sdd→lesson, upstream→research, docs→pattern. If none fits, ask — don't invent. If an extracted "memory" is really procedural, flag it for a skill — don't store it.

Memory header

Every memory keeps its existing key and carries one greppable header line:

@type=semantic:lesson @created=2026-06-28 @salience=4 @refs=<bead-id>,<memory-key> @tags=memory,curation
<self-contained fact body>
  • @type — <class>:<subtype> from the taxonomy — the subtype sets store/injection/lifecycle per the taxonomy table above. @created — ISO date. @salience — 1–5, best-effort. @refs — related bead IDs / memory keys. @tags — lexical filter.

The class makes the prune signal greppable (bd memories | grep '@type=episodic:'); @salience/@tags filter recall.

Beads-native knowledge store

Reference-class memories (research/design/decision) live as deferred knowledge-beads, not in memory. — a deferred bead is never auto-injected at session start, so pointers stay out of every session's context but keep persistence + Dolt sync.

  • Bead: status=deferred with a far-future --defer 2099-01-01 — never closed (closed beads are GC-deleted at 90d). issue_type matches the subtype (research/design/decision); every knowledge-bead also carries the class-marker label kb plus 1–3 topic labels from the controlled vocabulary (scripts/kb-label-vocab.txt).

  • Body: the research doc / ADR stays on disk as the source of truth; the bead is the queryable index/pointer via metadata.doc (display-only), with a distilled summary as the description:

    printf '%s' "<distilled summary: what this note establishes>" | \
    bd create "<one-line summary>" -t <research|design|decision> -l kb,<topic-labels> \
      --defer 2099-01-01 --metadata "$(jq -nc --arg d "<doc-path>" '{doc:$d}')" --body-file - --silent
    
  • Retrieval: bd list --label <topic> --status all (topic) and bd search "<kw>" --status all (keyword) — never metadata filters (broken in bd), never find-duplicates.

  • Lifecycle: bd supersede <old> --with <new> on replacement — the superseded bead closes and decays; the live pointer stays deferred.

  • Move-out invariant (curator route step): write the deferred knowledge-bead → verify (bd show <id> returns it) → then bd forget the memory. Never forget first. Existence-check before writing (idempotent re-run). Run the secret/PII scan on the body first — flag for removal, never relocate a secret into a bead.

  • Aging path: a cooled injected memory (low @salience, or superseded) can retire into a deferred knowledge-bead too, not just a tombstone — same move-out invariant above (write → verify → bd forget), never a copy left behind in both stores.

The sweep

One pass. Input: the session (i

阅读完整来源 ↗