Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →vellum-ai/vellum-memory-v3-migration
One-time migration of an existing memory-v2 concept corpus into the memory-v3 section-grain "wiki" — topical articles with a stand-alone lead and queryable sections — with loss-proof staging, assistant-reviewed authoring, and a retrieval-eval gate before cutover.
Passed 15 of 20 test cases with the skill, and 3 of 20 without it.
and 12 more in the full report
14 fixed3 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
We are tracking our migration progress in git. What exact commit message prefix must be used for all migration milestone commits so automated tooling can filter them?
| Checked | Without skill | With skill |
|---|---|---|
| Mandates the commit message prefix memory-v3-migration:. | Missed | Passed |
The instructions your model reads when the skill loads.
Reform an existing memory-v2 corpus into the memory-v3 wiki: a cross-linked set of topical articles where each article's lead is its retrieval card and each ## section is an independently retrievable unit. The assistant is the sole reader and editor of this knowledge base; the goal is a clean, well-organized wiki optimized for retrieval.
This skill is the successor to vellum-memory-v2-migration. That skill backfills an empty corpus from scratch; this one reorganizes a populated one. If concepts/ is empty, stop and run that skill instead.
The mechanical cutover is cheap and mostly automatic: v3 reads the same memory/concepts/*.md tree, the schema is shared, the DB tables already exist, and section embeddings backfill on demand. The work is the reform. v3 retrieval is section-grain: it shows a compact card (the article's lead + its section names) and spotlights the single best-matching ## section. A flat v2 page — bullets, no ## headings, a summary: field v3 ignores — collapses under v3 into one giant lead with no sections: a bloated card that starves the card budget and exposes no section to match. So this skill does two things at once:
links: not edges:, optional current:).⚠️ Prime directive: loss-proof. You are rewriting memory you cannot regenerate. Every stage runs against a read-only snapshot, writes to a separate staging tree, and carries provenance. The live corpus is never edited until a verified cutover. "Loss-proof" is a property you verify (Step 7), not one you intend.
Read references/v3-wiki-principles.md end-to-end first. It defines the v3 article skeleton, the lead-is-the-card rule, the event-vs-topic distinction, hubs (kind: index), section discipline, the card budget, and the banned content shapes. It owns what a good v3 article is; this SKILL.md owns what order to do things in.
Then read references/loss-proofing.md — the snapshot/staging/provenance/verify contract that every later step depends on.
Resolve each before touching anything; if a check fails, stop and fix it.
(1) CLI surface. Confirm the v3 subcommands exist:
assistant --version
assistant memory v3 --help
Expect at least backfill-sections and rebuild-index (used at cutover, Step 8). If absent, the binary predates v3 — upgrade before proceeding.
(2) Cutover switch. Memory-v3 is gated by the workspace config memory.v3.live (a boolean the assistant sets directly — no feature flag, no operator hand-off). Confirm you can read it now, without changing it:
assistant config get memory.v3.live # expect: false — you flip it at cutover (Step 9)
test cases passed, vs 3 / 20 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.