memory-corpus-ingest SKILL.md skillA
memory-corpus-ingest from vellum-ai/vellum-assistant is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add vellum-ai/vellum-assistant/memory-corpus-ingest@git:20260818.de25f32Pins git:20260818.de25f32 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- vellum-ai/vellum-assistant
- Path
skills/memory-corpus-ingest/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260818.de25f32, committed Aug 18, 2026
- First version recorded
- Jul 30, 2026
- Size
- 12,062 bytes
- Repository stars
- 1,467
- License
- MIT
Ingest a large dataset into memory as a skimmed map. Cold-store the raw files under a workspace imports directory, census them into a slice plan, skim each slice into compact map pages that point back at the raw files, ingest the map with the memory ingest CLI, and author a drill-in retrieval skill so the corpus stays searchable on demand. For recording archives, transcript collections, document dumps, and any corpus too large to hold in memory directly.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Corpus Ingest Bring a large dataset into the assistant's working knowledge without stuffing it into memory. The model is a library: the workspace holds the stacks (the raw files, cold and complete), memory holds the card catalog (a small set of map pages that say what exists, when it is from, and where to look), and a purpose-built retrieval skill is the librarian that walks to the right shelf on demand. Two invariants drive everything below: 1. **Raw data never enters the memory corpus.** Nothing from the dataset is written into `memory/concepts/` except the map pages, and nothing is ever appended to `memory/buffer.md` (bulk buffer appends trip the consolidation burst guard and per-run caps; the map bypasses the buffer entirely via `assistant memory ingest`). 2. **The map stays small.** Roughly 10 to 50 pages regardless of corpus size. If the corpus doubles, the pages get denser or the slices get coarser; the page count does not double. ## Procedure ### Step 1: Scope and confirm Identify the source and its size before committing: ```bash du -sh /path/to/raw-corpus find /path/to/raw-corpus -type f | wc -l ``` …
Read the whole file at its exact version.
How to install
mdr add vellum-ai/vellum-assistant/memory-corpus-ingest@sha256:ccc38916b79bf36bThe line at the top of this page pins the label git:20260818.de25f32, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ftxhlvpps6m5bzkv)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Jul 30, 2026 and Aug 18, 2026, about one every 19 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260818.de25f32 latest | 2026-08-18 | de25f32 | 12,062 B | A | view · diff |
| git:20260730.f82d69d | 2026-07-30 | f82d69d | 11,832 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (12062 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
vellum-ai/vellum-assistant · 1,467 stars · license MIT · pushed 2026-10-29 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ftxhlvpps6m5bzkv GET https://markdownregistry.com/api/v1/resolve?ref=vellum-ai/vellum-assistant/memory-corpus-ingest GET https://markdownregistry.com/api/v1/blob/ccc38916b79bf36bf8f6a396dcaeb4521d93f9462a1805d00ec9ccfacdf659d8
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from vellum-ai/vellum-assistant
Every file in vellum-ai/vellum-assistant