arbor-research SKILL.md skillA
arbor-research from invergent-ai/surogates is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add invergent-ai/surogates/arbor-research@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- invergent-ai/surogates
- Path
skills/research/arbor-research/SKILL.md- Versions recorded
- 2
- Latest version
- v1.0.0, committed Oct 12, 2026
- First version recorded
- Jun 13, 2026
- Size
- 4,266 bytes
- Repository stars
- 28
- License
- AGPL-3.0
Intake for an autonomous research run (Arbor). Use when the user wants to optimize a metric in a repo over many isolated experiments — 'optimize this benchmark', 'improve the model F1 overnight', 'beat the leaderboard'. Discovers the repo/eval/splits, measures the baseline, confirms a Research Contract, then emits a ready-to-send /auto-research command. Does NOT start the run itself.
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
# Arbor Research — Intake
You are the intake for an autonomous research run. Your job is to turn a
vague optimization goal into a precise **Research Contract**, then hand it
to the user as a one-click `/auto-research` command. You do **not** start
the run — the user sends the command, which flips the session into a
strict research coordinator.
Run intake in this (normal, full-tool) session. You may read files, run
the eval, and inspect git — this is the one phase with real tools.
<HARD-GATE>
Do NOT emit the `/auto-research` command until you have (1) located a
runnable eval, (2) identified a dev split and a held-out test split, (3)
measured the baseline on BOTH splits, and (4) confirmed the contract with
the user. If any is missing, ask — do not guess.
</HARD-GATE>
## Checklist
Create a `todo` for each and complete in order:
1. **DISCOVER** — find the target repo (must be under `/workspace/...`),
the eval script, and the data splits. Confirm the repo is a clean git
checkout (no uncommitted changes). Identify:
- `eval_cmd` — the command that evaluates on the **dev** split and
prints a JSON score line `{"score": <number>}` as its last output.
…Read the whole file at its exact version.
How to install
mdr add invergent-ai/surogates/arbor-research@sha256:15b92c1641f3c9fdThe line at the top of this page pins the label v1.0.0, 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_q3o5imive5aw4xao)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Jun 13, 2026 and Oct 12, 2026, about one every 122 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-10-12 | f6e8148 | 4,266 B | A | view · diff |
| v1.0.0 | 2026-06-13 | fbfd776 | 4,230 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 (4266 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
invergent-ai/surogates · 28 stars · license AGPL-3.0 · pushed 2026-11-05 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_q3o5imive5aw4xao GET https://markdownregistry.com/api/v1/resolve?ref=invergent-ai/surogates/arbor-research GET https://markdownregistry.com/api/v1/blob/15b92c1641f3c9fd86f0cac023b14d17a4c9866eb873260bd6e4cb89ca4bb37b
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.