arbor SKILL.md skillA
arbor from k-dense-ai/scientific-agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add k-dense-ai/scientific-agent-skills/arbor@v1.6Pins v1.6 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- k-dense-ai/scientific-agent-skills
- Path
skills/arbor/SKILL.md- Versions recorded
- 8
- Latest version
- v1.6, committed Oct 1, 2026
- First version recorded
- Jun 12, 2026
- Size
- 17,075 bytes
- Repository stars
- 53,159
- License
- MIT
Applies Arbor Hypothesis Tree Refinement to research artifacts with repeatable evaluators, including model training, agent harnesses, data synthesis and benchmark optimization. Uses persistent hypotheses, isolated experiments, evidence propagation and held-out candidate comparison for multi-experiment research runs. Includes a standard-library state manager and guidance for the RUC-NLPIR Arbor CLI.
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 — Autonomous Optimization via Hypothesis Tree Refinement ## Overview This skill runs an **Autonomous Optimization (AO)** loop: starting from an existing artifact and a measurable objective, improve it through many rounds of experiment and evaluation — without step-by-step human supervision, while checking for overfitting to the development signal. It's the right tool when the bottleneck isn't writing one good change, but *organizing dozens of trials* so that lessons accumulate instead of evaporating. It implements **Hypothesis Tree Refinement (HTR)** from *Arbor* (Jin et al., 2026). The key idea: keep the research state in a persistent **hypothesis tree** rather than in conversation history. Each node binds a hypothesis, the distilled insight it produced, and a pointer to the artifact version that realizes it. You play the long-lived **coordinator** that owns this tree and decides where to search; short-lived **executor** subagents test one hypothesis each in isolated git worktrees and report back. A **held-out merge gate** admits a change only when it improves on a *test* evaluator executors do not optimize against. This is what turns trial-and-error into cumulative… …
Read the whole file at its exact version.
How to install
mdr add k-dense-ai/scientific-agent-skills/arbor@sha256:aae219831d92984eThe line at the top of this page pins the label v1.6, 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_5pv7qxtptml5brjl)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 8 versions of this file, between Jun 12, 2026 and Oct 1, 2026, about one every 16 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.6 latest | 2026-10-01 | a92663a | 17,075 B | A | view · diff |
| v1.5 | 2026-09-30 | 351845e | 15,036 B | A | view · diff |
| v1.4 | 2026-09-30 | 203bcce | 15,036 B | A | view · diff |
| v1.3 | 2026-09-30 | ce9e6e9 | 15,036 B | A | view · diff |
| v1.2 | 2026-09-02 | 1e5eeff | 14,629 B | A | view · diff |
| v1.1 | 2026-07-31 | 4226ca8 | 13,671 B | A | view · diff |
| v1.0 | 2026-07-26 | b085e11 | 13,671 B | A | view · diff |
| git:20260612.9c12fcc | 2026-06-12 | 9c12fcc | 13,676 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 (17075 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
k-dense-ai/scientific-agent-skills · 53,159 stars · license MIT · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_5pv7qxtptml5brjl GET https://markdownregistry.com/api/v1/resolve?ref=k-dense-ai/scientific-agent-skills/arbor GET https://markdownregistry.com/api/v1/blob/aae219831d92984eb6584831f77509cb8650a3986e8c42474aaa4d118ce080a6
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 k-dense-ai/scientific-agent-skills
Every file in k-dense-ai/scientific-agent-skills