Individual skill
setup-rosettafold3-remote-tool
Set up, launch, validate, and troubleshoot the RoseTTAFold3 ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.
skills/setup-rosettafold3-remote-tool/SKILL.md
Source commit 5598a9fc97e32964fe9b703818e7d0747142f179
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 9, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 1,779
- Repository last updated
- Nov 8, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agents Repository topic
- reasoning-agent Repository topic
- reasoning-language-models Repository topic
- tool-use Repository topic
- ai-agents Repository topic
- ai-scientists Repository topic
- automated-science Repository topic
- co-pilot Repository topic
- co-scientist Repository topic
- ai-for-science Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 12,905 bytesSKILL.mdcore · 12,905 bytesSKILL.mdcore · 12,905 bytesSKILL.mdcore · 12,905 bytesSKILL.mdcore · 12,905 bytesSKILL.mdcore · 12,905 bytesSKILL.mdcore · 12,905 bytesSKILL.mdcore · 12,905 bytesSKILL.mdcore · 12,905 bytesSKILL.mdcore · 12,905 bytesSKILL.mdcore · 12,905 bytesSKILL.mdcore · 12,905 bytes
Read excerpt
# Set up RoseTTAFold3 as a remote tool
> Validation status (2026-09-29): RoseTTAFold3 under the optimization kit's `fast` mode ran on the NVIDIA GB10 (aarch64, cc 12.1). Verified on FOUR CONSECUTIVE IDENTICAL REQUESTS in one held worker -- not on a single smoke, which is the test this standard stopped trusting after openfold3 passed one and then could not answer a repeat. Build 41.3 s, then folds of 20.7 / 16.2 / 16.1 / 16.2 s, peak reserved 3.56 rising to 3.70 GiB, and 13.25 GiB measured at 800 residues. Note this deployment runs a PATCHED interpreter: the kit overwrites five files of the installed `rf3` package and checks them by sha256, so `[kit] mode = "off"` is not available here -- a stock comparison needs a second, pristine environment. Public publication, cross-user isolation, concurrency, recovery and biological accuracy are untested; keep this deployment private.
## Prerequisites
- Run from the ToolUniverse repository root on Linux with Python 3.12.3.
- A CUDA GPU is required. This provider holds its model resident between requests; CPU is not a target.
- Keep provider data, weights, caches, and credentials outside Git.
- Bind to loopback. A non-loopback bind requires TOOLUNIVERSE_API_TOKEN; never put it in arguments or results.
Run the standard-library contract check before downloading large dependencies:
~~~bash