Individual skill
setup-progen2-remote-tool
Set up, launch, validate, and troubleshoot the ProGen2 ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.
skills/setup-progen2-remote-tool/SKILL.md
Source commit 5598a9fc97e32964fe9b703818e7d0747142f179
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 5, 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 · 12,932 bytesSKILL.mdcore · 12,932 bytesSKILL.mdcore · 12,932 bytesSKILL.mdcore · 12,932 bytesSKILL.mdcore · 12,932 bytesSKILL.mdcore · 12,932 bytesSKILL.mdcore · 12,932 bytesSKILL.mdcore · 12,932 bytesSKILL.mdcore · 12,932 bytesSKILL.mdcore · 12,932 bytesSKILL.mdcore · 12,932 bytesSKILL.mdcore · 12,932 bytes
Read excerpt
# Set up ProGen2 as a remote tool
> Validation status (2026-10-01): ProGen2-base ran on the NVIDIA GB10 (aarch64, cc 12.1) with the optimization kit **OFF** — its one prebuilt object is x86-64 and owns a lever family whose all-or-none rule takes the whole mode. Verified on FOUR CONSECUTIVE IDENTICAL REQUESTS in one held worker: 0.65 s then 0.16 s each. **Read the generate bound before deploying.** The two obvious ceilings — 16 sequences, 1024 tokens — are each sane and their PRODUCT is not: measured, 8x512 tokens costs 5.81 GiB, 8x1024 costs 29.2, and 16x1024 costs **116.93 GiB**, essentially the whole card, because peak is roughly quadratic in num_samples x max_length and nothing caps the K/V cache. The tool therefore bounds the product at 4096 tokens, which is where the budget is declared. Scoring is a separate and much flatter envelope: 1.65 GiB at 128 residues to 2.82 at 2040, 1.71x over 16x the length. Public publication, cross-user isolation, concurrency, recovery and sequence quality 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