infrarsi-optimize — Claude Code skill: setup and use
The infrarsi-optimize Claude Code skill tunes an existing GPU training job while keeping its training task unchanged. It tests launch settings and code edits to reduce step time or improve throughput.
no license ★ 99 updated 2026-11-12
npx skills add TokenRhythm/InfraRSI --skill infrarsi-optimize -a claude-codeWhat infrarsi-optimize does
The skill helps tune a training launch and patch code to reduce the time per optimizer update without changing the model, data, or precision rules. InfraRSI runs each candidate against the original job and keeps only changes that pass verification. The process includes noise calibration, a search, and a back-to-back rerun of the best candidate.
First, define and agree on a contract: which settings and files may change, what stays frozen, and the run budget. The engine then runs in the background. A fresh sub-agent handles each engine question about settings or code patches, without access to earlier answers. Measurements must come from the engine; the skill does not target inference speed, model quality, or hyperparameter search.
Run the commands from the project directory with Python 3.11+, or Python 3.10 plus tomli, and PyYAML. After the user agrees, apply verified changes with infrarsi apply <run_dir> --write. If no candidate passes, the result keeps the current configuration at x1.00.
What it helps with
- reduce optimizer-update time in a GPU training run
- raise training MFU or throughput
- test settings for distributed training
- check whether a larger batch fits the run
Example prompts for the agent
- Speed up GPU training without changing the model or data.
- Reduce the step time in my PyTorch DDP run.
- Tune distributed training with DeepSpeed and verify each candidate.
How to install infrarsi-optimize
1Skills CLI (Vercel)
npx skills add TokenRhythm/InfraRSI --skill infrarsi-optimize -a claude-code2Manually: put the files in place
~/.claude/skills/infrarsi-optimize/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/infrarsi-optimize/
1Skills CLI (Vercel)
npx skills add TokenRhythm/InfraRSI --skill infrarsi-optimize -a codex2Manually: put the files in place
.agents/skills/infrarsi-optimize/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add TokenRhythm/InfraRSI --skill infrarsi-optimize -a cursor2Manually: put the files in place
.cursor/skills/infrarsi-optimize/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install TokenRhythm/InfraRSI agent_skill/infrarsi-optimize/SKILL.md2Manually: put the files in place
.github/skills/infrarsi-optimize/SKILL.md1Skills CLI (Vercel)
npx skills add TokenRhythm/InfraRSI --skill infrarsi-optimize -a gemini-cli2Platform CLI
gemini skills install https://github.com/TokenRhythm/InfraRSI --path agent_skill/infrarsi-optimizeManually: put the files in place
.devin/skills/infrarsi-optimize/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about infrarsi-optimize
How do I install infrarsi-optimize in Claude Code?
Run npx skills add TokenRhythm/InfraRSI --skill infrarsi-optimize -a claude-code. The skill file is at ~/.claude/skills/infrarsi-optimize/SKILL.md.
What does infrarsi-optimize do?
It tunes an existing GPU training job and checks launch-setting or code changes against the original run. Only candidates that pass verification are accepted.
What does infrarsi-optimize require?
It requires Python 3.11+, or Python 3.10 with tomli, PyYAML, and a runnable GPU training job. Run its commands from the project directory.