Agent Skills: sia

|-

UncategorizedID: elasticdotventures/_b00t_/sia

Install this agent skill to your local

pnpm dlx add-skill https://github.com/elasticdotventures/_b00t_/tree/HEAD/skills/sia

Skill Files

Browse the full folder contents for sia.

Download Skill

Loading file tree…

skills/sia/SKILL.md

Skill Metadata

Name
sia
Description
|-

What

SIA (Self Improving AI) implements a 3-agent loop — Meta, Target, and Feedback — for autonomous benchmark improvement. The Meta agent designs task-specific agents, the Target agent executes tasks, and the Feedback agent reviews performance and drives improvement. Results include 56.6% LawBench gain, #1 on MLE-Bench, and 14x GPU kernel speedup. The three agent roles map to b00t patterns: Meta ≈ research-soul, Feedback ≈ lfmf + discriminator, and generations ≈ checkpoints.

Installation is via pip install 'sia-agent[claude]' or pip install 'sia-agent[openhands]'. Run with sia run --task gpqa --max_gen 5 --run_id 1. Visualize results with sia web. Custom tasks use sia run --task_dir ./my-task --max_gen 5 --run_id 1. MLE-Bench requires dataset preparation via python -m sia.prepare_mlebench_dataset -c 'spaceship-titanic'.

When to Use

Use SIA for autonomous task improvement, benchmark optimization, and any scenario requiring a feedback-driven self-improvement loop. It is particularly effective for ML benchmarks and agent optimization tasks.

How

  1. Install: pip install 'sia-agent[claude]'
  2. Run a task: sia run --task gpqa --max_gen 5 --run_id 1
  3. Visualize results: sia web
  4. For custom tasks: sia run --task_dir ./my-task --max_gen 5 --run_id 1
  5. For MLE-Bench: prepare dataset with python -m sia.prepare_mlebench_dataset -c 'spaceship-titanic'
<!-- b00t:map v1 summary: SIA Self Improving AI — Meta→Target→Feedback 3-agent loop for autonomous task improvement tags: self-improving, ai, agents, python, ml, benchmark tier: ch0nky cmds: pip install 'sia-agent[claude]'; sia run --task gpqa --max_gen 3 --run_id 1 complexity: 6 -->