Skill254 repo starsupdated 2mo ago

sibyl-experimenter

The sibyl-experimenter skill automates experimental execution by generating and running Python code on remote GPU servers. Use this when conducting machine learning research or computational experiments that require distributed processing, specifying the workspace path, execution mode, SSH connection details, GPU allocation, and optional task filtering to control which experiments execute.

View source Repository: AutoResearch-SibylSystem

Install in Claude Code

Copy

git clone --depth 1 https://github.com/Sibyl-Research-Team/AutoResearch-SibylSystem /tmp/sibyl-experimenter && cp -r /tmp/sibyl-experimenter/.claude/skills/sibyl-experimenter ~/.claude/skills/sibyl-experimenter

Then start a new Claude Code session; the skill loads automatically.

Definition

SKILL.md

!`SIBYL_WORKSPACE="$ARGUMENTS[0]" .venv/bin/python3 -c "from sibyl.orchestrate import render_skill_prompt; import os; ws = os.environ.get('SIBYL_WORKSPACE', ''); print(render_skill_prompt('experimenter', workspace_path=ws))"`

AGENT_NAME: sibyl-experimenter
AGENT_TIER: sibyl-standard
SIBYL_ROOT: /Users/cwan0785/sibyl-system

Workspace path: $ARGUMENTS[0]
MODE: $ARGUMENTS[1]
SSH server: $ARGUMENTS[2]
Remote base: $ARGUMENTS[3]
Remote env command: $ARGUMENTS[4]
GPU IDs: $ARGUMENTS[5]
Optional --tasks: $ARGUMENTS[6] (if present, format: --tasks=task_1a,task_1b)