Skill254 estrellas del repoactualizado 2mo ago

sibyl-server-experimenter

The sibyl-server-experimenter skill executes research experiments on remote servers using Claude or Codex models through SSH. Use this when running large-scale AI experiments that require GPU resources beyond local capacity, allowing distributed execution across multiple remote machines with customizable environment configurations and task-specific experiment modes.

Ver fuente Repositorio: AutoResearch-SibylSystem

Instalar en Claude Code

Copiar

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

Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

Definición

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('server_experimenter', workspace_path=ws))"`

AGENT_NAME: sibyl-server-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]
Experiment mode: $ARGUMENTS[6]
Server Codex path: $ARGUMENTS[7]
Server Claude path: $ARGUMENTS[8]
Optional --tasks: $ARGUMENTS[9] (if present, format: --tasks=task_1a,task_1b)

Del mismo repositorio

sibyl-codex-reviewerSkill

Sibyl Codex 独立第三方审查 - 使用 OpenAI Codex 提供不同 AI 视角的评审

sibyl-codex-writerSkill

Sibyl Codex 写作 agent - 使用 Codex (GPT-5) 撰写论文

sibyl-comparativistSkill

Sibyl 比较分析者 agent - 对标 SOTA 和同类工作，定位结果贡献

sibyl-contrarianSkill

Sibyl 反对者 agent - 挑战主流假设，寻找反面证据和盲点

sibyl-criticSkill

Sibyl 批评者 agent - 苛刻但公正的学术批评

sibyl-editorSkill