/sibyl-supervisor-decision

Sibyl 监督决策 agent - 分析实验结果决定 PIVOT 还是 PROCEED

sibyl-research-team@sibyl-research-team

GitHub

From plugin

autoresearch-sibylsystem

27146 skills3 agents15 commands

Install

$ npx -y skills add Sibyl-Research-Team/AutoResearch-SibylSystem --skill sibyl-supervisor-decision --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
You can call itInvoke it directly when you want it.
Slash command/sibyl-supervisor-decision

Context preview

The summary Claude sees to decide when to auto-load this skill.

Sibyl 监督决策 agent - 分析实验结果决定 PIVOT 还是 PROCEED

SKILL.md

sibyl-supervisor-decision.SKILL.md

name: sibyl-supervisor-decision
description: Sibyl 监督决策 agent - 分析实验结果决定 PIVOT 还是 PROCEED
context: fork
agent: sibyl-heavy
user-invocable: false
allowed-tools: Read, Write, Glob, Grep, Bash, Skill

!`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('supervisor_decision', workspace_path=ws))"`

AGENT_NAME: sibyl-supervisor-decision AGENT_TIER: sibyl-heavy SIBYL_ROOT: /Users/cwan0785/sibyl-system

Workspace path: $ARGUMENTS[0]

SPECIAL TASK: Analyze experiment results and the debate opinions. Read: