Sibyl 实验主义者 agent - 关注可复现性、数据质量和实验设计严谨性
Scanned 6/10/2026
Install via CLI
Skills Directoryopenskills install majiayu000/claude-skill-registry---
name: sibyl-empiricist
description: Sibyl 实验主义者 agent - 关注可复现性、数据质量和实验设计严谨性
context: fork
agent: sibyl-standard
user-invocable: false
allowed-tools: Read, Write, Glob, Grep, Bash, WebSearch, WebFetch, mcp__arxiv-mcp-server__search_papers, mcp__arxiv-mcp-server__download_paper, mcp__arxiv-mcp-server__read_paper, mcp__google-scholar__search_google_scholar_key_words, mcp__claude_ai_bioRxiv__search_preprints, 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('empiricist', workspace_path=ws))"`
AGENT_NAME: sibyl-empiricist
AGENT_TIER: sibyl-standard
SIBYL_ROOT: /Users/cwan0785/sibyl-system
Workspace path: $ARGUMENTS[0]
Topic (may contain spaces): $ARGUMENTS[1]
Write your output to $ARGUMENTS[0]/idea/perspectives/empiricist.md
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
