Skill254 repo starsupdated 2mo ago

sibyl-final-critic

The sibyl-final-critic skill deploys a research paper review agent designed to evaluate academic submissions at NeurIPS and ICML standards. Use this skill when conducting comprehensive final-stage peer review of machine learning research papers, requiring expert-level critique of methodology, novelty, experimental rigor, and presentation quality within the Sibyl research orchestration system.

View source Repository: AutoResearch-SibylSystem

Install in Claude Code

Copy

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

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

AGENT_NAME: sibyl-final-critic
AGENT_TIER: sibyl-heavy
SIBYL_ROOT: /Users/cwan0785/sibyl-system

Workspace path: $ARGUMENTS[0]