Skill254 repo starsupdated 2mo ago
sibyl-section-critic
The sibyl-section-critic skill evaluates specific sections of academic papers by reading markdown files from a designated workspace directory and generating detailed critiques. Use this tool when you need systematic feedback on individual paper sections during the research writing process, with results stored in a structured critique output file.
Install in Claude Code
Copygit clone --depth 1 https://github.com/Sibyl-Research-Team/AutoResearch-SibylSystem /tmp/sibyl-section-critic && cp -r /tmp/sibyl-section-critic/.claude/skills/sibyl-section-critic ~/.claude/skills/sibyl-section-criticThen 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('section_critic', workspace_path=ws))"`
AGENT_NAME: sibyl-section-critic
AGENT_TIER: sibyl-light
SIBYL_ROOT: /Users/cwan0785/sibyl-system
Workspace path: $ARGUMENTS[0]
Section: $ARGUMENTS[1]
Section ID: $ARGUMENTS[2]
Read: $ARGUMENTS[0]/writing/sections/$ARGUMENTS[2].md
Write critique to: $ARGUMENTS[0]/writing/critique/$ARGUMENTS[2]_critique.mdMore from this repository
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
Sibyl 编辑 agent - 整合论文各章节为完整稿件
sibyl-empiricistSkill
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
sibyl-experiment-supervisorSkill
Sibyl 后台实验监督 agent - 持续刷新 GPU 空闲状态、动态派发排队实验、处理运行时间/状态漂移