toc-review
Skill0 starsChanged 2 months agoNo licenceView on GitHub
商科版 Tree-of-Concerns 对抗红队，分支分类学基于 Pollock 2025 故事架构：张力与结/读者转化/对话与贡献/人物与故事线/证据登台/承诺兑现六分支 + 0-2 条按稿派生动态分支（五幕断裂/稿型比例/写作阶段/AMJ Canvas），分支轮换不同厂商模型家族（跨模型对抗），四阶段辩论（质疑→辩护→修订→裁决，双轴判定+realism 门），独立裁判模型跨分支 Panel 调解并分诊可修复 vs 结构性，报告以叙事骨架总评开篇、只提取未声明弱点与 desk-reject 门禁风险，附原文引文与修复优先级。触发词：红队、压力测试、弱点清单、预判审稿、审稿人会怎么打、会被拒吗、desk reject 风险、toc review、unstated limitations。全稿总控（叙事+实质一份报告）用 paper-review，工艺打分用 pollock-qc，交互追问用 grill-the-claim，已收审稿意见用 revision-coach。
In this repository55 other files it gives its agents.
- humanizer/AGENTS.mdAGENTS.md
- _pi-config/AGENTS.mdAGENTS.md
- ai-disclosureSkill
- causal-analysisSkill
- check-methodologySkill
- diagnose-introductionSkill
- did-analysisSkill
- discussion-reviewSkill
- distill-introduction-exemplarSkill
- distill-methods-exemplarSkill
- distill-paper-exemplarSkill
- distill-results-exemplarSkill
- distill-story-exemplarSkill
- distill-theory-exemplarSkill
- empirical-intakeSkill
- empirical-pipeline-pythonSkill
- empirical-pipeline-stataSkill
- empirical-writeupSkill
- exploratory-data-analysisSkill
- grill-the-claimSkill
- handoffSkill
- humanizerSkill
- human-writingSkill
- huntington-klein-causal-designSkill
- intro-reviewSkill
- latex-tablesSkill
- literature-notes-obsidianSkill
- methods-reviewSkill
- miles-management-organization-theoriesSkill
- ml-analysisSkill
- notebooklm-pipelineSkill
- officecliSkill
- paper-reviewSkill
- paper-state-protocolSkill
- paper-story-contractSkill
- paper-writing-stackSkill
- polishSkill
- pollock-qcSkill
- proofreadSkill
- python-panel-dataSkill
- research-gap-diagnosisSkill
- results-reviewSkill
- reverse-validation-pipelineSkill
- revision-coachSkill
- run-empirical-researchSkill
- stata-data-cleaningSkill
- stataSkill
- theory-reviewSkill
- tod-debateSkill
- wooldridge-econometricsSkill
- write-introductionSkill
- write-methodsSkill
- write-resultsSkill
- write-theorySkill
- writing-for-agentsSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.