🎯

argument-selfloop

🎯Skill

from willoscar/research-units-pipeline-skills

VibeIndex|
What it does

Checks and repairs self-referential or circular arguments within a research document to ensure logical consistency and prevent circular reasoning.

argument-selfloop

Installation

Install skill:
npx skills add https://github.com/willoscar/research-units-pipeline-skills --skill argument-selfloop
101
AddedJan 25, 2026

Skill Details

SKILL.md

Overview

# research-units-pipeline-skills

> 一句话:让 Pipeline 会"带人 / 带模型"做研究——不是给一堆脚本,而是给一套语义化的 skills,每个 skill 知道"该做什么、怎么做、做到什么程度、不能做什么"。

---

WIP

  1. 在 Appendix 增加了表格
  2. 持续打磨写作技巧,提升写作上下限(已经尝试了增加 role playing 的 soft 约束)

Todo

  1. 加入多 cli 协作,multi-agent design (在合适的环节接入 API,替代或者分担 codex 执行过程中的压力)
  2. 完善剩余的Pipeline,example 新增例子
  3. 精简Pipeline中冗余的中间内容,遵循优雅的奥卡姆剃刀原则,如无必要,勿增实体。

核心设计:Skills-First + 拆解链路 + 证据先行

传统问题:研究流水线要么是黑盒脚本(不知道怎么改),要么是松散文档(执行时靠人肉判断)。

本设计的解法

  1. Skills 语义化:每个 skill 不是函数,而是带引导的执行单元——

- inputs / outputs:明确依赖和产物

- acceptance:验收标准(如"每小节映射 >=8 篇论文")

- notes:怎么做、边界条件、常见错误

- guardrail:不能做什么(如 C2-C4 阶段 NO PROSE

  1. 拆解链路:6 个 checkpoint(C0→C5),约 40+ 个原子 units(不同 pipeline 略有差异;LaTeX 版本会多几个),依赖关系显式写在 UNITS.csv
  2. 证据先行:C2-C4 强制先建证据底座(taxonomy → mapping → evidence packs),C5 才写作

设计目标

  • 可复用:同一个 skill(如 subsection-writer)可被多个 pipeline 复用,换个 pipeline 不用重写逻辑
  • 可引导:新手/模型按 skill 的 acceptance + notes 执行,不需要"猜"该做到什么程度
  • 可约束guardrail 防止执行者(尤其是模型)越界(如在 C3 阶段偷偷写正文)
  • 可定位:失败时报告指向具体 skill + 中间产物,修复后从失败点继续

---

为什么这样设计?

| 特性 | 传统做法 | 本设计 |

|------|----------|--------|

| 可见 | 黑盒脚本 | 每个 unit 产出中间文件(papers/outline/citations/sections/) |

| 可审计 | 日志散落 | UNITS.csv 记录执行历史与验收标准,DECISIONS.md 记录人类检查点 |

| 可自循环 | 失败全部重跑 | 质量门 FAIL → 报告告诉你改哪个中间产物 → 修复后从失败 unit 继续 |

| 可复用 | 每个项目重写 | skills 模块化,跨 pipeline 复用(如 taxonomy-builderevidence-binder) |

| 可引导 | 靠人肉判断 | 每个 skill 带 acceptance + notes,执行者知道"做到什么程度" |

English version: [README.en.md](README.en.md).

codex 参考配置

```toml

[sandbox_workspace_write]

network_access = true

[features]

unified_exec = true

shell_snapshot = true

steer = true

```

一句话启用(推荐:对话里跑 Pipeline)

启动 codex

> codex --sandbox workspace-write --ask-for-approval never

把下面这句话丢给 Codex(或 Claude Code)即可:

> 给我写一个 agent 的 latex-survey

这句话会触发 repo 内的 skills 自动路由并执行 pipeline(按 UNITS.csv 合同落盘中间产物)。

(可选:指定 pipeline 文件:pipelines/arxiv-survey-latex.pipeline.md(或 research-units-pipeline-skills/pipelines/arxiv-survey-latex.pipeline.md);不想自动同意 C2:把“C2 自动同意”删掉即可。C2 是一个 human in the loop 的介入点)

你也可以更明确一点(避免 router 选错):

> 用 pipelines/arxiv-survey-latex.pipeline.md 给我写一个 agent 的 latex-survey(启用 strict 质量门;C2 自动同意)

你会得到什么(分层产物 + 自循环入口)

执行层

  • UNITS.csv:39+(还在增加) 个原子 unit 的执行合约(依赖 → 输入 → 输出 → 验收标准)
  • DECISIONS.md:人类检查点(C2 必须审批大纲后才进入写作)

中间产物层(按 checkpoint 分层):

```

C1: papers/papers_raw.jsonl → papers/papers_dedup.jsonl → papers/core_set.csv (+ papers/retrieval_report.md) # 检索 + 去重/精选

C2: outline/taxonomy.yml → outline/outline.yml → outline/mapping.tsv (+ outline/coverage_report.md; outline/outline_state.jsonl) # 结构(NO PROSE)

C3: papers/fulltext_index.jsonl → papers/paper_notes.jsonl + papers/evidence_bank.jsonl → outline/subsection_briefs.jsonl (+ outline/chapter_briefs.jsonl) # 证据底座(NO PROSE)

C4: citations/ref.bib + citations/verified.jsonl → outline/evidence_bindings.jsonl → outline/evidence_drafts.jsonl → outline/anchor_sheet.jsonl → outline/writer_context_packs.jsonl (+ outline/claim_evidence_matrix.md) # 引用 + 证据包(NO PROSE)

C5: sections/*.md → output/DRAFT.md → latex/main.tex → latex/main.pdf # 写作 + 编译

```

质量门 + 自循环入口

  • --strict 模式才会持续写入质量门结论:unit 被 BLOCKED 时看 output/QUALITY_GATE.md(最新条目)定位需要修的中间产物;脚本/缺产物等运行问题看 output/RUN_ERRORS.md
  • --strict 跑法:不会做 unit-level 质量门拦截(output/QUALITY_GATE.md 可能只有模板/历史记录);以 output/AUDIT_REPORT.md(全局审计)+ output/RUN_ERRORS.md 为主
  • 写作层自循环(只修复失败小节):

- output/WRITER_SELFLOOP_TODO.md(写作门:PASS/FAIL + 需要修复的 sections 列表)

- output/SECTION_LOGIC_REPORT.md(thesis + 连接词密度)

- output/ARGUMENT_SELFLOOP_TODO.md(论证链路 + 前提/口径一致性;ledger 为中间态,不进终稿)

- output/CITATION_BUDGET_REPORT.md(引用增密建议)

简单的对话式执行(从 0 到 PDF)

```

你:给我写一个 agent 的 latex-survey

↓ [C0-C1] 检索 1200+ 候选论文(目标 1500+)→ core set=300(最终文献150++ 默认;arXiv 可补全 meta)

↓ [C2] 构建 taxonomy + outline + mappin

More from this repository10

🎯
unit-planner🎯Skill

Plans and structures research unit workflows by defining precise execution guidelines, inputs, outputs, acceptance criteria, and guardrails for each research pipeline skill, ensuring systematic and...

🎯
evaluation-anchor-checker🎯Skill

Validates and checks evaluation anchors in research papers to ensure they meet specific quality and consistency standards during the research pipeline.

🎯
agent-survey-corpus🎯Skill

Curates and processes a corpus of research papers specifically focused on agent-related research, preparing the collection for systematic survey and analysis.

🎯
chapter-lead-writer🎯Skill

Coordinates and guides the writing of a research chapter, ensuring coherent structure, academic rigor, and alignment with the predefined outline and evidence base.

🎯
writer-selfloop🎯Skill

Enables self-correcting and iterative writing processes within a research pipeline, allowing automatic recovery and continuation from writing failures by identifying and fixing specific intermediat...

🎯
pdf-text-extractor🎯Skill

Extracts raw text content from PDF files, preparing research papers for further text-based analysis and processing in the research pipeline.

🎯
unit-executor🎯Skill

Executes individual research pipeline units according to predefined semantic contracts, tracking inputs, outputs, acceptance criteria, and guardrails for each atomic research task.

🎯
chapter-briefs🎯Skill

Generates concise, structured briefs for research paper chapters, mapping key insights and arguments to support systematic literature review writing.

🎯
citation-anchoring🎯Skill

Identifies and contextualizes academic citations by mapping references to specific sections or claims within a research document, ensuring precise and meaningful citation placement.

🎯
paper-notes🎯Skill

Extracts and summarizes key insights and notes from research papers, organizing them in a structured format for further analysis and reference during the research pipeline.