paper-draft

paper-draft is a skill for Claude Code from Lambenthan/empiricalwiki. It costs 39 tokens per session (3,667 once invoked), scanned A, original, MIT.

A workflow that turns a research paper plan into a complete LaTeX paper, including sections, figures, tables, and verified bibliography entries. LaTeX is a text-based system commonly used to typeset technical documents.

In plain words
What is it for?
Use it to draft or incrementally write a paper, optionally review each section, and produce a compilable paper directory with references and visual materials.
Why use it?
It connects each section to the project’s recorded claims, experiments, and sources, reducing unsupported writing and citation mistakes.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; mentions Claude Code.

Not installable on its own: it runs a file from its repository that does not travel with it. Clone the repository, or install whatever ships that file. The line is python3 tools/research_wiki.py log wiki/ \.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for paper-draft

README.md
[![agentmods](https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/paper-draft.svg)](https://agentmods.dev/skills/lambenthan/empiricalwiki/paper-draft)
Your own site
<a href="https://agentmods.dev/skills/lambenthan/empiricalwiki/paper-draft"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/paper-draft.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,667 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.03667
Opus 5 $0.00019 $0.01834
Sonnet 5 $0.00008 $0.00733
Haiku 4.5 $0.00004 $0.00367

Measured 6d ago against content hash 255b10dbf620, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

paper-draft scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/paper-draft/SKILL.md · 330 lines

How it starts

The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/paper-draft

从 /paper-plan 生成的 PAPER_PLAN.md 起草完整 LaTeX 论文。 逐 section 撰写:每个 section 从 wiki 读取 claims/experiments/papers/concepts 取材, 生成 LaTeX + figures + tables。BibTeX 从 DBLP/CrossRef 获取(遵循 citation-verification), 完成后执行 de-AI polish(遵循 academic-writing)。 可选逐 section Review LLM review。输出可编译的 paper/ 目录。

Inputs

  • plan:PAPER_PLAN.md 的路径(如 wiki/outputs/paper-plan-sparse-lora-2026-04-08.md
  • --review(可选):启用逐 section Review LLM review
  • --sections(可选):只写指定 section(如 --sections 3,4 只写 Method + Experiments),用于增量撰写

Outputs

  • paper/ 目录(在 wiki 项目根下):
    • paper/main.tex — 主文件(include 各 section)
    • paper/sections/introduction.tex
    • paper/sections/related_work.tex
    • paper/sections/method.tex
    • paper/sections/experiments.tex
    • paper/sections/conclusion.tex
    • paper/sections/appendix.tex(若有)
    • paper/figures/ — 生成的 figures(PDF/PNG)
    • paper/tables/ — 独立 table 文件(可选)
    • paper/math_commands.tex — 共享数学符号定义
    • paper/references.bib — 验证的 BibTeX 条目
  • wiki/log.md — 追加日志

Wiki Interaction

Reads

  • wiki/outputs/paper-plan-*.md — PAPER_PLAN(章节大纲、evidence map、figure plan、citation plan)
  • wiki/claims/*.md — target claims 的 Statement、Evidence summary、Conditions
  • wiki/experiments/*.md — Results、Analysis、key_result、metrics 数据
  • wiki/papers/*.md — Method、Results、Related(作为引用内容和 baseline 参考)
  • wiki/concepts/*.md — Definition、Formal notation、Variants(支持 Method 撰写)
  • wiki/topics/*.md — Overview、Timeline、SOTA tracker(支持 Introduction 上下文)
  • wiki/ideas/*.md — Motivation、Hypothesis(支持 Introduction 的 gap 叙述)
  • wiki/people/*.md — 人名和机构(引用格式)
  • wiki/graph/edges.jsonl — 关系图(构建论证逻辑链)
  • wiki/graph/open_questions.md — 已知局限(写 Limitations 和 Future Work)
  • .claude/skills/shared-references/academic-writing.md — 写作规范
  • .claude/skills/shared-references/citation-verification.md — 引用纪律

Writes

  • paper/ 目录(所有文件)
  • wiki/log.md — 追加操作日志

Graph edges created

  • 无(paper-plan 已创建 derived_from 边)

Workflow

前置:确认工作目录为 wiki 项目根(包含 wiki/raw/tools/ 的目录)。

Read the full file on GitHub · 330 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 330 lines · 39 tokens per session scan A 255b10dbf620

Subscribe to this mod's changes

paper-draft is a skill published in the GitHub repository Lambenthan/empiricalwiki (82 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 3,667 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

audit-reproducibility

Enforce the replication-protocol.md rule by cross-checking numeric claims in a manuscript against the actual R / Stata / Python outputs. Report PASS/FAIL per claim against tolerance thresholds. Use before submission and before releasing a replication package.

pedrohcgs/claude-code-my-workflow · 54 tokens

grant-proposal

Scaffold a research grant proposal (NSF, NIH, ERC, or foundation) by composing existing primitives — pulls identification strategy from an /interview-me spec, delegates the data-management plan to /data-management-plan and the facilities statement to /capture-environment, and emits a funder-requirements checklist. Use…

pedrohcgs/claude-code-my-workflow · 131 tokens

preregister

Draft a structured preregistration document (OSF, AsPredicted, or AEA RCT Registry style) from a research spec or free-form study description. Output is a Markdown file with hypotheses, design, sampling plan, analysis plan, exclusions, and inference criteria — annotated with MUST / SHOULD / MAY clarity flags. Use when…

pedrohcgs/claude-code-my-workflow · 153 tokens

capture-environment

Snapshot the computational environment for a replication package — detects the analysis stack (R / Stata / Python) and emits the right lockfiles (renv.lock + sessionInfo.txt, requirements.txt / environment.yml / uv.lock, Stata version + ado package list), records seeds and RNG kind, optionally writes a pinning…

pedrohcgs/claude-code-my-workflow · 139 tokens

data-management-plan

Draft a funder-compliant Data Management Plan (NSF DMP, NIH DMS Policy 2023, ERC, Horizon Europe) by composing the confidential-data and environment-capture primitives. Sections cover data description, formats/metadata, storage/backup, access/sharing, preservation/archiving, and roles. Use when user says "data…

pedrohcgs/claude-code-my-workflow · 143 tokens

power-analysis

Compute statistical power, required sample size, and minimum detectable effect (MDE) for a study design, then write a registry-ready power section. Handles two-arm RCTs (with clustering / ICC and unequal allocation), multiple-arm corrections, and a simulation-based power option for non-standard designs…

pedrohcgs/claude-code-my-workflow · 150 tokens