What is research_idea.write_draft_paper?

A workflow for turning a research idea into a full conference-paper draft using an existing paper template.

Use it to create a paper directory, copy its supporting files, and draft the title, abstract, keywords, and main sections.

It removes the repetitive work of setting up paper files and filling in standard sections from an idea.

research_idea.write_draft_paper — Skill for Claude Code by causify-ai

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add causify-ai/helpers --skill research_idea.write_draft_paper

Clone the repo

git clone --depth 1 https://github.com/causify-ai/helpers

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/causify-ai/helpers/research_idea.write_draft_paper/github.svg)](https://agentmods.dev/skills/causify-ai/helpers/research_idea.write_draft_paper)

Your own site

<a href="https://agentmods.dev/skills/causify-ai/helpers/research_idea.write_draft_paper"><img src="https://agentmods.dev/badge/skills/causify-ai/helpers/research_idea.write_draft_paper/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/causify-ai/helpers/research_idea.write_draft_paper"><img src="https://agentmods.dev/badge/skills/causify-ai/helpers/research_idea.write_draft_paper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 9 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 951 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 3
Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00009	$0.00951
Opus 5.5	$0.00004	$0.00380
Sonnet 5.5	$0.00002	$0.00190
Haiku 4.5	$0.00001	$0.00095

Measured 3d ago against content hash b32ae4a48ce6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

research_idea.write_draft_paper 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 3d 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/research_idea.write_draft_paper/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal

Given a research idea, write a full conference paper draft using the template in papers/template/

Workflow

Read the Inputs

Read the research idea passed by the user (a file under research/ideas/*.md, or idea text pasted directly)
Read the paper template papers/template/paper.md, including the comment block at the top, for usage and section structure
Read an existing paper for style and depth, e.g. papers/Optimal_strategy_for_racket_sports/paper.md

Set Up the Paper Directory

Derive a short Title_Case name for the paper from the idea (e.g. RL_for_Automated_EDA); ask the user if the idea does not suggest an obvious name
Create papers/<Paper_Name>/ if it does not exist
Link Makefile to papers/template/Makefile with a symlink, so that all the paper dirs stay in sync, e.g., ln -s ../template/Makefile papers/<Paper_Name>/Makefile
- Do not copy it and do not edit it for a single paper
Copy references.bib, ieee-template.typ, and figures/ from papers/template/ into the new directory
Do not copy run_latex.sh, lint_latex.sh, or template.pdf, since they are obsolete or build outputs
- Build with make (which calls run_latex.py for LaTeX, which also renders the diagrams with render_images.py)
- Lint with lint_text.py -i <file> --use_dockerized_prettier
If the paper is written in LaTeX instead of Markdown, also copy paper.tex and keep the \input{papers/template/style.tex} line in paper.tex, which is shared by all the papers
Do not overwrite an existing paper.md without confirming with the user

Write `paper.md`

Fill in every <...> placeholder with content derived from the idea: title, author(s) (use the assignee(s) listed in research/ideas/README.md for this idea, plus GP Saggese), abstract, keywords, and all body sections
Keep the template's section structure (Introduction, Related Work, Problem Formulation, core methodology, Discussion/Limitations, Conclusion); add, remove, or rename sections only where the template says it's allowed
Turn the idea's Core Idea, Formalization, Key Examples, and Research Topics into the Introduction and Problem Formulation sections
Turn the idea's Questions and Next steps into Discussion/Limitations and Conclusion/Future Work material
State plainly, per the template, what has not been validated (e.g. no computational implementation or empirical evaluation) instead of fabricating results the idea does not support
Delete the template's guidance bullets and HTML comment once replaced with real content

Read the full file on GitHub · 82 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.

3d ago Changed · +13 lines b32ae4a48ce6
1mo ago Changed 840a4f49c93c
1mo ago First seen · 69 lines · 9 tokens per session scan A 93e186b377a4

Subscribe to this mod's changes

research_idea.write_draft_paper is a skill published in the GitHub repository causify-ai/helpers (150 stars, last pushed yesterday), licensed Apache-2.0. It adds 9 tokens to every session and 951 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-09-03.

Research Writing and docs

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens