What is ml-paper-writing?

A set of instructions for writing research papers about machine learning and artificial intelligence for conferences such as NeurIPS, ICML, ICLR, ACL, AAAI, and COLM.

Use it to draft or revise paper sections, find and verify citations, prepare camera-ready submissions, or adapt a paper to another conference.

It provides a process for turning research repositories and results into structured drafts, checking references, following conference formats, and revising papers.

ml-paper-writing — Skill for Claude Code and Codex by DJRHails

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 DJRHails/dotfiles --skill ml-paper-writing

Clone the repo

git clone --depth 1 https://github.com/DJRHails/dotfiles

Made for: Claude Code, Codex.

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/djrhails/dotfiles/ml-paper-writing.svg)](https://agentmods.dev/skills/djrhails/dotfiles/ml-paper-writing)

Your own site

<a href="https://agentmods.dev/skills/djrhails/dotfiles/ml-paper-writing"><img src="https://agentmods.dev/badge/skills/djrhails/dotfiles/ml-paper-writing.svg" alt="Measured on agentmods" height="20"></a>

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,120 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.

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	$0.00065	$0.03120
Opus 5	$0.00032	$0.01560
Sonnet 5	$0.00013	$0.00624
Haiku 4.5	$0.00006	$0.00312

Measured 6d ago against content hash fafcb159548f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ml-paper-writing 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.

modules/agents/skills/ml-paper-writing/SKILL.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ML Paper Writing for Top AI Conferences

Expert-level guidance for writing publication-ready papers targeting NeurIPS, ICML, ICLR, ACL, AAAI, and COLM. Combines writing philosophy from top researchers (Nanda, Farquhar, Karpathy, Lipton, Steinhardt, Perez) with practical tools: LaTeX templates, citation verification APIs, and conference checklists. This file is the summary; the deep dives live in references/.

When to Use This Skill

Starting from a research repo to write a paper
Drafting or revising specific sections
Finding and verifying citations for related work
Formatting for conference submission
Resubmitting to a different venue (format conversion)
Iterating on drafts with scientist feedback

Always remember: First drafts are starting points for discussion, not final outputs.

Core Philosophy: Collaborative but Proactive

Paper writing is collaborative, but be proactive in delivering drafts. Understand the project (repo, results, docs), deliver a complete first draft when confident, search literature via APIs, then refine through feedback cycles. Don't block waiting for feedback on every section—produce something concrete the scientist can react to.

Confidence Level	Action
High (clear repo, obvious contribution)	Write full draft, deliver, iterate on feedback
Medium (some ambiguity)	Write draft with flagged uncertainties, continue
Low (major unknowns)	Ask 1-2 targeted questions, then draft

Only block for input when: target venue is unclear, contradictory framings seem equally valid, results look incomplete/inconsistent, or review is explicitly requested. Per-section flagging tables and repo-exploration steps: references/paper-workflow.md.

⚠️ CRITICAL: Never Hallucinate Citations

AI-generated citations have a ~40% error rate. Hallucinated references are academic misconduct that can cause desk rejection or retraction.

Read the full file on GitHub · 244 lines

Files

What ships with it

52 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

6d ago First seen · 244 lines · 65 tokens per session scan A fafcb159548f

Subscribe to this mod's changes

ml-paper-writing is a skill published in the GitHub repository DJRHails/dotfiles (2 stars, last pushed 2d ago), licensed MIT. It adds 65 tokens to every session and 3,120 once invoked, about $0.0003 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 2026-08-31.

Scientific Writing and docs dotfile dotfiles vim zsh

autopilot-batch

Fan out a batch of autopilot-queued issues to parallel background worktree subagents — each runs /autopilot at the build model from its 'model:' label — with a gating review at Opus 5 or above and never below the build (Opus reviews Sonnet and Opus builds, Fable reviews Fable builds).

joshukraine/dotfiles · 75 tokens

todoist-cli

Manage Todoist tasks, projects, labels, filters, sections, comments, reminders, and workspaces via the td CLI. Use when the user wants to view, create, update, complete, or organize Todoist items, or mentions tasks, inbox, today, upcoming, projects, labels, or filters.

joshukraine/dotfiles · 68 tokens

autopilot

Carry a well-scoped GitHub issue through the full dev loop autonomously, stopping at a per-run tier boundary (PR-ready, or merge+deploy for small reversible changes).

joshukraine/dotfiles · 40 tokens

qa-handoff

Generate a hands-on QA testing guide as a self-contained HTML page — for Rails apps or static (Hugo) sites. --publish uploads the HTML to the project's configured QA host.

joshukraine/dotfiles · 41 tokens

walkthrough

Generate a hands-on browser walkthrough of a PR's user-facing changes to exercise before review; --publish posts the final version to the PR for QA.

joshukraine/dotfiles · 33 tokens

dustoff

Assess a project that's been dormant for months and produce a prioritized re-entry plan — lifecycle stage, what's stale or broken, and how far the project's tooling has drifted from current conventions — delegating every fix to the skill that owns it, and optionally capturing the plan as a tracking issue that survives…

joshukraine/dotfiles · 64 tokens