What is draft-section?

A writing tool for drafting one part of an academic research paper, such as its introduction, methods, results, or abstract. It follows the project's chosen writing style and uses the project's existing materials.

Use it to write or revise a named paper section using the project's notes, references, related sections, tables, figures, and analysis output.

It reduces the risk of inconsistent writing, incorrect numbers, or made-up citations. It also avoids drafting from unstable analysis results that may later change.

draft-section — Skill by matthewdigiuseppe

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.

agentmods

npx agentmods add skills/matthewdigiuseppe/mstack/draft-section

Any agent

npx skills add matthewdigiuseppe/MStack --skill draft-section

Clone the repo

git clone --depth 1 https://github.com/matthewdigiuseppe/MStack

Made for: Claude Code, Codex.

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,201 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.

Model	Per session	Once invoked
Fable 5	$0.00061	$0.01201
Opus 5	$0.00030	$0.00600
Sonnet 5	$0.00012	$0.00240
Haiku 4.5	$0.00006	$0.00120

Measured 2d ago against content hash a55111ab6593, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

draft-section 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 2d 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.

skills/draft-section/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/mstack:draft-section

Stage: write Voice: writer (anchored to the skill named in .mstack/config.yaml → voice.writing_style)

When to invoke

After analysis is stable (results in output/tables/ and output/figures/ are not changing) and the paper has a target journal in .mstack/config.yaml. Drafting before results lock in produces prose that has to be rewritten.

Argument

$ARGUMENTS is the section name. One of: intro, theory, data, methods, results, discussion, abstract.

If not supplied or unrecognized, list the recognized names and stop.

Procedure

Load context.
- Read .mstack/config.yaml for title, target journals, status.
- Read .mstack/learnings.jsonl for paper-specific conventions (variable names, design choices, framing).
- Read paper/refs.bib to know what citations are available — never invent BibTeX entries.
- Read sibling sections in paper/sections/ so voice and references stay consistent.
- For methods/results: read code/02-analyze.R, output/tables/*, output/figures/*. The numbers in your prose must match the tables on disk.
Invoke the writing-style skill.
- Read voice.writing_style from .mstack/config.yaml.
- If set, invoke that skill for tone, sentence rhythm, and vocabulary.
- If unset or empty, write in a clean, generic academic voice: short sentences, active verbs where possible, no hedge-stuffing, no thesaurus reaches. Tell the user once that no voice.writing_style is configured and they can set one in .mstack/config.yaml.

Draft the section with the section-specific bar:

Section	Quality bar
`intro`	Hook, puzzle, contribution, roadmap. The puzzle must survive a "so what?" attack in two sentences.
`theory`	Mechanism in one sentence. DAG or analog in prose. Scope conditions stated. Hypotheses numbered (H1, H2…).
`data`	Sources, vintage, unit of analysis, sample restrictions, missingness. Every claim cites the codebook.
`methods`	Specification in equation form. Identifying assumption stated. Standard errors justified.
`results`	One claim per table/figure. Numbers match `output/`. No "highly significant" — give the coefficient and CI.
`discussion`	What the result is and is not. Scope, threats, alternative explanations addressed. Implications proportional to evidence.
`abstract`	One paragraph: question, design, finding, contribution. ≤250 words unless journal demands less.

Read the full file on GitHub · 83 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.

2d ago First seen · 83 lines · 61 tokens per session scan A a55111ab6593

Subscribe to this mod's changes

draft-section is a skill published in the GitHub repository matthewdigiuseppe/MStack (14 stars, last pushed 5d ago), licensed MIT. It adds 61 tokens to every session and 1,201 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 2026-08-30.

Productivity Research Writing and docs

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

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens