A writing workflow for turning established research evidence into a paper, report, or research summary. It keeps claims connected to supporting results, figures, and citations.

Use it to draft or revise sections, check that claims match evidence, prepare a paper bundle, or improve an existing conference submission.

It prevents unsupported statements and avoids polishing a draft when the underlying evidence is incomplete or unstable.

write — Skill by ResearAI

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/researai/deepscientist/write

Any agent

npx skills add ResearAI/DeepScientist --skill write

Clone the repo

git clone --depth 1 https://github.com/ResearAI/DeepScientist

Made for: Claude Code, Codex.

Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 11,060 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	$0.00027	$0.11060
Opus 5	$0.00014	$0.05530
Sonnet 5	$0.00005	$0.02212
Haiku 4.5	$0.00003	$0.01106

Measured 3d ago against content hash e5f6b28b8a73, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

write 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.

src/skills/write/SKILL.md · 814 lines

How it starts

The opening of the file, as written. The whole thing — 814 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write

Match Signals

Use when an accepted baseline and at least one meaningful result already exist, and the main blocker is now drafting, revising, bundling, or tightening a paper/report.
Strong triggers: draft a paper/report, revise a section, synchronize claim-evidence support, prepare a paper bundle, or upgrade an existing draft into a stronger conference submission.
If the task is specifically "upgrade an existing draft toward top-conference / oral quality", use the Draft To Top Conference Oral section below.
Do not use when the evidence base is still weak or unstable, the main need is new experiments / baselines / ideation, or the request is only literature search.

One-Sentence Summary

Refresh the paper contract first, then draft section-by-section from durable evidence; if evidence, figures, or citations are not ready, repair or route back instead of writing around the gap.

Pre-write Revision Strategy Gate

Before editing a manuscript, first produce a concrete revision strategy from the current evidence state. Do not begin polishing prose until the strategy separates:

evidence gaps: require new analysis, rerun, or claim downgrade
manuscript-mapping gaps: completed results missing from main text, table, figure, or appendix
unsupported writing: claims present in the draft without durable result artifacts
narrative / positioning gaps: weak framing, novelty boundary, contribution logic
citation gaps: too few or weak references for the claimed scope
metadata drift: matrix, ledger, outline, figures, tables, and manuscript disagree

For each issue, choose exactly one action:

run or request analysis
downgrade or remove the claim
add result to main text
move result to appendix with a clear bridge
add or repair a table/figure
add verified citations
repair the paper contract before writing
route to review / decision instead of writing

Never make an unsupported claim sound more convincing. If evidence is missing, either obtain evidence, narrow the claim, or mark the blocker.

Read the full file on GitHub · 814 lines

Files

What ships with it

57 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.

3d ago First seen · 814 lines · 27 tokens per session scan A e5f6b28b8a73

Subscribe to this mod's changes

write is a skill published in the GitHub repository ResearAI/DeepScientist (3,310 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 11,060 once invoked, about $0.0001 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.

Research Writing and docs

systematic-debugging

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

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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