write
Use when a quest has enough evidence to draft or refine a paper, report, or research summary without inventing missing support.
Best for Research documentationWorks with GitHub
⌘source
- author
@ResearAI- language
- TypeScript
★2.3kstars
245forks
Apr 19, 2026
✦overview.md
Key Features
- ·Turns accepted evidence into drafts or reports
- ·Maintains citation integrity and evidence boundaries
- ·Includes storyline development and visual proofing
- ·Operates on a dedicated paper branch separate from source
- ·Focuses on stable narrative testing over polish
Use Cases
- →Drafting research papers from collected evidence
- →Creating technical reports based on experimental results
- →Summarizing findings into documentation bundles
Best for
- ✓Research documentation
- ✓Evidence-based reporting
Not ideal for
- !Creative writing
- !Marketing copy
FAQs
name
write
description
Use when a quest has enough evidence to draft or refine a paper, report, or research summary without inventing missing support.
skill_role:stage
Write
Use this skill to turn accepted evidence into a faithful draft, report, or paper bundle. The goal is to produce the lightest honest writing artifact the current evidence can really support, not to polish prose past the evidence boundary. This skill intentionally absorbs the strongest old DeepScientist writing discipline, including:
- evidence assembly
- storyline and outline
- drafting
- citation integrity
- figures and tables
- self-review
- visual proofing
- submission gate
Interaction discipline
- Follow the shared interaction contract injected by the system prompt.
- Keep writing updates brief unless the paper contract, evidence boundary, blocker state, or next route changed materially.
Planning note
Use quest/workspace planning files only when they help control a non-trivial paper line instead of becoming another reason to delay drafting or route-back decisions.
Stage purpose
The write stage does not exist to make the quest sound finished. It exists to test whether the current evidence can support a stable narrative.
Writing should happen on a dedicated paper/* branch/worktree derived from the source main-experiment run/* branch.
$install
1-click copynpx skills add ResearAI/DeepScientist --skill writeSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
4/ 5
very goodClear and well structured, with only minor parts that might need a second read.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
3/ 5
mediumPartially actionable with several concrete steps, but still missing important details.