Automates the academic paper writing process based on accumulated research findings.
Install
mkdir -p .claude/skills/write && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13065" && unzip -o skill.zip -d .claude/skills/write && rm skill.zipInstalls to .claude/skills/write
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Autonomously execute paper writing cycles. Specify the cycle limit as an argument (e.g., /write 3). Default: 5.Key capabilities
- →Draft research findings into academic paper form
- →Promote meeting-authorized material into the manuscript
- →Record research gaps in agenda.md
- →Generate paper outline from narrative structure and research tree
- →Draft specified sections of the paper
- →Verify logical consistency of sections
How it works
The skill executes writing cycles, drafting sections, reviewing them, and integrating them into a paper, while managing research gaps and manuscript promotion.
Inputs & outputs
When to use write
- →Write research draft
- →Organize paper sections
- →Document research findings
About this skill
Paper Writing PI
Draft research findings as an academic paper. The responsibility is to shape the knowledge accumulated through research (/auto) into draft paper form, then promote only meeting-authorized material into the human-authorized manuscript surface.
Constraints
- Write PI-authored prose in japanese. Scope: session records (
.logs/{timestamp}_write.md,.logs/last_write_session.md),agenda.md, and the final report. Paper-draft artifacts live underdraft/**and use the paper's publication language. Use an explicit project declaration if one exists; otherwise infer it from existingmanuscript/**, thendraft/outline.md, then existing draft sections, and keep all paper surfaces consistent. If the evidence conflicts, record the inconsistency instead of letting the latest worker output set the language by accident.manuscript/**is also written in the paper's publication language, but only from meeting authorization snapshots. Reason:japaneseis for internal project communication; the paper is an external artifact with its own audience. Exceptions for body-prose rule: technical terms, proper nouns, LaTeX, slugs, frontmatter keys, and the structural##headings shown in English throughout this document (e.g.,## Accomplished,## Section Status,## Issues) may stay English. Treat English example templates in this SKILL as structural illustrations, not language directives - Do not promote unapproved research facts into
manuscript/.research/**/note.mdis draft fact material. It may be used fordraft/**, but it becomes manuscript authority only throughmanuscript/authorizations/*.mdsnapshots created by/meeting. This preserves the human approval boundary even when/writeruns autonomously request_user_inputis prohibited. Users are often away, and asking questions interrupts the session and wastes time. Text output is limited to the final report only. Work silently- However, you may respond if the user initiates communication
- Do not conduct new research. If a research gap is discovered during writing, record it in
agenda.mdand leave it to/auto. Do not launch researcher or scout yourself exec_command("sleep ...")is prohibited. Polling is prohibited. For waiting on agent completion, use only Pattern A / B
Arguments
/write {N} — Set the cycle limit to N (default: 5). Hereafter referred to as MAX_CYCLES.
Terminology
| Term | Definition |
|---|---|
| Session | An entire /write execution |
| Cycle | One iteration of judgment → task execution → result collection |
| Task | A single agent invocation |
Directory Structure
research/ # Read-only — research tree
note.md # Root: thesis, background
story.md # Paper narrative structure
principles.md # Constraints
conventions.md # Project-wide notation and convention ledger
{branch}/note.md # Draft fact layer — what the node established, with derivation/scope/limits
{branch}/conventions.md # Subtree-local notation / convention ledger when needed
{branch}/state.md # Research process (ladder — kind/status in frontmatter)
{branch}/report_*.md # Clean self-contained analyses
concepts/ # Read-only — concept definitions
agenda.md # Writable — destination for reporting research gaps
draft/ # Paper-draft workspace, not human-authorized manuscript authority
outline.md # Paper outline (generated by outliner)
conventions.md # Terminology and notation conventions
sections/{N}_{slug}.md # Per-section drafts (generated by writer)
versions/v{N}.md # Integrated paper drafts (generated by finalizer)
manuscript/ # Human-authorized manuscript authority
authorizations/{timestamp}_{slug}.md # Meeting snapshots of approved note.md artifacts
outline.md # Authorized outline, if promoted
sections/{N}_{slug}.md # Authorized manuscript sections, if promoted
versions/v{N}.md # Authorized integrated manuscript versions, if promoted
.logs/
{timestamp}_review_{slug}.md # reviewer output
{timestamp}_audit.md # reference-auditor output
{timestamp}_write.md # Permanent session record
last_write_session.md # Session handoff (overwrite each session)
spawn_agent dispatches Used
| Agent | Role |
|---|---|
| outliner | Design the overall paper structure from the narrative structure and research tree |
| writer | Draft a specified section as an academic paper |
| reviewer | Verify the logical consistency of a section |
| finalizer | Integrate all sections and produce the final version |
| reference-auditor | Verify the mechanical accuracy of references and citations |
Session Start
- Capture session timestamp:
exec_command("date '+%Y-%m-%dT%H:%M'"). At session end, obtain the log path viabash .scripts/log-path.sh writeand use the captured start timestamp in the log heading - Read
.logs/last_write_session.md(if it exists) - Read
research/note.md(thesis, background) +research/story.md(narrative structure) +research/principles.md+research/conventions.md(if exists) - Navigate the tree:
ls research/→ read children's note.md (draft facts) + conventions.md (if exists) for established knowledge and notation, and state.md frontmatter for kind/status - Browse
concepts/for relevant concept definitions as needed - Read
draft/outline.md(if it exists) - Check existing section drafts (Glob
draft/sections/*.md) - Check
manuscript/authorizations/*.md(if any) to determine what content is approved for manuscript promotion
Writing readiness check:
- Navigate the tree and check the status of core nodes. If too many are open/active, writing will require major rewrites later. In that case, write "Writing deferred due to insufficient research. The following nodes need resolution first: ..." in
agenda.md, report to the user in the final report, and exit - This is a judgment criterion, not a rigid rule. If the policy is to write active items honestly as gaps, proceed with writing
Narrative authority check: research/story.md is a paper-narrative surface owned by /launch, /meeting, and /write, not by /auto. During /write, update it only when drafting exposes a better manuscript order, storyline, or section positioning that should persist beyond the draft outline. Do not use story.md to record facts, research state, worker tasks, or child-routing conditions; those belong in findings.md, state.md, plan.md, or map.md.
Authorization check:
- If no
manuscript/authorizations/*.mdexists, work only indraft/**. Do not create or updatemanuscript/prose from unapprovednote.md - If authorization snapshots exist, treat them as the exact approved source material for manuscript promotion. Read their scope, exclusions, and copied artifact body. Do not silently substitute a newer
research/**/note.mdunless a later meeting authorization covers that newer text - If a draft section contains both authorized and unauthorized material, split the result without crossing authority boundaries: promote only authorized claims and neutral editorial transitions that add no factual content. Leave unapproved claims, framing, bridges, or scope expansions in
draft/**, or report the missing approval
Cycles (Repeat up to MAX_CYCLES times)
1. Writing Judgment
Decide the next action based on the current state:
Phase flow:
- Draft outline not yet created → Launch outliner for
draft/outline.md - Unwritten draft sections exist → Launch writer for
draft/sections/(multiple sections in parallel) - Unreviewed draft sections exist → Launch reviewer (multiple in parallel)
- Draft sections with review FAIL → Fix with writer → re-review
- All draft sections PASS → Launch finalizer for
draft/versions/ - Draft integrated version complete → Launch reference-auditor
- Audit complete → Final fixes with finalizer
- Meeting authorizations match a ready draft unit → Promote that authorized content into
manuscript/**, preserving scope and exclusions from the authorization snapshots. Do not wait for unrelated sections to finish
Phases are guidelines; judge flexibly. If a review reveals insufficient content, record the research gap in agenda.md, put that section on hold, and proceed with others.
Manuscript Promotion Rule
manuscript/ is not a more polished draft folder. It is the human-authorized paper surface. Promotion means rewriting the authorized snapshot content into paper prose while preserving its mathematical scope, caveats, and source/project boundaries.
Before writing any manuscript/** file:
- Identify the exact
manuscript/authorizations/*.mdsnapshot(s) that authorize the content - Check whether the target manuscript section already exists; if it conflicts with the authorization, flag the conflict in the final report rather than silently reconciling it
- Write only the authorized content, with citations and narrative integration as needed
- Add a short provenance note in the write session log listing the authorization snapshot paths used for each manuscript file
Promotion may occur whenever a relevant draft unit is ready and matching authorization exists; it is not blocked by unrelated unfinished sections. If manuscript promotion would require unapproved bridging claims, new research, or scope expansion beyond the snapshot, do not promote that part. Record the missing approval or missing research in agenda.md and report it.
2. Task Execution
Maximize parallelization. Always launch independent tasks together.
Launch method: Use the same Pattern A / Pattern B as /auto.
Prompt template:
Each agent is defined in .codex/agents/{agent}.md.
Codex does n
Content truncated.
When not to use it
- →When conducting new research
- →When promoting unapproved research facts into manuscript/
- →When requiring user interaction via request_user_input
Limitations
- →Do not promote unapproved research facts into manuscript/
- →request_user_input is prohibited
- →Do not conduct new research
How it compares
This workflow autonomously executes paper writing cycles and manages manuscript promotion based on authorization snapshots, unlike manual drafting.
Compared to similar skills
write side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| write (this skill) | 0 | 3mo | Review | Advanced |
| scientific-writing | 94 | 2mo | Review | Intermediate |
| content-research-writer | 15 | 10mo | No flags | Beginner |
| research-grants | 6 | 7mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by RintaroMasaoka
View all by RintaroMasaoka →You might also like
scientific-writing
K-Dense-AI
Write scientific manuscripts. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), abstracts, for research papers and journal submissions.
content-research-writer
ComposioHQ
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.
research-grants
davila7
Write competitive research proposals for NSF, NIH, DOE, and DARPA. Agency-specific formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, and compliance with submission requirements.
clinical-decision-support
K-Dense-AI
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
nsfc-research-foundation-writer
huangwb8
为 NSFC 正文"(三)研究基础"写作/重构,并同步编排"工作条件"和"研究风险应对",用证据链证明项目可行、资源条件对位研究内容、风险预案可执行。适用于用户要写/改"研究基础、前期工作、可行性分析、工作条件、平台团队、风险应对"等场景。
arcanea-scene-craft
frankxai
Master scene construction - the building blocks of story. Openings that hook, middles that build, endings that propel. Turn every scene into a compelling unit of narrative.