agentsclimarketplace
Sign in

Paper workflow

Skill kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/Boom5426__Nature-Paper-Skills/skills/core/paper-workflow

Use when deciding which paper-related skill to use or how to sequence manuscript work under `/data/boom/Papers` from project setup through submission and rebuttal.From its SKILL.md

Install
npx -y skills add kenantang/codex-and-claude-skills --skill paper-workflow

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.0 KB, 599 tokens by cl100k_base, as published. Nobody here has run it

Paper Workflow

Overview

Use this skill as the routing map for paper work. It does not replace the specialized skills. It tells you which one to use next.

Default assumption: unless the user explicitly names a conference venue, the manuscript should follow the journal-oriented, Nature-style workflow.

When writing follows experiments or analysis performed across multiple sessions, freeze a compact handoff first: current paper story, supported findings, unresolved decisions, and the figure list that actually carries those findings.

Routing Map

Use:

  • paper-bootstrap when a project is new, messy, or missing a source of truth
  • nature-portfolio-playbook when the target is Nature, Nature Methods, Nature Biotechnology, or the venue fit among those journals is still unclear
  • scientific-writing when drafting or rewriting sections in prose
  • manuscript-optimizer when the paper's claim structure, evidence chain, terminology, or prose need revision
  • results-section-revision when the Results section is scientifically stable but the subsection flow, paragraph openings, or argument progression still feel jumpy
  • figure-planner when the main bottleneck is figure logic, panel roles, or legend sync
  • citation-verifier when bibliography hygiene or source verification is the bottleneck
  • submission-audit when the paper is near submission or resubmission and needs a preflight pass
  • rebuttal-response when reviewer comments exist and a response letter plus aligned manuscript edits are needed
  • conference-paper-writing only when the user explicitly wants a conference paper for venues such as NeurIPS, ICML, ICLR, ACL, AAAI, or COLM

Default Sequence

For most papers under /data/boom/Papers, prefer this order:

  1. paper-bootstrap
  2. nature-portfolio-playbook when venue fit or article type is uncertain
  3. Refresh notes/project_truth.md, notes/result_summary.md, and notes/paper_handoff.md after any major experimental or figure update
  4. scientific-writing or manuscript-optimizer
  5. figure-planner
  6. results-section-revision when Results is substantively right but narratively abrupt
  7. citation-verifier
  8. submission-audit
  9. rebuttal-response after external review

Common Mistakes

  • using conference-style writing skills by default for journal manuscripts
  • polishing sections before the active manuscript source of truth is clear
  • rewriting the manuscript from experiment memory instead of a current result_summary.md or paper_handoff.md
  • editing figure legends late without rechecking the Results text
  • postponing Nature Portfolio article-type or venue-fit decisions until after the paper is mostly rewritten
  • treating citation formatting as the same thing as citation verification
  • writing a response letter before deciding the underlying manuscript edits

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most automation workflows skills give in 599 tokens

Counted across 745 of the 1,008 authors here whose files we hold, read 2026-08-07

  • Write conventional commit messagesin 36 of 745, across 35 files
  • Delete branches after mergein 30 of 745, across 21 files
  • Make atomic commitsin 25 of 745, across 15 files
  • Write minimal code to pass testsin 22 of 745, across 10 files
  • Re-snapshot after navigation or DOM changesin 21 of 745, across 13 files
  • Use try-catch for error handlingin 20 of 745, across 8 files
  • Run tests before committingin 20 of 745, across 12 files
  • Write tests before implementationin 20 of 745, across 8 files
  • Configure branch protection rulesin 19 of 745, across 5 files
  • Explain the why in commit messagesin 19 of 745, across 9 files
  • Refactor code while tests remain greenin 19 of 745, across 6 files
  • Interact with elements using refsin 19 of 745, across 11 files

Said here and by no other author read

  • use specialized skills for specific tasks
  • assume journal-style workflow by default
  • freeze a compact handoff after multi-session work
  • use conference skills only when explicitly requested
  • refresh project notes after major updates
  • prefer the default sequence for most papers

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,149. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.