agentleFS
a-attiaa-attia/scicomp-research-skills/skills/research-paper-writing/SKILL.md

research-paper-writing

Skill13 starsChanged 33 days agoMITView on GitHub

Improve academic paper writing quality for ML/CV/NLP-style papers with clear section structure, paragraph flow, and reviewer-facing presentation. Use when drafting or revising Abstract, Introduction, Related Work, Method, Experiments, or Conclusion; polishing figures/tables; checking claim-support alignment; or performing self-review before submission.

29 other projects use a version of this, 9 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use frontend-design, skill-creator and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • BlockSkill

    frontend-design

    Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

    Also in 6 projects that use this

  • SentrySkill

    skill-creator

    Create new agent skills following the Agent Skills specification. Use when asked to "create a skill", "add a new skill", "write a skill", "make a skill", "build a skill", or scaffold a new skill with SKILL.md. Guides through requirements, writing, registration, and verification.

    Also in 4 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 3 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

28 rules. 0 are common, 23 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 27 edited versions we read keep these.

  • 23

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill to rewrite a research paper into a reviewer-friendly, high-clarity draft.

    line 14
  2. Very specific:

    Use section-specific guidance in references/.

    line 20
  3. Distinctive:

    Run reverse outlining after writing each section.

    line 22
  4. Distinctive:

    Check every major claim in Abstract/Introduction against experimental evidence.

    line 23
  5. Very specific:

    Run final-paper adversarial review with references/paper-review.md.

    line 24
  6. Distinctive:

    Keep one paragraph for one message only.

    line 28
  7. Distinctive:

    Treat visual quality as core content, not decoration.

    line 33
  8. Distinctive:

    Use a clean teaser and pipeline figure.

    line 34
  9. Distinctive:

    Use readable, minimal-ink tables.

    line 35
  10. Distinctive:

    Keep formatting consistent and tidy.

    line 36
  11. Distinctive:

    Use this quick test whenever the user asks whether a paragraph "flows" or is clear.

    line 40
  12. Distinctive:

    Read as an external reader:

    line 42
  13. Distinctive:

    Run reverse outlining for the current section:

    line 47
  14. Distinctive:

    Write down thesis/main claim.

    line 48
  15. Distinctive:

    Write down each paragraph topic sentence.

    line 49
  16. Distinctive:

    Write down the evidence/explanation points under each paragraph.

    line 50
  17. Distinctive:

    Check mapping: topic sentence -> thesis, and evidence -> topic sentence.

    line 51
  18. Distinctive:

    If flow is still weak, add temporary section headers and explicit transition phrases during revision, then remove unnecessary headers …

    line 53
  19. Very specific:

    Use references/paper-review.md for the full checklist and workflow.

    line 75
  20. Distinctive:

    Add an end-of-draft self-review question list in five dimensions:

    line 77
  21. Distinctive:

    Treat claim-evidence alignment as a hard constraint, especially for Abstract and Introduction.

    line 83
  22. Distinctive:

    Avoid writing style that looks like incremental patching of a naive baseline.

    line 91
  23. Distinctive:

    Keep terminology stable across the full paper.

    line 92
  24. Distinctive:

    If a claim cannot be supported by results, weaken or remove the claim.

    line 93
  25. Distinctive:

    Before finalizing, append and answer a five-dimension self-review question list, then revise the paper based on unresolved items.

    line 94
  26. Very specific:

    Do not load all section references (Introduction/Abstract/Related Work/Method/Experiments/Conclusion) at once.

    line 95
  27. Distinctive:

    When asked to rewrite or draft sections, return:

    line 99
  28. Distinctive:

    When upstream evolves the references files, we may selectively cherry-pick changes (per ATTRIBUTION.md "Pulling updates from upstream").

    line 163

“Common” is measured: kept by at least 6 in 10 of the 27 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Research Paper Writing

Overview

Use this skill to rewrite a research paper into a reviewer-friendly, high-clarity draft. Prioritize first-impression quality (figures/tables/layout), logical flow, and evidence-backed claims.

Core Workflow

  1. Clarify the paper story before sentence-level edits.
  2. Use section-specific guidance in references/.
  3. Rewrite paragraph-by-paragraph with one message per paragraph.
  4. Run reverse outlining after writing each section.
  5. Check every major claim in Abstract/Introduction against experimental evidence.
  6. Run final-paper adversarial review with references/paper-review.md.

Global Principles

  1. Keep one paragraph for one message only.
  2. State the paragraph message in the first sentence.
  3. Make nouns self-contained; define new terms before reusing them.
  4. Maintain sentence-to-sentence flow (cause, contrast, consequence, or refinement).
  5. Iterate with adversarial self-review: read as a skeptical reviewer.
  6. Treat visual quality as core content, not decoration.
  7. Use a clean teaser and pipeline figure.
  8. Use readable, minimal-ink tables.
  9. Keep formatting consistent and tidy.

Paragraph Clarity Check (Important)

Use this quick test whenever the user asks whether a paragraph "flows" or is clear.

  1. Read as an external reader:
    • Does this paragraph have one explicit message?
    • Does the first sentence state what this paragraph will do?
    • Are all key nouns/terms readable without hidden context?
    • Does each sentence connect to the previous one with a clear relation (cause, contrast, consequence, refinement, example)?
  2. Run reverse outlining for the current section:
    • Write down thesis/main claim.
    • Write down each paragraph topic sentence.
    • Write down the evidence/explanation points under each paragraph.
    • Check mapping: topic sentence -> thesis, and evidence -> topic sentence.
    • Revise or remove any paragraph that cannot be mapped cleanly.
  3. If flow is still weak, add temporary section headers and explicit transition phrases during revision, then remove unnecessary headers before finalizing.

Source reference for this check:

  • references/does-my-writing-flow-source.md

Section Guides

Load only the needed section file:

  • Introduction: references/introduction.md
  • Abstract: references/abstract.md
  • Related Work: references/related-work.md
  • Method: references/method.md
  • Experiments: references/experiments.md
  • Conclusion: references/conclusion.md
  • Paper review (Paper Review): references/paper-review.md
  • Paragraph clarity source: references/does-my-writing-flow-source.md
  • Example bank index: references/examples/index.md

Paper Review Core Points

Use references/paper-review.md for the full checklist and workflow.

  1. Add an end-of-draft self-review question list in five dimensions:
    • contribution,
    • writing clarity,
    • experimental strength,
    • evaluation completeness,
    • method design soundness.
  2. Treat claim-evidence alignment as a hard constraint, especially for Abstract and Introduction.
  3. Perform adversarial writing: review as a skeptical reviewer and resolve every high-risk question.
  4. Revise until major rejection risks are explicitly addressed.

Execution Rules

  1. Build a mini-outline before drafting prose.
  2. For each subsection, explicitly include motivation, design, and technical advantage when applicable.
  3. Avoid writing style that looks like incremental patching of a naive baseline.
  4. Keep terminology stable across the full paper.
  5. If a claim cannot be supported by results, weaken or remove the claim.
  6. Before finalizing, append and answer a five-dimension self-review question list, then revise the paper based on unresolved items.
  7. Do not load all section references (Introduction/Abstract/Related Work/Method/Experiments/Conclusion) at once; load only the specific section guide needed for the current edit target.

Output Contract

When asked to rewrite or draft sections, return:

  1. A compact section outline (3-7 bullets).
  2. Revised paragraphs with explicit paragraph roles (opening/challenge/method/advantage/evidence/limitation).
  3. A short self-review checklist covering clarity, flow, terminology consistency, unsupported claims, and missing evidence.
  4. A claim-evidence map for each major claim in the revised text using Claim: ... | Evidence: ... | Status: supported/needs evidence.

Adjacent human-facing documents

This skill governs the published paper draft itself (Abstract, Introduction, Related Work, Method, Experiments, Conclusion). When the work also requires producing or revising meta-documents that support the paper -- for example:

  • updates to the project's PLAN.md,
  • per-section research notes (notes/section_<N>.md),
  • per-component implementation plans (notes/impl_<component>.md),
  • the project's README.md,
  • a reviewer-response draft,

those documents have a different audience (the user, co-authors, reviewers) and a different style budget than the paper itself. Load ~/.scicomp-research-skills/skills/human-facing-doc-authoring/SKILL.md for the conventions and per-doc-type structural skeletons. Use BOTH skills together: paper-writing for the paper draft, human-facing for any meta-doc.

Resource discipline for paper-writing sessions

A paper-writing session typically iterates across multiple sections, re-reads many survey notes, may re-grep the paper draft repeatedly, and often spans multiple sessions before a section is finalised. Whenever the session is going to be heavy (more than ~5 file reads, multiple section drafts, or a span across multiple sittings), load ~/.scicomp-research-skills/skills/agent-resource-discipline/SKILL.md at session start. In particular:

  • agent-resource-discipline/references/persistent-memory.md -- the first-/last-action protocol that updates notes/section_<N>.md and PLAN.md status fields so the next session resumes cheaply.
  • agent-resource-discipline/references/context-window-budget.md -- the rule that this skill's Execution Rule #7 ("do not load all section references at once") generalises to: do not load all survey notes at once, do not load the full .txt extraction of every cited paper -- target-grep instead.

Both skills compose: paper-writing for what to write; agent-resource- discipline for what to load while writing.


Note on this skill's references/ files

The references files under references/ (abstract.md, conclusion.md, experiments.md, introduction.md, method.md, paper-review.md, related-work.md, examples/) are vendored from the upstream Master-cai/Research-Paper-Writing-Skills repository at commit 9ee5edd (see ATTRIBUTION.md). They are deliberately preserved without per-file date-stamp footers -- our universal "every plan-of-record-style document ends with a date-stamp footer" convention (root AGENTS.md Section 6) does not apply to upstream-imported reference content; modifying the upstream files to add footers would create false revision history.

When upstream evolves the references files, we may selectively cherry-pick changes (per ATTRIBUTION.md "Pulling updates from upstream"). When we substantially modify a reference file, we will add a *Revised YYYY-MM-DD by A. Attia: <note>.* footer to that specific file at that point. Until then the upstream provenance is authoritative.


Revised 2026-05-13: added "Adjacent human-facing documents" section pointing at the human-facing-doc-authoring skill for meta-docs (PLAN.md, section/impl notes, README, rebuttal) that this skill does not directly govern. Revised 2026-05-13: added "Resource discipline for paper-writing sessions" section pointing at the agent-resource-discipline skill for the cross-cutting context-window / persistent-memory protocol that complements this skill's Execution Rule #7. Revised 2026-05-14 (post-fresh-audit): documented the deliberate exception from the universal date-stamp-footer convention for upstream-vendored references files (the eight files under references/ that were imported from Master-cai upstream and have not been substantially modified).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.