agentleFS
Sign inStart free
KangDongGwonKangDongGwon/claude-skills/skills/paper-style/SKILL.md

paper-style

Skill0 starsChanged 6 months agoMITView on GitHub

Load the author's scientific writing style profile, or do a light AI-ism cleanup on a paragraph. Use when drafting, reviewing, or humanizing any paragraph for a scientific manuscript. Triggers - paper style, 저자 문체, style profile, 논문 스타일, humanize, 논문 humanize, AI 흔적 제거, paper humanize.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If override exists in cwd, read and merge (override wins on conflict).

    line 19
  2. Distinctive:

    Never change numbers, citation markers, chemical formulas, or any technical claim.

    line 36
  3. Distinctive:

    If a word on the strip list is load-bearing for the claim, leave it and flag.

    line 37
  4. Very specific:

    If more than 30% of the paragraph would need editing, STOP and return ESCALATE.

    line 38
  5. Very specific:

    If the paragraph is already clean, return it verbatim with NO_CHANGES.

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

paper-style

Two modes: (1) load profile for drafters, (2) light humanize for a last-pass AI-ism scrub.

Source: ~/.claude/paper-team/STYLE_PROFILE.md (author-global). Optional per-project override: <cwd>/.claude/paper-team/STYLE_PROFILE.override.md.

Mode 1. Load profile

Called by drafter agents before writing.

  1. Read ~/.claude/paper-team/STYLE_PROFILE.md.
  2. If override exists in cwd, read and merge (override wins on conflict).
  3. Return section 3.1 banned words, section 3.2 approved transitions, section 2 dials, section 12 checklist. Verbatim, no paraphrase.

Mode 2. Light humanize

Called by /paper-humanize. This is a light pass. Do NOT rewrite, do NOT inject voice, do NOT enforce the full STYLE_PROFILE checklist (that is the drafter's job). Only strip the AI-isms below.

Strip list (scientific-safe)

  • AI vocab: delve into, leverage, intricate, underscores, nuanced, tapestry, realm, in the realm of, it is worth noting, it should be noted, plays a crucial role, stands as a testament, navigating the complexities, comprehensive understanding, shed light on, pave the way.
  • Em dash overuse (Unicode U+2014): replace with comma, period, or parenthesis. Keep at most one per paragraph.
  • Rule of three: triple parallel constructions where all three items are near-synonyms. Cut to one.
  • "As shown in Fig. X" and "as can be seen" as sentence opener: move the figure reference into a parenthetical (Fig. X).
  • Rhetorical questions and mic-drop paragraph endings.

Hard rules

  • Never change numbers, citation markers, chemical formulas, or any technical claim.
  • If a word on the strip list is load-bearing for the claim, leave it and flag.
  • If more than 30% of the paragraph would need editing, STOP and return ESCALATE.
  • If the paragraph is already clean, return it verbatim with NO_CHANGES.

Output

## Cleaned text
<paragraph>

## Changes
- <one line per edit>

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.

Check your setup, free