agentleFS
Nbill27Nbill27/academic-writing-skills/skills/edit/SKILL.md

edit

Skill4 starsChanged 2 days agoMITView on GitHub

Edit Indonesian academic prose and other scholarly writing while preserving facts, claims, citations, disciplinary terminology, and author voice. Supports correction, editing, rewriting, and drafting from user material.

16 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use daily-arxiv, exp-eval and 10 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.
  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • skyllwtSkill

    exp-pilot-eval

    Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.

    Also in 4 projects that use this

  • skyllwtSkill

    exp-pilot-run

    Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.

    Also in 4 projects that use this

  • phanghonghaoSkill

    poster

    HTML/CSS A4 海报生成。从沙龙/活动 Markdown 文件生成科技风 A4 海报 PDF/PNG。Use when user mentions: poster, 海报, 海报生成, make poster, generate poster, 活动海报, 沙龙海报.

    Also in 4 projects that use this

  • +6 more from Lambenthan
  • +1 more from skyllwt

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 4 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 14 edited versions we read keep these.

  • 4

    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:

    Read ../shared/workflow-contract.md before substantive work.

    line 12
  2. Very specific:

    Start from user-provided text.

    line 14
  3. Distinctive:

    When unclear, use the narrowest scope (Correction) and state that choice.

    line 25
  4. Distinctive:

    Read the text and determine the requested scope.

    line 29
  5. Very specific:

    Check applicable language rules (EYD V/KBBI for Indonesian) using references/eyd-kbbi.md.

    line 30
  6. Very specific:

    Check mechanical writing patterns in references/ai-patterns.md.

    line 31
  7. Very specific:

    Check references/keep-it.md to avoid damaging legitimate field conventions, technical terms, hedging, quotations, and author voice.

    line 32
  8. Distinctive:

    Check terminology and cross-section consistency.

    line 33
  9. Distinctive:

    Never change numbers, dates, names, direct quotations, source metadata, formulas, variable names, or citations without explicit verified …

    line 38

“Common” is measured: kept by at least 6 in 10 of the 14 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

Edit

Read ../shared/workflow-contract.md before substantive work. Reuse the current task's terminology list and completed institution profile where available. The institution profile is a template, not an official source.

Start from user-provided text. If no text exists, route to draft.

Editing scopes

ScopeMay changeMust preserve
CorrectionTypos, punctuation, spellingWording, facts, claims, structure, numbers, citations
EditingGrammar, clarity, flow, sentence structureFacts, numbers, claims, citations, terminology, author voice
RewritingSentence/paragraph order and wordingFacts, numbers, claims, citations; flag unsupported claims
WritingNew prose from user materialNo invented facts; missing/unverified items are marked

When unclear, use the narrowest scope (Correction) and state that choice. Ask one question only when scope materially affects the result.

Workflow

  1. Read the text and determine the requested scope.
  2. Check applicable language rules (EYD V/KBBI for Indonesian) using references/eyd-kbbi.md.
  3. Check mechanical writing patterns in references/ai-patterns.md. Patterns are signals, not proof of AI authorship or misconduct.
  4. Check references/keep-it.md to avoid damaging legitimate field conventions, technical terms, hedging, quotations, and author voice.
  5. Check terminology and cross-section consistency.
  6. Return revised text plus a change report with location, issue, and correction. Never rewrite silently.

Boundaries

Never change numbers, dates, names, direct quotations, source metadata, formulas, variable names, or citations without explicit verified basis. Never promise plagiarism/AI-detector scores, and never edit to evade detectors or conceal AI authorship. A pattern signal alone is not evidence of misconduct.

References

  • references/editing-scopes.md: scope boundaries.
  • references/eyd-kbbi.md: Indonesian language rules.
  • references/ai-patterns.md: patterns to improve clarity.
  • references/keep-it.md: legitimate conventions to preserve.

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.