SkillAgentSearch skills...

acl-writing-style

Use when revising an ACL paper for computational-linguistics house style, covering task-first framing, linguistic examples tied to quantitative error analysis, scoping language claims to tested languages, LLM-era claim discipline, anonymous self-reference, Limitations prose, and compressing into the…

Install / Use

npx skills add brycewang-stanford/Awesome-Journal-Skills --skill acl-writing-style

Installs into whichever agent you are using.

About this skill
πŸ“„

SKILL.md

Installable skill definition

Quality Score

87/100

Supported Platforms

Universal

Our assessment of acl-writing-style

acl-writing-style scores 87/100 on our quality scale, 504th of 950 AI & Machine Learning skills we index.

Its SKILL.md is 5.6 KB long, well organised into 11 sections with 2 code examples: a solid amount of guidance for an agent.

With 1,158 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
26/30
Structure
18/20
Description
15/15
Adoption
13/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so acl-writing-style is actively maintained.
  • Our last check on 2026-11-02 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit β€” read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-04. Automated pattern scan on 2026-10-04. It catches known dangerous patterns, not every risk β€” read a skill before letting an agent act on it.

acl-writing-style compared with similar skills

All 4 of these similar skills score higher than acl-writing-style; compare them before choosing.

SkillScoreStarsUpdatedFormat
acl-writing-style (this skill)by brycewang-stanford871.2k2mo agoSKILL.md
claude-memby thedotmack100117.9ktodayCLAUDE.md
Understand-Anythingby Egonex-AI10093.0k2d agoCLAUDE.md
headroomby headroomlabs-ai10079.9ktodayCLAUDE.md
CowAgentby zhayujie10048.0ktodayCLAUDE.md

Frequently asked questions

How do I install acl-writing-style?
Run npx skills add brycewang-stanford/Awesome-Journal-Skills --skill acl-writing-style. The install tabs above show the steps for each supported agent.
Which AI agents does acl-writing-style work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is acl-writing-style safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is acl-writing-style still maintained?
The repository was last updated about 2 months ago, so acl-writing-style is actively maintained.

name: acl-writing-style description: Use when revising an ACL paper for computational-linguistics house style, covering task-first framing, linguistic examples tied to quantitative error analysis, scoping language claims to tested languages, LLM-era claim discipline, anonymous self-reference, Limitations prose, and compressing into the 8-page or 4-page ACL format.

ACL Writing Style

Use this on the manuscript itself. ACL reviewers are NLP specialists who read for whether the paper understands language as well as models; the style that survives them is concrete, example-grounded, and precisely scoped.

First-page contract

  • Open with the task or linguistic phenomenon, not the model family: what goes in, what comes out, why it is hard, and for whom.
  • State the contribution as a typed claim by paragraph two: new method, new resource, new analysis, or new finding β€” ACL reviews are calibrated per type.
  • Give one real example (input, desired output, failure of the status quo) on page one; abstract problem statements without an example read as vague at this venue.
  • Say what languages the paper covers in the abstract if the answer is not "English only" β€” and if it is, say that too.

Claim scoping in the LLM era

| Reflex phrasing | ACL-safe phrasing | |---|---| | "LLMs cannot do X" | "The five models tested fail X under these prompts" | | "Our method understands Y" | "Improves the Y benchmark by n points; error classes A, B shrink" | | "Works across languages" | "Evaluated on de/hi/sw/zh/ar; typological coverage discussed in Β§7" | | "Significantly better" | Reserve for tested significance; give the test and p-value or interval | | "State-of-the-art" | Scope to the exact setting, model scale, and date checked |

Reviewers increasingly ask whether a result is a property of the task, the model snapshot, or the prompt; write so each claim names which.

Examples and error analysis as prose

  • Every qualitative example must be attached to a number: how often the illustrated behavior occurs, in which slice, under which condition. Cherry-picked generations presented as evidence is a named reject pattern.
  • Use interlinear glosses or transliteration conventions correctly for non-English examples; sloppy linguistics costs credibility with exactly the reviewers who like the paper's topic.
  • Name error categories functionally ("negation-scope errors") rather than narratively ("the model gets confused").

Anonymity-compatible voice

  • Write self-reference in third person: "Smith (2024) introduced X," never "In our previous work." Keep it in place until camera-ready.
  • Do not cite "anonymous (under review)" material that reviewers cannot read; ARR bars relying on documents unavailable to them.
  • Acknowledgements, funding, and AI-assistance credits are omitted at submission and added at camera-ready.

Compression into 8 (or 4) pages

  • The short-paper form is a single sharp point with one strong experiment β€” do not shrink a long paper into four pages; re-argue it.
  • Push prompt dumps, per-language tables, and hyperparameter grids to the appendix; keep one summary row of each in the body (see acl-supplementary).
  • Kill the related-work-as-inventory section; two paragraphs of positioned contrast beat a page of citations (see acl-related-work).
  • Figures earn their space only when they carry an argument β€” pipeline diagrams restating the text are the first cut.

Limitations and ethics prose

  • Write Limitations as the referee brief against yourself: scope, data coverage, model dependence, evaluation validity. Specificity here is protected β€” ACL instructs reviewers not to penalize honest limitations.
  • The optional ethics statement is for real stakes: human data, dual use, representational harm. A boilerplate ethics paragraph is worse than none.

Micro-edit pass

weak:   "We leverage powerful LLMs to achieve impressive gains."
strong: "Reranking with a 7B model cuts negation-scope errors from
         31% to 12% of sampled failures (Table 4)."

weak:   "Performance is good across all settings."
strong: "Gains hold on 4 of 5 languages; Swahili degrades (-1.2 F1),
         which Β§7 traces to tokenizer fragmentation."

Terminology and notation discipline

  • Pick one name per concept and hold it: a system called "our reranker," "the verifier," and "the LLM judge" in three sections reads as three systems to a tired reviewer.
  • Define task-specific terms at first use, even standard-seeming ones β€” "hallucination," "faithfulness," and "robustness" each have three incompatible literatures behind them.
  • Dataset names get their citation at first mention and exact split names thereafter ("XNLI dev-matched," not "the dev set").
  • Numbers in prose match tables to the decimal; reviewers diff them.
  • Language codes: introduce once (ISO 639), then use consistently in tables, figures, and prose alike.

Section-level failure smells

  • An introduction with no example β†’ underspecified task (fix first).
  • A method section narrating engineering chronology ("we first tried...") β†’ rewrite as design with rationale.
  • A results section that re-reads the table aloud β†’ replace with claims the table supports plus pointers into it.
  • A conclusion introducing new claims β†’ move them into results or delete; ACL reviewers treat conclusions as summaries under oath.

Output format

[Style diagnosis] task-first / model-first / survey-ish / underspecified
[First-page fix] <one concrete rewrite>
[Overclaim list] <claim -> scoped version>
[Example-evidence gaps] <anecdotes lacking counts>
[Compression plan] <cut / move / merge>

Related Skills

View on GitHub
GitHub Stars1.2k
CategoryAI
Updated2mo ago
Forks153

Languages

Stata

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit β€” see the Safety scan above for what the skill file itself contains.

No cautions
acl-writing-style β€” Universal Skill: Install & Safety Check | SkillAgent