New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Writing Style

by OpenLAIR in OpenLAIR/dr-claw

Apply the 21 prose rules from "The Elements of Agent Style" — 12 canonical rules (Strunk, Orwell, Pinker) plus 9 field-observed AI-output patterns.

CC-BY-4.0Auto-check passedWriting & Content

Install Writing Style

skills CLI
$ npx skills add OpenLAIR/dr-claw --skill writing-style -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install OpenLAIR/dr-claw writing-style --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/OpenLAIR/dr-claw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/writing-style .claude/skills/writing-style && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
writing-style
GitHub stars
1.2k
Token cost
~2.4k tokens
SKILL.md length
1,335 words
Files
1
Skills in repo
36
Repo updated
First seen
Licence
CC-BY-4.0

At a glance

Apply the 21 prose rules from "The Elements of Agent Style" — 12 canonical rules (Strunk, Orwell, Pinker) plus 9 field-observed AI-output patterns.

  • Works in 4 steps: Read $ARGUMENTS. If it contains a draft… → Scan the draft against all 21 rules.… → Revise. Return the revised draft… → …
  • The user says writing style
  • SKILL.md covers Escape hatch, Canonical rules…, Field-observed rules… and Workflow when invoked directly
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Writing Style is an agent skill from OpenLAIR/dr-claw. Apply the 21 prose rules from "The Elements of Agent Style" — 12 canonical rules (Strunk, Orwell, Pinker) plus 9 field-observed AI-output patterns. Use when the user says "writing style", "agent style", "apply style rules", "style review", "check my prose", or explicitly invokes /writing-style with an optional draft to revise. For detecting and rewriting AI-specific tells (symbolism inflation, promotional vocabulary, rule of three), prefer /inno-humanizer.

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Writing & Content, covering Brand voice and tone, Humanizing AI text and Plain language and style rules. The repository describes itself as: A Super AI Lab with massive AI Doctors as Assistants. Best IDE for Research via AI Power. The licence is CC-BY-4.0.

When your agent uses it

  • The user says writing style
  • Apply style rules
  • Explicitly invokes /writing-style with an optional draft to revise

Example prompts

  • “The Elements of Agent Style”
  • “writing style”
  • “agent style”
  • “/writing-style”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Read $ARGUMENTS. If it contains a draft (more than a few words of prose), treat that as the text to revise. If it contains a scope…
  2. Scan the draft against all 21 rules. Flag the two or three rules with the highest severity violations.
  3. Revise. Return the revised draft followed by a short change log (one line per major edit, naming the rule ID).
  4. Do not invent content. If the draft is thin, improve clarity and structure, but do not fabricate facts or citations (RULE-H).

What it can do on your machine

Read from SKILL.md and the folder at commit d51b64e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Writing Style loads about 2.4k tokens when it runs. Until then it costs about 119 tokens; SKILL.md has 1,335 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~119
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from OpenLAIR/dr-claw at commit d51b64e, republished under its CC-BY-4.0 licence (© OpenLAIR). 1,335 words, ~2,405 tokens.

Download SKILL.mdSave it as .claude/skills/writing-style/SKILL.md (or your agent's skills folder).
name
writing-style
description
Apply the 21 prose rules from "The Elements of Agent Style" — 12 canonical rules (Strunk, Orwell, Pinker) plus 9 field-observed AI-output patterns. Use when the user says "writing style", "agent style", "apply style rules", "style review", "check my prose", or explicitly invokes /writing-style with an optional draft to revise. For detecting and rewriting AI-specific tells (symbolism inflation, promotional vocabulary, rule of three), prefer /inno-humanizer.
argument-hint
[draft-or-scope]
license
CC-BY-4.0
metadata.author
yzhao062/agent-style
metadata.upstream
https://github.com/yzhao062/agent-style
metadata.pinned-commit
6633397fe213944b0ffbf2b66c5fe827773cd001
metadata.version
0.3.1

Writing Style Rules

Based on The Elements of Agent Style by yzhao062 (CC BY 4.0). Source: https://github.com/yzhao062/agent-style

Follow these rules when producing any prose (explanations, summaries, documentation, commit messages, paper text, release notes, postmortems, design docs). These rules shape natural-language output only; they do not change code behavior.

If $ARGUMENTS contains a draft, revise that draft against these rules and return the revised text with a brief note explaining the top two or three changes. Otherwise, apply the rules to the rest of this conversation's prose output from this point forward until the user says otherwise.

Escape hatch

"Break any of these rules sooner than say anything outright barbarous." — George Orwell, 1946

Rules are guides to clarity, not ends in themselves. When a rule fights the sentence, drop the rule.

Canonical rules (literature-backed)

RULE-01 — Do not assume the reader shares your tacit knowledge

Do not use technical terms or acronyms that have not been established for the reader. Name the intended reader (adjacent-field graduate student, junior engineer, on-call engineer, cross-panel reviewer). If that reader would pause to infer what a term means, define it or rewrite around it.

RULE-02 — Do not use passive voice when the agent matters

Do not write "X was done by Y" when "Y did X" fits. Active voice names the agent, shortens the sentence, and makes the verb carry the action. Passive is correct only when the agent is genuinely unknown or irrelevant (scientific attribution, observation of phenomena).

RULE-03 — Do not use abstract language when concrete terms exist

Replace category words ("factors", "aspects", "issues", "elements") with the specific items they refer to. "The system has performance issues" says nothing; "the checkout endpoint p95 latency rose from 120ms to 450ms at 14:00 UTC" names what, when, and how much.

RULE-04 — Do not include needless words

"In order to" is "to"; "due to the fact that" is "because"; "at this point in time" is "now"; "it is important to note that" is (delete and state the fact); "may potentially" and "could possibly" are redundant hedges.

RULE-05 — Do not use dying metaphors or prefabricated phrases

Do not use metaphors, similes, or phrases you have seen often in print. If a phrase feels off-the-shelf — ready-made framing for work-in-general rather than for this work — restate in plain technical terms with specific numbers or a specific mechanism, or delete the sentence.

RULE-06 — Do not use avoidable jargon

Do not use "leverage" where "use" fits, "utilize" where "use" fits, "methodology" where "method" fits, or "functionality" where "function" or "feature" fits. Technical jargon with distinct meaning ("backpropagation", "quantization") is fine. Corporate-speak jargon is substitutable by shorter everyday words without loss of meaning.

RULE-07 — Use affirmative form for affirmative claims

Replace "not important" with "trivial"; "did not remember" with "forgot"; "did not pay attention to" with "ignored"; "is not often" with "rarely"; "does not succeed" with "fails". Prefer one affirmative word over two negating words.

RULE-08 — Do not overstate or understate claims relative to evidence

Calibrate verbs to evidence: experimental results "suggest" or "show"; theoretical derivations "imply" or "prove"; user reports "indicate"; benchmarks "measure". Use "best" only when you have compared against the strongest alternative; use "only" when you have ruled out alternatives.

RULE-09 — Express coordinate ideas in similar form (parallel structure)

Write coordinate ideas in the same grammatical form. In a list of three, if item 1 is a noun phrase, items 2 and 3 are also noun phrases; if item 1 is a verb-initial clause, items 2 and 3 are also verb-initial clauses. Applies to bullet lists, parallel predicates, and compound sentences.

Keep subject close to verb, verb close to object, and modifier close to modified. If the gap between subject and verb exceeds roughly 8 words, split the sentence or move the intervening clause.

RULE-11 — Place new information in the stress position at sentence end

End sentences with the information you want the reader to remember. The beginning of a sentence connects to what came before; the end is where new or important information lands with maximum emphasis. Applies especially to result sentences, conclusions, and root-cause lines.

RULE-12 — Break long sentences; vary length

Split any sentence over 30 words into two or more. Vary sentence length across a paragraph — short sentences land points, long sentences carry qualification. A paragraph of five 25-word sentences reads less well than the same content in sentences of 8, 18, 22, 14, 30 words.

Field-observed rules (AI-output patterns)

RULE-A — Do not convert prose into bullet points unless the content is a genuine list

Keep prose in paragraphs when ideas connect by cause-and-effect, argument, or narrative. Use bullets only when items are genuinely parallel enumerations (API endpoints, config options, checklist steps). Do not force 3-item lists when 2 items or a sentence fit.

Show full SKILL.md (544 more words)Show less
RULE-B — Do not use em or en dashes as casual sentence punctuation

Prefer commas for appositives, semicolons for linked independent clauses, colons for expansions, and parentheses for asides. En dashes remain correct in numeric ranges (1-3, 2020-2026) and paired names. Normal hyphens in compound words (command-line, zero-shot) are not dashes.

RULE-C — Do not start consecutive sentences with the same word or phrase

Do not open two or more consecutive sentences with the same word. Vary the opener: topic-fronted versus subject-fronted versus connective. Pronoun subjects ("It", "We", "They") are the most common offenders in LLM output.

RULE-D — Do not overuse transition words

Do not open sentences with "Additionally", "Furthermore", "Moreover", "In addition", "What's more", or "Notably" unless the sentence genuinely builds on the preceding clause in a way that a period alone would not convey. In most cases, a period ends the prior sentence and the next sentence makes the connection by content alone.

RULE-E — Do not close every paragraph with a summary sentence

Do not end every paragraph with a sentence that restates the paragraph's point ("In summary,", "Thus,", "Overall,", "In conclusion,"). Summary closers are correct for the final paragraph of a piece. For body paragraphs, if the closer can be deleted without losing the point, delete it.

RULE-F — Use consistent terms; do not redefine abbreviations mid-document

Once you introduce a term or abbreviation, keep using it. Do not alternate "large language model", "LLM", "language model", "foundation model" as synonyms for the same thing. Do not redefine an abbreviation later in the document.

RULE-G — Use title case for section and subsection headings

Capitalize the first word, the last word, and all major words (nouns, verbs, adjectives, adverbs, pronouns) in headings. Lowercase articles (a, an, the), coordinating conjunctions (and, but, or), and short prepositions (of, in, on, to, for, by, at, with).

RULE-H — Support factual claims with citation or concrete evidence

When a sentence asserts a factual claim that warrants attribution, name the specific source (author and year, benchmark, dataset, observed experiment). Do not write handwavy attributions ("prior work shows", "it is well known that", "recent studies suggest") without naming the specific work. Never invent a citation.

RULE-I — Prefer full forms over contractions in technical prose

In formal technical prose (research papers, grant proposals, API specifications), prefer "it is" over "it's", "does not" over "doesn't", "cannot" over "can't". Contractions are acceptable in informal registers (blog posts, release notes, commit messages). Pick the register and hold it within the document.

Workflow when invoked directly

  1. Read $ARGUMENTS. If it contains a draft (more than a few words of prose), treat that as the text to revise. If it contains a scope directive like "apply to the next reply" or "apply for this session", switch to continuous-application mode.
  2. Scan the draft against all 21 rules. Flag the two or three rules with the highest severity violations.
  3. Revise. Return the revised draft followed by a short change log (one line per major edit, naming the rule ID).
  4. Do not invent content. If the draft is thin, improve clarity and structure, but do not fabricate facts or citations (RULE-H).

If $ARGUMENTS is empty, acknowledge that the rules are now active for the remainder of the conversation and wait for the next user message to apply them.

© OpenLAIR, CC-BY-4.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/writing-style of OpenLAIR/dr-claw.

Open the folder on GitHubat commit d51b64e

Compare with similar skills

Writing Style next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Writing Style compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Writing Style this skillOpenLAIR/dr-claw1.2k—~2.4kAutomated safety check: PassCC-BY-4.0
Writing Style ReviewArmDeveloperEcosystem/arm-learning-paths154—~1.9kAutomated safety check: PassCustom licence
Avoid AI Writingconorbronsdon/avoid-ai-writing4.9k3 repos~8.1kAutomated safety check: PassMIT
Natural Japanese Business Writingcoji/natural-japanese1.9k—~2.1kAutomated safety check: PassMIT
Unslop AI Writing Cleanuptheclaymethod/unslop518—~1.7kAutomated safety check: PassMIT
UX Writingcontent-designer/ux-writing-skill2241 repos~3.8kAutomated safety check: PassMIT

Similar skills

  • Writing Style Review

    ArmDeveloperEcosystem/arm-learning-paths

    Review and improve writing style, voice, tone, readability, inclusive language, Arm terminology, heading style, word choice, and AI-sounding prose in Arm Learning Paths and install guides.

    154 GitHub stars~1.9k tokensUpdated today
    Writing & ContentAuto-check passed

  • Avoid AI Writing

    conorbronsdon/avoid-ai-writing

    Audit and rewrite content to remove AI writing patterns ("AI-isms").

    4.9k GitHub starsUsed in 3 repos~8.1k tokens
    Writing & ContentAuto-check passed

  • Natural Japanese Business Writing

    coji/natural-japanese

    Writes and edits Japanese business documents so they read clearly and naturally, removes AI-sounding phrasing and can score how AI-like a text reads.

    1.9k GitHub stars~2.1k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed

  • Unslop AI Writing Cleanup

    theclaymethod/unslop

    Removes AI writing tells from prose through an audit-first flow, routing to a two-pass rewrite, a report-only cleanup, voice teaching or mimicry depending on the sub-command used.

    518 GitHub stars~1.7k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed

  • UX Writing

    content-designer/ux-writing-skill

    Applies UX writing practice to interface copy such as buttons, errors, forms and onboarding, using four quality standards and accessibility guidance.

    224 GitHub starsUsed in 1 repo~3.8k tokens
    Writing & ContentAuto-check passed

  • Remove AI Patterns

    pchalasani/claude-code-tools

    Remove AI-writing patterns ("AI-isms") from text using the avoid-ai-writing catalog (conorbronsdon/avoid-ai-writing).

    2k GitHub stars~1.4k tokensUpdated yesterday
    Writing & ContentAuto-check passed

More from OpenLAIR/dr-claw

All 36 skills in this repo

  • Academic Rebuttal Drafting

    OpenLAIR/dr-claw

    Analyzes reviewer comments and drafts venue-specific rebuttals for AI and computer science conferences, with an issue board, task list and paper edit plan.

    1.2k GitHub stars~4.9k tokensUpdated 23 days ago
    Auto-check: notes

  • Academic Presentation Maker

    OpenLAIR/dr-claw

    Turns a research paper into a slide deck and, optionally, a narrated demo video, through script, slide generation, text-to-speech and video assembly stages you control.

    1.2k GitHub stars~1.5k tokensUpdated 23 days ago
    Auto-check passed

  • News to Research Idea Briefing

    OpenLAIR/dr-claw

    Clusters the latest news-feed results by topic and writes a briefing of research idea seeds with citations, plus a structured seeds file, without crawling new sources.

    1.2k GitHub stars~1.3k tokensUpdated 23 days ago
    Auto-check: notes

  • ML Dataset Discovery

    OpenLAIR/dr-claw

    Searches Hugging Face Hub, OpenML, GitHub and paper references for datasets that fit a research task and returns a ranked, de-duplicated table.

    1.2k GitHub stars~741 tokensUpdated 23 days ago
    Auto-check passed

  • Gemini Deep Research

    OpenLAIR/dr-claw

    Runs multi-source web research through Google's Gemini Deep Research Agent with a bundled Python script and saves a structured, cited report as files.

    1.2k GitHub stars~996 tokensUpdated 23 days ago
    Auto-check passed

  • Grant Proposal Writing Workflow

    OpenLAIR/dr-claw

    Six-phase workflow for writing, revising and adapting grant proposals for NSF, NIH, DOE, DARPA, NASA and China's NSFC, from profiling through simulated peer review.

    1.2k GitHub stars~9.2k tokensUpdated 23 days ago
    Auto-check passed

Categories

Questions about Writing Style

What does Writing Style do?

Apply the 21 prose rules from "The Elements of Agent Style" — 12 canonical rules (Strunk, Orwell, Pinker) plus 9 field-observed AI-output patterns. Writing Style is an agent skill from OpenLAIR/dr-claw. Apply the 21 prose rules from "The Elements of Agent Style" — 12 canonical rules (Strunk, Orwell, Pinker) plus 9 field-observed AI-output patterns.

When should I use Writing Style?

Writing Style fits situations like: the user says writing style; apply style rules; explicitly invokes /writing-style with an optional draft to revise.

How do I install Writing Style in Claude Code?

Run `npx skills add OpenLAIR/dr-claw --skill writing-style -a claude-code`. Or copy the skill folder (skills/writing-style in OpenLAIR/dr-claw) into .claude/skills/writing-style in your project. Claude Code loads it when a task matches its description.

How do I install Writing Style in Codex?

Run `npx skills add OpenLAIR/dr-claw --skill writing-style -a codex`. Or copy the skill folder (skills/writing-style in OpenLAIR/dr-claw) into .agents/skills/writing-style in your project. Codex loads it when a task matches its description.

Can I use Writing Style in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add OpenLAIR/dr-claw --skill writing-style -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/writing-style, .gemini/skills/writing-style, .github/skills/writing-style and .opencode/skills/writing-style in your project.

What does Writing Style need to run?

SKILL.md names no scripts, command-line tools or credentials: Writing Style is instructions for the agent only.

Does Writing Style access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Writing Style safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Writing Style use?

Writing Style is published under the CC-BY-4.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Writing Style use?

About 2.4k tokens (SKILL.md is roughly 9.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Writing Style?

Skills that share tags, products or a category with Writing Style: Writing Style Review (ArmDeveloperEcosystem/arm-learning-paths, 154 stars), Avoid AI Writing (conorbronsdon/avoid-ai-writing, 4.9k stars), Natural Japanese Business Writing (coji/natural-japanese, 1.9k stars) and Unslop AI Writing Cleanup (theclaymethod/unslop, 518 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Writing Style?

OpenLAIR (a GitHub organization) maintains it in OpenLAIR/dr-claw, which has 1,155 GitHub stars. The repository holds 36 skills in this directory. The repository was last updated on September 17, 2026.

Source: OpenLAIR/dr-claw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.