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

Docs Voice Tone

by adobe in adobe/spectrum-design-data

Reviews docs-site prose (articles, spec pages, READMEs) against Spectrum's voice principles (Clear, Genuine, Concise, Upfront), adapted for public/reference docs rather than in-product UI strings.

Apache-2.0Auto-check passedWriting & Content

Install Docs Voice Tone

skills CLI
$ npx skills add adobe/spectrum-design-data --skill docs-voice-tone -a claude-code

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

GitHub CLI
$ gh skill install adobe/spectrum-design-data docs-voice-tone --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/adobe/spectrum-design-data.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/docs-voice-tone .claude/skills/docs-voice-tone && 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
docs-voice-tone
GitHub stars
155
Token cost
~1.1k tokens
SKILL.md length
551 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
Apache-2.0

At a glance

Reviews docs-site prose (articles, spec pages, READMEs) against Spectrum's voice principles (Clear, Genuine, Concise, Upfront), adapted for public/reference docs rather than in-product UI strings.

  • Works in 5 steps: Read the doc once for content… → Run humanizer first if the doc hasn't… → Walk the four principles in order (Clear… → …
  • Tasks that involve Humanizing AI text
  • SKILL.md covers The four voice principles, How to apply this in review and What NOT to flag
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Docs Voice Tone is an agent skill from adobe/spectrum-design-data. Reviews docs-site prose (articles, spec pages, READMEs) against Spectrum's voice principles (Clear, Genuine, Concise, Upfront), adapted for public/reference docs rather than in-product UI strings. Use after drafting or editing an article, README, or spec page, or when asked to check tone/voice on written docs. Complements (run after, not instead of) the humanizer skill — humanizer strips AI-writing tells; this checks Spectrum voice fit on top of clean prose.

Its SKILL.md is about 1.1k 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 Humanizing AI text, Technical documentation and Static sites and blogs. The repository describes itself as: Design data, including design tokens, component schemas, and tooling for Spectrum, Adobe's design system. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Humanizing AI text
  • Tasks that involve Technical documentation
  • Tasks that involve Static sites and blogs

Example prompts

  • “Use the docs-voice-tone skill to review docs-site prose (articles, spec pages, READMEs) against Spectrum's voice principles (Clear, Genuine…”
  • “/docs-voice-tone”

Workflow steps

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

  1. Read the doc once for content correctness first (that's a separate pass — see
  2. Run humanizer first if the doc hasn't already been through it — this skill assumes
  3. Walk the four principles in order (Clear → Genuine → Concise → Upfront) and flag
  4. Common docs-specific failure modes to watch for, mapped to the principle they break
  5. Report findings as a short list: [principle] — [line/quote] — [what to change]. No

What it can do on your machine

Read from SKILL.md and the folder at commit dc75d47. 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

    No URLs in SKILL.md.

    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

Docs Voice Tone loads about 1.1k tokens when it runs. Until then it costs about 120 tokens; SKILL.md has 551 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~120
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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 adobe/spectrum-design-data at commit dc75d47, republished under its Apache-2.0 licence (© adobe). 551 words, ~1,111 tokens.

Download SKILL.mdSave it as .claude/skills/docs-voice-tone/SKILL.md (or your agent's skills folder).
name
docs-voice-tone
description
Reviews docs-site prose (articles, spec pages, READMEs) against Spectrum's voice principles (Clear, Genuine, Concise, Upfront), adapted for public/reference docs rather than in-product UI strings. Use after drafting or editing an article, README, or spec page, or when asked to check tone/voice on written docs. Complements (run after, not instead of) the `humanizer` skill — humanizer strips AI-writing tells; this checks Spectrum voice fit on top of clean prose.
license
Apache-2.0

Docs voice & tone (Spectrum-adapted)

Source: Spectrum Voice and Tone Framework, Adobe Design (spectrum.adobe.com/page/voice-and-tone), Spectrum 2 alignment.

That framework governs in-product, authenticated UI strings — buttons, errors, onboarding. This repo's docs (articles, /spec/ pages, READMEs, CLI help prose) are public reference/marketing-adjacent content, not in-product strings, so treat the four voice principles below as a prose-review lens, not a literal rule (there's no "tone variant by moment" here — that part of the framework doesn't apply to docs).

The four voice principles

Clear — direct, not buried. One idea per sentence. No jargon left unexplained, no action buried three clauses in.

  • Do: "The export command emits the whole dataset as one DTCG document."
  • Don't: "The export functionality has been designed to facilitate the retrieval of the complete resolved token dataset in DTCG-conformant form."

Genuine — honest, not performed. No marketing verbs, no claimed enthusiasm, no significance-inflation about what a change means.

  • Do: "This fixes a stale token reference in the article."
  • Don't: "This exciting update ensures our documentation stays cutting-edge."

Concise — necessary, not more. No padding, no redundant restatement, no hedging qualifiers that add nothing.

  • Do: "Every example below is a real token you can look up on the Tokens page."
  • Don't: "It's worth noting that, in general, most of the examples below tend to be real tokens that you can typically look up."

Upfront — actor and limit disclosed, not implied. Say what's still in progress, what's provisional, what changed and why, rather than letting a reader assume.

  • Do: "The Design Data Specification is still in development; the legacy format keeps shipping in the meantime."
  • Don't: silently describing a future-state format as if it's already the one people should use today.
Show full SKILL.md (276 more words)Show less

How to apply this in review

  1. Read the doc once for content correctness first (that's a separate pass — see accuracy review conventions elsewhere in this repo). This skill is voice/tone only.
  2. Run humanizer first if the doc hasn't already been through it — this skill assumes AI-writing tells (em dashes, testament/pivotal/showcase, inline-header lists, etc.) are already gone. Don't re-litigate those here.
  3. Walk the four principles in order (Clear → Genuine → Concise → Upfront) and flag violations with the specific line and which principle it breaks. Don't rewrite wholesale — this is a targeted pass on top of otherwise-good prose.
  4. Common docs-specific failure modes to watch for, mapped to the principle they break:
    • Feature announcements dressed up as significant ("this powerful new capability") → Genuine.
    • Spec/status ambiguity — describing a draft/in-progress spec section as settled fact → Upfront.
    • Nested clauses explaining how something works before saying what it does → Clear.
    • Restating the heading in the first sentence under it, or repeating a claim already made two paragraphs up → Concise.
  5. Report findings as a short list: [principle] — [line/quote] — [what to change]. No need for a formal score; this isn't the monetization system's 1–4 rubric, which is built for conversion surfaces, not reference docs.

What NOT to flag

  • Technical precision that reads a little dry (API names, exact token names, code blocks). Reference docs are allowed to be plain — that's Clear and Concise doing their job, not a violation.
  • Necessary caveats and version/compatibility notes — that's Upfront, not padding.
  • First-person or opinion is not expected here (unlike humanizer's "personality and soul" guidance for blog-style writing) unless the doc is explicitly an opinion piece. Neutral and plain is correct voice for spec/reference content.

© adobe, Apache-2.0. 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 .claude/skills/docs-voice-tone of adobe/spectrum-design-data.

Open the folder on GitHubat commit dc75d47

Compare with similar skills

Docs Voice Tone 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.

Docs Voice Tone compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Docs Voice Tone this skilladobe/spectrum-design-data155—~1.1kAutomated safety check: PassApache-2.0
Not AIudaysharmadev/Not-Ai131—~4.7kAutomated safety check: PassMIT
Writewaynesutton/markdown-site628—~3kAutomated safety check: PassMIT
Unsloppoteto/noodle437—~1.1kAutomated safety check: PassMIT
Natural Writing Enmizchi/skills356—~3.9kAutomated safety check: PassNone
Writerrileyhilliard/claude-essentials130—~2kAutomated safety check: PassMIT

Similar skills

  • Not AI

    udaysharmadev/Not-Ai

    Edit prose into a clear, specific, source-grounded version that preserves the author's meaning and voice.

    131 GitHub stars~4.7k tokensUpdated 3 days ago
    Writing & ContentAuto-check passed

  • Write

    waynesutton/markdown-site

    Writing style guide for technical content, social media, blog posts, READMEs, git commits, and developer documentation.

    628 GitHub stars~3k tokensUpdated 4 mo ago
    Writing & ContentAuto-check passed

  • Unslop

    poteto/noodle

    Remove AI writing patterns from prose. An agent skill from poteto/noodle.

    437 GitHub stars~1.1k tokensUpdated 6 mo ago
    Writing & ContentAuto-check passed

  • Natural Writing En

    mizchi/skills

    English prose norm for writing explanatory text that does not read as machine-generated.

    356 GitHub stars~3.9k tokensUpdated 6 days ago
    Writing & ContentAuto-check passed

  • Writer

    rileyhilliard/claude-essentials

    Writing style and tone guide for human-sounding content. An agent skill from rileyhilliard/claude-essentials.

    130 GitHub stars~2k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed

  • Humanizer

    dotnetdreamer/open-screenshot-generator

    Rewrite AI-sounding text so it reads naturally without changing what it says.

    124 GitHub stars~7.7k tokensUpdated yesterday
    Writing & ContentAuto-check passed

More from adobe/spectrum-design-data

  • S2 Docs

    adobe/spectrum-design-data

    Look up Spectrum 2 (S2) component documentation, design guidelines, and usage patterns when building with React Spectrum or Spectrum Web Components.

    155 GitHub stars~868 tokensUpdated 5 days ago
    Auto-check passed

  • Design Data

    adobe/spectrum-design-data

    Look up Spectrum design tokens, component schemas, and design-system decisions when building with or extending Adobe Spectrum.

    155 GitHub stars~1.2k tokensUpdated 5 days ago
    Auto-check passed

  • Design Data Agent

    adobe/spectrum-design-data

    Validate, query, resolve, diff, and author spec-conformant design tokens and components using the design-data MCP tools against a local dataset.

    155 GitHub stars~2k tokensUpdated 5 days ago
    Auto-check passed

  • Enhance Sync PR

    adobe/spectrum-design-data

    Enhances auto-generated spectrum-design-data PRs from spectrum-tokens-studio-data sync (branch tokens-sync/patch-spectrum2-from-main, author mrcjhicks).

    155 GitHub stars~2.3k tokensUpdated 5 days ago
    Auto-check passed

Categories

Questions about Docs Voice Tone

What does Docs Voice Tone do?

Reviews docs-site prose (articles, spec pages, READMEs) against Spectrum's voice principles (Clear, Genuine, Concise, Upfront), adapted for public/reference docs rather than in-product UI strings. Docs Voice Tone is an agent skill from adobe/spectrum-design-data. Reviews docs-site prose (articles, spec pages, READMEs) against Spectrum's voice principles (Clear, Genuine, Concise, Upfront), adapted for public/reference docs rather than in-product UI strings.

When should I use Docs Voice Tone?

Docs Voice Tone fits situations like: tasks that involve Humanizing AI text; tasks that involve Technical documentation; tasks that involve Static sites and blogs.

How do I install Docs Voice Tone in Claude Code?

Run `npx skills add adobe/spectrum-design-data --skill docs-voice-tone -a claude-code`. Or copy the skill folder (.claude/skills/docs-voice-tone in adobe/spectrum-design-data) into .claude/skills/docs-voice-tone in your project. Claude Code loads it when a task matches its description.

How do I install Docs Voice Tone in Codex?

Run `npx skills add adobe/spectrum-design-data --skill docs-voice-tone -a codex`. Or copy the skill folder (.claude/skills/docs-voice-tone in adobe/spectrum-design-data) into .agents/skills/docs-voice-tone in your project. Codex loads it when a task matches its description.

Can I use Docs Voice Tone 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 adobe/spectrum-design-data --skill docs-voice-tone -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/docs-voice-tone, .gemini/skills/docs-voice-tone, .github/skills/docs-voice-tone and .opencode/skills/docs-voice-tone in your project.

What does Docs Voice Tone need to run?

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

Does Docs Voice Tone access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Docs Voice Tone 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 Docs Voice Tone use?

Docs Voice Tone is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Docs Voice Tone use?

About 1.1k tokens (SKILL.md is roughly 4.4k 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 Docs Voice Tone?

Skills that share tags, products or a category with Docs Voice Tone: Not AI (udaysharmadev/Not-Ai, 131 stars), Write (waynesutton/markdown-site, 628 stars), Unslop (poteto/noodle, 437 stars) and Natural Writing En (mizchi/skills, 356 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Docs Voice Tone?

adobe (a GitHub organization) maintains it in adobe/spectrum-design-data, which has 155 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 2, 2026.

Source: adobe/spectrum-design-data on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.