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

Editorial Document

by Sidiora-Labs in Sidiora-Labs/centra-gideon-agent

Write long-form editorial documents as clean, semantic HTML saved as an artifact (kind=document) — reports, briefs, explainers, proposals, write-ups.

Apache-2.0Auto-check passedFrontend & Design

Install Editorial Document

skills CLI
$ npx skills add Sidiora-Labs/centra-gideon-agent --skill editorial-document -a claude-code

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

GitHub CLI
$ gh skill install Sidiora-Labs/centra-gideon-agent editorial-document --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/Sidiora-Labs/centra-gideon-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/runtime/gideon/extensions/skills/bundled/editorial-document .claude/skills/editorial-document && 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
editorial-document
GitHub stars
181
Token cost
~1.3k tokens
SKILL.md length
511 words
Files
1
Skills in repo
24
Repo updated
First seen
Licence
Apache-2.0

At a glance

Write long-form editorial documents as clean, semantic HTML saved as an artifact (kind=document) — reports, briefs, explainers, proposals, write-ups.

  • Works in 4 steps: Confirm a document is right (a written… → Draft semantic HTML within the… → artifact_save(kind="document", name="…",… → …
  • Wants a polished written document
  • SKILL.md covers When to use this vs other types, The security contract (author…, House style and Example, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Editorial Document is an agent skill from Sidiora-Labs/centra-gideon-agent. Write long-form editorial documents as clean, semantic HTML saved as an artifact (kind=document) — reports, briefs, explainers, proposals, write-ups. Covers the house style (structure, voice, typography) AND the security contract (the HTML is sanitized fail-closed, so author within the allowlist). Load when the user wants a polished written document, report, brief, or explainer that should read like a publication, not a chat message.

Its SKILL.md is about 1.3k 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 Frontend & Design, covering Proposals and quotes and Typography. The repository describes itself as: The companion AI agent that learns, adapts and gets the work done no matter the task. The licence is Apache-2.0.

When your agent uses it

  • Wants a polished written document
  • Explainer that should read like a publication
  • Not a chat message

Example prompts

  • “/editorial-document”

Workflow steps

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

  1. Confirm a document is right (a written piece to be read, not interactive).
  2. Draft semantic HTML within the allowlist; structure with headings + the lede.
  3. artifact_save(kind="document", name="…", content=) (or artifact_update
  4. The user reads it, edits the HTML with live preview, comments on passages (those

What it can do on your machine

Read from SKILL.md and the folder at commit 2176d5b. 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 (its code samples are html).

    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

Editorial Document loads about 1.3k tokens when it runs. Until then it costs about 114 tokens; SKILL.md has 511 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~114
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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 Sidiora-Labs/centra-gideon-agent at commit 2176d5b, republished under its Apache-2.0 licence (© Sidiora-Labs). 511 words, ~1,319 tokens.

Download SKILL.mdSave it as .claude/skills/editorial-document/SKILL.md (or your agent's skills folder).
name
editorial-document
description
Write long-form editorial documents as clean, semantic HTML saved as an artifact (kind=document) — reports, briefs, explainers, proposals, write-ups. Covers the house style (structure, voice, typography) AND the security contract (the HTML is sanitized fail-closed, so author within the allowlist). Load when the user wants a polished written document, report, brief, or explainer that should read like a publication, not a chat message.
triggers
document, write a report, write up, brief, explainer, proposal, white paper, editorial, long-form, publish a doc, formatted document, article, memo, one-pager

Editorial Documents

Gideon renders long-form written documents from semantic HTML, saved as an artifact with kind=document. Unlike a widget (interactive HTML in a sandboxed iframe) or markdown, a document is prose-first editorial HTML rendered in the page with a tuned reading type scale — it should read like a published piece.

Save with artifact_save(kind="document", name="…", content=<HTML>). The body is HTML (semantic tags, no <html>/<body> wrapper needed — just the content). The viewer renders it with the editorial stylesheet, lets the user edit the HTML with a live split preview, comment on any passage, and export it (standalone HTML / copy).

When to use this vs other types

  • Document — a written piece meant to be read: reports, briefs, explainers, proposals, post-mortems, design write-ups. Prose is the substance.
  • Markdown — quick notes / READMEs / chat-adjacent text where Markdown's shorthand is enough and you don't need editorial typography.
  • Widget (visual-output skill) — interactive HTML, dashboards, custom charts.
  • Infographic (infographic-syntax skill) — structured visual info-design.

The security contract (author within the allowlist)

The document body is sanitized fail-closed before rendering: anything not on the allowlist is dropped. This is a security control because the content may echo untrusted material (e.g. crawled pages). Author accordingly:

  • Allowed: semantic prose + structure — headings (h1–h6), p, ul/ol/ li, blockquote, pre/code, table/thead/tbody/tr/th/td, figure/figcaption, img, a, strong/em, hr, section/article, inline svg for simple diagrams.
  • Dropped (don't bother emitting): <script>, <style>, <iframe>, <object>, <form>, inline event handlers (onclick=…), inline style= attributes, and javascript:/data:text/html URLs. Links must be http(s), mailto:, tel:, relative, or #anchors; data:image/* is allowed for inline images.
  • Don't fight the sanitizer with inline styles — the editorial stylesheet handles typography. Write clean structure and let it style.
Show full SKILL.md (242 more words)Show less

House style

Structure. Open with an <h1> title and a one-paragraph lede that states the point. Use <h2> for major sections, <h3> for sub-sections. Prefer short sections with descriptive headings over one long wall. Close with a clear takeaway or next-steps section when the piece calls for it.

Voice. Direct and concrete. Lead with the conclusion, then support it (BLUF). Active voice. Cut filler ("it should be noted that", "in order to"). One idea per paragraph; 2–4 sentences each.

Evidence. Use <table> for comparisons/data, <ul> for parallel points, a <blockquote> for a pulled quote or key caveat. Link sources with real <a href>. Use <figure> + <figcaption> for images/diagrams.

Typography. Don't hand-set fonts/sizes/colors — the reader stylesheet owns the type scale (heading hierarchy, a measure of roughly 75 characters, readable line-height) and is theme-aware. Your job is correct semantics; the styling follows.

Example

html
<h1>Q3 Reliability Review</h1>
<p>Availability held at 99.95% despite a 40% traffic increase — but two incidents
share a root cause we haven't fixed. This brief lays out what happened and the one
change that closes both.</p>

<h2>What happened</h2>
<p>…</p>
<table>
  <thead><tr><th>Incident</th><th>Duration</th><th>Root cause</th></tr></thead>
  <tbody>
    <tr><td>Aug 12 latency</td><td>34 min</td><td>Connection-pool exhaustion</td></tr>
    <tr><td>Sep 3 errors</td><td>18 min</td><td>Connection-pool exhaustion</td></tr>
  </tbody>
</table>

<h2>The fix</h2>
<blockquote>One change — bounded pools with backpressure — removes the shared cause.</blockquote>
<p>…</p>

Workflow

  1. Confirm a document is right (a written piece to be read, not interactive).
  2. Draft semantic HTML within the allowlist; structure with headings + the lede.
  3. artifact_save(kind="document", name="…", content=<HTML>) (or artifact_update a prior one — artifact_list first, per the artifacts skill).
  4. The user reads it, edits the HTML with live preview, comments on passages (those route back to you), and can export a standalone HTML file.

Pitfalls

  • Don't emit <script>/<style>/inline style=/onclick= — they're stripped.
  • Don't wrap the body in <widget> — kind=document is its own type.
  • Don't hand-style — semantics + the reader stylesheet, not inline CSS.
  • Keep links to safe schemes (http(s)/mailto/tel/relative/#).

© Sidiora-Labs, 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 runtime/gideon/extensions/skills/bundled/editorial-document of Sidiora-Labs/centra-gideon-agent.

Open the folder on GitHubat commit 2176d5b

Compare with similar skills

Editorial Document 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.

Editorial Document compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Editorial Document this skillSidiora-Labs/centra-gideon-agent181—~1.3kAutomated safety check: PassApache-2.0
Site SpecificationAutomattic/wordpress-agent-skills115—~2.7kAutomated safety check: PassNone
Design Archivistcuriositech/some_claude_skills2431 repos~1.6kAutomated safety check: PassMIT
Impeccablebestofjs/bestofjs3.1k27 repos~2.6kAutomated safety check: PassMIT
Tailwindcss Developmentanonaddy/anonaddy4.9k10 repos~865Automated safety check: PassMIT
Design SystemOhh-889/skyroc79511 repos~1.7kAutomated safety check: PassMIT

Similar skills

  • Site Specification

    Automattic/wordpress-agent-skills

    Extract comprehensive site specifications from simple descriptions.

    115 GitHub stars~2.7k tokensUpdated 6 mo ago
    Frontend & DesignAuto-check passed

  • Design Archivist

    curiositech/some_claude_skills

    Long-running design anthropologist that builds comprehensive visual databases from 500-1000 real-world examples, extracting color palettes, typography patterns, layout systems, and interaction…

    243 GitHub starsUsed in 1 repo~1.6k tokens
    Frontend & DesignAuto-check passed

  • Impeccable

    bestofjs/bestofjs

    A skill your agent uses when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a…

    3.1k GitHub starsUsed in 27 repos~2.6k tokens
    Frontend & DesignAuto-check passed

  • Tailwindcss Development

    anonaddy/anonaddy

    Always invoke when the user's message includes 'tailwind' in any form.

    4.9k GitHub starsUsed in 10 repos~865 tokens
    Frontend & DesignAuto-check passed

  • Design System

    Ohh-889/skyroc

    Token architecture, component specifications, and slide generation.

    795 GitHub starsUsed in 11 repos~1.7k tokens
    Frontend & DesignAuto-check passed

  • Make Interfaces Feel Better

    samuelclay/NewsBlur

    Design engineering principles for making interfaces feel polished.

    7.6k GitHub starsUsed in 10 repos~1.5k tokens
    Frontend & DesignAuto-check passed

More from Sidiora-Labs/centra-gideon-agent

All 24 skills in this repo

  • Artifacts

    Sidiora-Labs/centra-gideon-agent

    Persist, version, and iterate on LLM-generated UI (widgets, HTML, markdown).

    181 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Best Of N

    Sidiora-Labs/centra-gideon-agent

    Sample several candidate answers in parallel, judge them against stated criteria, and present the winner with the runners-up kept one click away.

    181 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Document Authoring

    Sidiora-Labs/centra-gideon-agent

    Author a real document — a report, proposal, slide deck, spec, or paper — by settling audience, claim, and structure before drafting prose, then writing to that structure.

    181 GitHub stars~970 tokensUpdated today
    Auto-check passed

  • Gideon API

    Sidiora-Labs/centra-gideon-agent

    The operator's manual for DRIVING Gideon's API and tools — how to find an exact tool/route signature, the mandatory verify-after-mutate loop, and what NOT to hand-roll.

    181 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Infographic Syntax

    Sidiora-Labs/centra-gideon-agent

    Author infographics with the AntV declarative DSL — pick a template, fill a small indented data tree, and save as an artifact (kind=infographic) that renders to crisp SVG and streams as you write it.

    181 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Research Campaign

    Sidiora-Labs/centra-gideon-agent

    Run a multi-cycle research campaign — grill the question, decompose it into answerable sub-questions, investigate each against sources, then synthesize with confidence and gaps stated.

    181 GitHub stars~1.3k tokensUpdated today
    Auto-check passed

Categories

Questions about Editorial Document

What does Editorial Document do?

Write long-form editorial documents as clean, semantic HTML saved as an artifact (kind=document) — reports, briefs, explainers, proposals, write-ups. Editorial Document is an agent skill from Sidiora-Labs/centra-gideon-agent. Write long-form editorial documents as clean, semantic HTML saved as an artifact (kind=document) — reports, briefs, explainers, proposals, write-ups.

When should I use Editorial Document?

Editorial Document fits situations like: wants a polished written document; explainer that should read like a publication; not a chat message.

How do I install Editorial Document in Claude Code?

Run `npx skills add Sidiora-Labs/centra-gideon-agent --skill editorial-document -a claude-code`. Or copy the skill folder (runtime/gideon/extensions/skills/bundled/editorial-document in Sidiora-Labs/centra-gideon-agent) into .claude/skills/editorial-document in your project. Claude Code loads it when a task matches its description.

How do I install Editorial Document in Codex?

Run `npx skills add Sidiora-Labs/centra-gideon-agent --skill editorial-document -a codex`. Or copy the skill folder (runtime/gideon/extensions/skills/bundled/editorial-document in Sidiora-Labs/centra-gideon-agent) into .agents/skills/editorial-document in your project. Codex loads it when a task matches its description.

Can I use Editorial Document 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 Sidiora-Labs/centra-gideon-agent --skill editorial-document -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/editorial-document, .gemini/skills/editorial-document, .github/skills/editorial-document and .opencode/skills/editorial-document in your project.

What does Editorial Document need to run?

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

Does Editorial Document 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 Editorial Document 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 Editorial Document use?

Editorial Document is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Editorial Document use?

About 1.3k tokens (SKILL.md is roughly 5.3k 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 Editorial Document?

Skills that share tags, products or a category with Editorial Document: Site Specification (Automattic/wordpress-agent-skills, 115 stars), Design Archivist (curiositech/some_claude_skills, 243 stars), Impeccable (bestofjs/bestofjs, 3.1k stars) and Tailwindcss Development (anonaddy/anonaddy, 4.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Editorial Document?

Sidiora-Labs (a GitHub organization) maintains it in Sidiora-Labs/centra-gideon-agent, which has 181 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 8, 2026.

Source: Sidiora-Labs/centra-gideon-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.