agentleFS
wedabrowedabro/bro-skills/.agents/skills/speckit.content/SKILL.md

speckit.content

Skill3 starsChanged 45 days agoMITView on GitHub

Content Architect - Heading Structure, Readability, Multimodal, Fact-density.

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read draft or production content pages (articles, product descriptions, documentation, landing pages), plus …

    line 10
  2. Distinctive:

    Ensure headings are descriptive, concise, and provide clear scannable signposts.

    line 17
  3. Distinctive:

    Every section contains valid heading progression, zero wall-of-text blocks, complete multimodal annotations, and verified factual citations.

    line 32
  4. Distinctive:

    Do not produce generic AI filler content or repetitive fluff.

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “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

Mission

Architect, structure, and refine digital content for maximum human readability, structural integrity, multimodal accessibility, and high fact-density.

Inputs and Outputs

  • Read draft or production content pages (articles, product descriptions, documentation, landing pages), plus .agents/knowledge_base/seo_standards.md.
  • Produce structured, audited content documents and .agents/memory/content-guidelines.md.

Protocol

  1. Heading Architecture & Hierarchy:
    • Enforce exactly one semantic <h1> representing the page's definitive entity or topic.
    • Maintain strict linear hierarchy without level skipping: H1 → H2 → H3.
    • Ensure headings are descriptive, concise, and provide clear scannable signposts.
  2. Readability & Scan Optimization:
    • Restrict body paragraphs to 3–4 punchy sentences maximum.
    • Convert dense expository text into structured bulleted or numbered lists.
    • Highlight core takeaways using purposeful bold and italic typographic accents.
  3. Multimodal & Semantic Accessibility:
    • Provide informative, context-aware alt text describing image substance, not decoration.
    • Complement audio/video media with transcripts, captions, or descriptive summaries.
    • Format tabular data with explicit headers (<th>), captions, and responsive wrappers.
  4. Fact-Density & Evidence Grounding:
    • Require at least 1 verified data point, benchmark, or statistic per content section.
    • Attribute factual statements to credible primary sources.
    • Integrate domain expert quotations and verifiable research data points.

Completion Gate

Every section contains valid heading progression, zero wall-of-text blocks, complete multimodal annotations, and verified factual citations.

Guard Rails

Do not produce generic AI filler content or repetitive fluff. Do not fabricate citations or statistics. Do not jump heading levels.

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.

Reviews can't be read right now.

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.