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
- Very specific: line 10
Read draft or production content pages (articles, product descriptions, documentation, landing pages), plus …
- Distinctive: line 17
Ensure headings are descriptive, concise, and provide clear scannable signposts.
- Distinctive: line 32
Every section contains valid heading progression, zero wall-of-text blocks, complete multimodal annotations, and verified factual citations.
- Distinctive: line 35
Do not produce generic AI filler content or repetitive fluff.
≈ “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.
Files
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
- 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.
- Enforce exactly one semantic
- 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.
- Multimodal & Semantic Accessibility:
- Provide informative, context-aware
alttext 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.
- Provide informative, context-aware
- 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.
In this repository64 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/bro-skills.mdcCursor rule
- .agents/skills/llms.txtllms.txt
- brandkitSkill
- bro-mcp-loopSkill
- ci-security-scanning-with-strixSkill
- design-taste-frontendSkill
- fix-security-vulnerabilities-with-strixSkill
- full-output-enforcementSkill
- gpt-tasteSkill
- high-end-visual-designSkill
- imagegen-frontend-mobileSkill
- imagegen-frontend-webSkill
- image-to-codeSkill
- industrial-brutalist-uiSkill
- managed-pentesting-with-strixSkill
- minimalist-uiSkill
- penetration-testing-with-strixSkill
- ponytailSkill
- redesign-existing-projectsSkill
- speckit.ai-engineerSkill
- speckit.analyzeSkill
- speckit.architectureSkill
- speckit.backendSkill
- speckit.backlogSkill
- speckit.checkerSkill
- speckit.checklistSkill
- speckit.clarifySkill
- speckit.constitutionSkill
- speckit.databaseSkill
- speckit.dddSkill
- speckit.debugSkill
- speckit.devopsSkill
- speckit.diffSkill
- speckit.event-realtimeSkill
- speckit.frontendSkill
- speckit.game-embeddedSkill
- speckit.game-native-jsSkill
- speckit.geoSkill
- speckit.identity-accessSkill
- speckit.identitySkill
- speckit.implementSkill
- speckit.mapSkill
- speckit.migrateSkill
- speckit.payment-fintechSkill
- speckit.planSkill
- speckit.quizmeSkill
- speckit.reviewerSkill
- speckit.roadmapSkill
- speckit.securitySkill
- speckit.seoSkill
- speckit.specifySkill
- speckit.sre-observabilitySkill
- speckit.statusSkill
- speckit.tasksSkill
- speckit.taskstoissuesSkill
- speckit.testerSkill
- speckit.uatSkill
- The first 60 shown.
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.

