agentleFS
Sign inStart free
romanveselovskiromanveselovski/agents-frontend-rules/skills/blog-author/SKILL.md

blog-author

Skill0 starsChanged 2 months agoMITView on GitHub

Universal article pipeline: fact-check against project facts, SEO draft, locales if the site is multilingual, narrative rewrite, avoid-ai-writing, images, schema, then publish via the project's own CMS. Use when writing or publishing a blog post or long-form guide.

3 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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. Distinctive:

    Read the source in full.

    line 35
  2. Distinctive:

    Read project-facts.md. If empty, fill from site code and docs, not from memory.

    line 36
  3. Distinctive:

    Verify contested claims in the repo (API, i18n, README).

    line 37
  4. Distinctive:

    If the project has SEO MCP or a keyword export, take up to 5 working queries per publish language.

    line 44
  5. Distinctive:

    No tool — queries from the brief and common sense, no fake volumes.

    line 46
  6. Very specific:

    Write only languages the site actually serves.

    line 58
  7. Distinctive:

    Do not publish until there is a short note for 3c and 3d.

    line 82

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Article author

Pipeline for any site. Facts come from this project's project-facts.md. Do not invent product, prices, or integrations.

Copy quality is required before publish: the SEO draft (step 3) is a skeleton. Production needs steps 3c and 3d.

- [ ] 1. Ingest and fact-check
- [ ] 2. Keywords (if an SEO tool exists)
- [ ] 3. Draft in the source language
- [ ] 3e. Other site languages (if they exist)
- [ ] 3c. Connected prose — copywriting.md + narrative-rewrite.md
- [ ] 3d. No AI-isms — humanize.md + avoid-ai-writing
- [ ] 3b. Locale check (for ru — ru-locale-style.md)
- [ ] 4. Article skeleton from content-template.md
- [ ] 5. Images — image-style.md
- [ ] 6. Schema for visible content
- [ ] 7. Publish the project's way
- [ ] 8. E-E-A-T / audit, patches
- [ ] 9. Indexing — if the project already has it

1. Ingest and fact-check

  1. Read the source in full.
  2. Read project-facts.md. If empty, fill from site code and docs, not from memory.
  3. Verify contested claims in the repo (API, i18n, README).
  4. Fact-check table: claim → source → ok / drop / soften.

Forbidden: invented numbers, reviews, “guaranteed growth”, features that do not exist.

2. Keywords

If the project has SEO MCP or a keyword export, take up to 5 working queries per publish language. Seeds in the SERP language, not English seeds in a foreign database.

No tool — queries from the brief and common sense, no fake volumes.

Optional: skills/seo-dataforseo/SKILL.md.

3. Draft

Source language = the site’s primary language (often html[lang]). Structure — content-template.md. Tone: teacher, not a sales reel.

Optional: skills/seo-aeo-landing-page-writer/SKILL.md — structure only, not “buy now” landing tone if this is a guide.

3e. Locales

Write only languages the site actually serves. Meaning and facts match the source, not word-order calque. For ru — ru-locale-style.md.

3c. Connected prose

copywriting.md → narrative-rewrite.md. Each H2 is a finished thought. FAQ — 2–4 sentences. Mistakes — paragraphs, not fragments.

3d. Humanize

humanize.md and rules/avoid-ai-writing.mdc. Edit all user-facing article copy. Leave facts, prices, code, UI labels, brands.

5. Images

image-style.md. Logo and domain from project facts, not invented.

6. Schema

JSON-LD only for what is on the page. HowTo if there are steps. FAQ if there is FAQ. Article/BlogPosting for every article.

Optional: skills/seo-aeo-schema-generator/SKILL.md.

7–9. Publish

File format, CMS, 404, sitemap, IndexNow — as in this repo. No tie to Supabase or one host.

Do not publish until there is a short note for 3c and 3d.

Audit: skills/seo-content-auditor/SKILL.md.

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.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.

Check your setup, free