agentleFS
Sign inStart free
UXMagicaiUXMagicai/seosorted-skills/skills/bulk-content-run/SKILL.md

bulk-content-run

Skill0 starsChanged 39 days agoMITView on GitHub

Generate many SEO articles at once (10 to 100+) with SEOsorted, prioritised by search volume and keyword difficulty, deduplicated against existing content and checked for cannibalization. Use when the user asks for a batch of blogs, "write 50 articles", fill a content calendar, scale content, restart publishing that stopped, or produce content to grow impressions.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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:

    QA.: When done, sample-read 5–10 articles with manage_articles operation: "get", plus any on YMYL topics.

    line 21

≈ “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

Bulk content run

This is the playbook used to ship 100 articles for a live client: research wide, filter hard, check overlap with Google's own results, then let SEOsorted generate at a steady pace.

Steps

  1. State of play. get_site_overview: quota left, articles by status, active generation run, next scheduled posts. If a run is already active, report it and do not start a second.
  2. Budget. Each finished article uses one article credit. If the request exceeds what is left, tell the user the number that fits and how to get more (upgrade or buy articles in Billing). Do not silently generate fewer.
  3. Research wide. keyword-research across 10–30 seeds covering every product line and customer problem. Expect thousands of raw ideas.
  4. Filter. Relevance to what the business sells, no navigational or competitor-brand terms, no topics the business must not promote, drop hasArticle ideas. Prefer quick-win and high buckets; keep a few high-volume long-term targets.
  5. Merge and dedupe. Collapse variants into one target with secondaries. Compare against manage_articles operation: "list" titles.
  6. Overlap check. check_keyword_overlap in chunks of 25 with compare_existing: true. Drop or merge every pair at 7+ shared URLs; differentiate 4–6.
  7. Approve. Show the final list (keyword, volume, KD, type) and total monthly volume. Get a yes — this spends credits.
  8. Generate. write_articles operation: "start" with keywords (max 25 per call; call again for the next chunk). SEOsorted dispatches at most a few at a time per workspace, so the rest queue and drain automatically.
  9. Monitor. write_articles operation: "status" with the run id every few minutes. Report progress in tens, and any failures with their error.
  10. QA. When done, sample-read 5–10 articles with manage_articles operation: "get", plus any on YMYL topics. Look for missing images, unsupported claims, and leaked phrasing such as "the supplied sources".

Hand-off

Finished articles sit as READY. Nothing publishes until it is scheduled — use content-calendar (e.g. 2 per day, quick wins first).

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