agentleFS
Sign inStart free
mrieckmrieck/seoblog-claude-plugin/skills/seoblog-humanize/SKILL.md

seoblog-humanize

Skill0 starsChanged 53 days agoMITView on GitHub

Rewrite an existing SEO Blog draft by id or slug to remove AI writing tells without changing its facts, links or images, or list drafts when no target is supplied.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 3 are distinctive, and 4 are 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.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read runtime instructions before running scripts.

    line 8
  2. Very specific:

    Use the humanize skill to do the rewrite and the blog-publish skill for the cms.mjs mechanics.

    line 10
  3. Distinctive:

    Use the user's request as the arguments.

    line 13
  4. Very specific:

    Run the blog preflight (doctor.mjs --workflow blog --site <id> --text-only).

    line 26
  5. Very specific:

    Read the site's voiceSamples, directions and toneGuide from config.json, then run the humanize skill's full process (mark, draft, check, …

    line 33
  6. Very specific:

    Write the patch to the session scratch directory as JSON holding only the fields that changed (body, title, metaDescription, excerpt), …

    line 38
  7. Distinctive:

    If nothing needed changing, say so and skip the update.

    line 41

≈ “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

Humanize an existing blog draft

Read runtime instructions before running scripts.

Use the humanize skill to do the rewrite and the blog-publish skill for the cms.mjs mechanics.

Use the user's request as the arguments.

Arguments may name a draft by slug or id, optionally with a site (--site <id>); otherwise use defaultSite. Running this command with a target IS the rewrite instruction: do it immediately, without asking for confirmation. If arguments are empty, list current drafts (cms.mjs list --status draft --exclude-assets) with their titles and live-URLs-to-be, then stop; the user re-runs with a slug or id. Drafts with slug sc-assets-* are SocialCue image holders: never list or rewrite them; if one is named as the target, refuse and say why.

Steps:

  1. Run the blog preflight (doctor.mjs --workflow blog --site <id> --text-only).
  2. Resolve the target. An id is used as is. A slug is matched against cms.mjs list --site <id> --exclude-assets (any status; a published article may be humanized too, and it stays published).
  3. Fetch the full article with cms.mjs get --site <id> --id N. get exists for the articles-api adapter only; for wordpress or shopify, say that the adapter has no single-article read yet and stop.
  4. Read the site's voiceSamples, directions and toneGuide from config.json, then run the humanize skill's full process (mark, draft, check, final) on body, title, metaDescription and excerpt. Leave <img> tags, links, code and the tag list untouched. Never ask the user anything; if a sentence needs a detail you do not have, simplify it.
  5. Write the patch to the session scratch directory as JSON holding only the fields that changed (body, title, metaDescription, excerpt), never status, and apply it with cms.mjs update --site <id> --id N --file patch.json. If nothing needed changing, say so and skip the update.
  6. Report: the article's title and live URL, the humanize report line (humanize: N tells fixed (strongest: …)), and the single strongest before/after pair in 3 to 5 lines. Do not update the state file; the article record already exists and its status has not changed.

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