agentleFS
ai-search-guruai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool/skills/publish/SKILL.md

publish

Skill432 starsChanged 12 days agoMITView on GitHub

Checks, page fields and a CMS draft. Goes live on its own only if an Admin allows it.

68 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use render, ingest and 4 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • suxrobGMSkill

    render

    Generate raster images (PNG, JPEG, WebP) from natural language prompts using Python rendering engines. Covers graphics, charts, layouts, and procedural art. Not for SVG output.

    Also in 3 projects that use this

  • JaimeGBASkill

    ingest

    Digest an external source (article, paper, transcript, URL, book chapter) and integrate its content into the knowledge base

    Also in 6 projects that use this

  • genomewalkerSkill

    explore

    RLM-style recursive memory exploration - dynamically navigate the memory graph

    Also in 4 projects that use this

  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    Also in 14 projects that use this

  • kt057Skill

    check

    lint, typecheck, test を一括実行して結果をサマリーする

    Also in 3 projects that use this

  • AnthropicSkill

    status

    Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 56 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check each draft: suggestions still waiting, links without an address, claims without a source, a missing FAQ or schema, figures that need …

    line 27
  2. Distinctive:

    Never publish yourself, and never say a page is live before the app says so: the app decides whether a page goes live, and asks the person …

    line 38
  3. Distinctive:

    Don't send a draft that still has waiting suggestions or [placeholders] without saying so.

    line 39
  4. Distinctive:

    Don't invent page fields from data the draft doesn't hold.

    line 40

“Common” is measured: kept by at least 6 in 10 of the 56 edited versions of this file we could read. “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

Ready to publish

Get drafts ready to go live: check them, fill their page fields, hand them to the site's CMS as drafts, and publish them. The app decides whether a page goes live: it asks the person unless an Admin allowed this agent to go live on its own.

When to use

  • "Get the 2 ready drafts published", "Is this draft ready to go live?", "Fill the SEO fields for this page."

What to read

  1. list_drafts: the brand's drafts and their status; the ready ones first.
  2. get_draft for each draft, at most three in one run: its passages, where it is live, and the suggestions still waiting for review.
  3. list_connections: whether the brand has a CMS site connected.
  4. get_site_audit_summary, then list_site_audit_issues, when the page is live already: what its latest audit failed.

Steps

  1. Check each draft: suggestions still waiting, links without an address, claims without a source, a missing FAQ or schema, figures that need a date, [placeholders] still in the text.
  2. Fill the page fields: the URL slug, the SEO title (about 60 characters) and the meta description (about 155 characters), from the draft's own words.
  3. Hand it to the CMS as a draft. If a tool that sends a draft to the site's CMS is offered to you, send the draft; the app asks the person first unless this agent may go live on its own. Otherwise the person uses Send to CMS in the Content Library. A draft isn't live.
  4. Publish only when the person asked for the page to go live, and only a new page: one that is live already is changed in the Content Editor. If a tool that publishes a page is offered to you (Webflow, WordPress or Wix; Framer publishes the whole site, so the person publishes it there), use it once the checks pass. If this agent may go live on its own, the app publishes once its own checks pass too; otherwise the person clicks. Never say a page is live before the app says so.

Output

For each draft: Ready or Not ready, the checks that failed and how to fix them, and the page fields in a small table (Field, Value). Then the next step: Send to CMS, then Publish, and whether it waits for the person's click.

Don't

  • Never publish yourself, and never say a page is live before the app says so: the app decides whether a page goes live, and asks the person unless an Admin allowed this agent to go live on its own.
  • Don't send a draft that still has waiting suggestions or [placeholders] without saying so.
  • Don't invent page fields from data the draft doesn't hold.

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.