agentleFS
Sign inStart free
lilly-buildslilly-builds/ads-cooking/skills/publish/SKILL.md

publish

Skill0 starsChanged 2 months agoMITView on GitHub

Create a Meta lead campaign from a config file: campaign, ad set, video, thumbnail, lead form, creative and ad. Shows exactly what it would do first and creates nothing until told to go, then creates everything paused. Use when the user says "/ads-cooking:publish", "publish my campaign", "launch the ad", "create the Meta campaign", or has a video and copy ready and wants it live.

60 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use create, render and 8 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.
  • MicrosoftSkill

    create

    Also in 4 projects that use this

  • 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

  • GoogleSkill

    translate

    Translates a common phrase into one or more languages.

    Also in 3 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

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 49 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run it again. Any id already in the live section is reused rather than recreated, so a failure at the lead form step does not re-upload the …

    line 37
  2. Distinctive:

    Add a Privacy Policy URL in App Settings, then flip App Mode to Live.

    line 45
  3. Very specific:

    Never run --go without the user asking in that turn.

    line 51
  4. Distinctive:

    Never set anything ACTIVE.

    line 52
  5. Distinctive:

    If the dry run warns about the privacy policy URL, stop and get a real one.

    line 53

“Common” is measured: kept by at least 6 in 10 of the 49 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

Publish a campaign

Seven steps in one command. Two safety rules hold throughout: nothing is created without --go, and everything that is created is PAUSED.

Always dry run first

PYTHONPATH="${CLAUDE_PLUGIN_ROOT}" python3 -m adscooking publish

This sends nothing. It prints the budget, the audience, the placements, the creative and where leads land. Show the user that summary and wait. Do not run the next command in the same turn.

Then, only if they say yes

PYTHONPATH="${CLAUDE_PLUGIN_ROOT}" python3 -m adscooking publish --go

It prints the ids it created. Paste them into the live section of campaign.json, or copy, form and pulse will not know what to change.

After it runs

Everything is paused. Tell them the last step is theirs: open Ads Manager, look at the ad preview and click through the lead form, then set the campaign, ad set and ad to active. That last click is deliberately not automated.

If it fails partway

Run it again. Any id already in the live section is reused rather than recreated, so a failure at the lead form step does not re-upload the video. Fill in what it printed before it failed.

Errors worth knowing before you debug

Full list with fixes in ${CLAUDE_PLUGIN_ROOT}/context/api-notes.md. The two that stop people:

  • "created by an app that is in development mode" means the app is still in Development. Add a Privacy Policy URL in App Settings, then flip App Mode to Live. Nothing else will fix it.
  • "Terms of Service Not Accepted" means the Page has never accepted the lead ads terms. Open the Forms Library for that page once and accept.

What not to do

  • Never run --go without the user asking in that turn.
  • Never set anything ACTIVE.
  • If the dry run warns about the privacy policy URL, stop and get a real one. Meta rejects the form otherwise, and it fails at step 5 after the video has already uploaded.

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