start
Skill0 starsChanged 2 months agoMITView on GitHub
Front door to the Meta ads workflows. Works out where you are (no account connected yet, nothing published, campaign live) and routes to the right command, stopping before anything that spends money. Use when the user says "/ads-cooking:start", "run my Meta ads", "help me with Facebook ads", "set up a lead campaign", or is not sure which of the Meta commands they need.
130 other projects use a version of this.
Adopted by
Most recently taken up by
- ansvisor/ansvisortheir own version, first seen Nov 8, 2026
- dsifry/metaswarmtheir own version, first seen Nov 8, 2026
- ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tooltheir own version, first seen Nov 8, 2026
- paulocsb/worldcup-fifa-pooltheir own version, first seen Nov 8, 2026
- srinator22/New-Projecttheir own version, first seen Nov 8, 2026
- Memolok/Claude-plugintheir own version, first seen Nov 6, 2026
Used with
Projects with it also use setup-engine, team-audio and 10 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.
CoralGameSkillsetup-engine
Configure the project's game engine and version. Pins the engine in CLAUDE.md, detects knowledge gaps, and populates engine reference docs via WebSearch when the version is beyond the LLM's training data.
Also in 13 projects that use this
- CoralGameSkill
team-audio
Orchestrate audio team: audio-director + sound-designer + technical-artist + gameplay-programmer for full audio pipeline from direction to implementation.
Also in 13 projects that use this
lilangMaxSkillcreate-stories
Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.
Also in 11 projects that use this
- lilangMaxSkill
story-done
End-of-story completion review. Reads the story file, verifies each acceptance criterion against the implementation, checks for GDD/ADR deviations, prompts code review, updates story status to Complete, and surfaces the next ready story from the sprint.
Also in 11 projects that use this
- +5 more from CoralGame
- +3 more from lilangMax
Other versions130 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 130
- anthropics/knowledge-work-plugins★ 35ksame name
- Donchitos/Claude-Code-Game-Studios★ 27ksame name
- openai/plugins★ 7.8ksame name
- SterlingChin/marvin-template★ 1ksame name
- educlopez/ui-craft★ 441same name
- ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool★ 432same name
- dsifry/metaswarm★ 426same name
- pixel-cellar/Claude-Code-Game-Studios★ 324same name
- ansvisor/ansvisor★ 233same name
- alexeykrol/claude-code-starter★ 194same name
120 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 4 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 117 edited versions we read keep these.
4
Distinctive
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
- Distinctive: line 12
Every command in this kit is run exactly this way, from any folder:
- Distinctive: line 18
No install step, no virtualenv, no dependencies.
- Distinctive: line 34
Check in this order and stop at the first thing that is not true:
- Very specific: line 36
Is there a config folder?: Look for ads-cooking/ in the current project, then ~/.ads-cooking/.
- Very specific: line 40
Does the token work?: Run /ads-cooking:check. If it fails, fix that before anything else.
- Very specific: line 42
Is anything published?: Read campaign.json. An empty live.ad_id means nothing exists yet.
- Distinctive: line 44
Something is live: Ask what they want:
- Very specific: line 67
If Meta returns an error, read ${CLAUDE_PLUGIN_ROOT}/context/api-notes.md before guessing.
“Common” is measured: kept by at least 6 in 10 of the 117 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Meta Ads Kit
Routes to the right workflow. Does none of the work itself.
The command form
Every command in this kit is run exactly this way, from any folder:
PYTHONPATH="${CLAUDE_PLUGIN_ROOT}" python3 -m adscooking <command>No install step, no virtualenv, no dependencies.
Check Python before anything else. It needs 3.10 or newer. On a Mac that has never had
developer tools installed, python3 is a stub that opens an Apple installer dialog, so without
this the first thing a new user meets is that dialog rather than a sentence from us:
python3 --versionOlder than 3.10, or no output: tell them to run xcode-select --install, or to get a current
Python from https://www.python.org/downloads/. /ads-cooking:connect checks this too and stops
with the same advice.
Work out where they are
Check in this order and stop at the first thing that is not true:
- Is there a config folder? Look for
ads-cooking/in the current project, then~/.ads-cooking/. Nothing there means they have never set this up. Run/ads-cooking:connect. Do not create the folder by hand:connectis the only path that sets the file permissions and proves git cannot commit the token. - Does the token work? Run
/ads-cooking:check. If it fails, fix that before anything else. Everything downstream fails in more confusing ways. - Is anything published? Read
campaign.json. An emptylive.ad_idmeans nothing exists yet. Run/ads-cooking:publish. - Something is live. Ask what they want:
- See how it is doing →
/ads-cooking:pulse - Change the wording →
/ads-cooking:copy - Change the form questions →
/ads-cooking:form
- See how it is doing →
The commands
| Command | What it does | Spends money? |
/ads-cooking:connect | Connect an ad account, ending with a working token | No |
/ads-cooking:check | Prove the token reaches the account, page and forms | No |
/ads-cooking:publish | Create the campaign, dry run unless told otherwise | Only with --go, and paused |
/ads-cooking:copy | Swap in new ad copy | Changes a live ad with --go |
/ads-cooking:form | Publish changed lead form questions | Changes a live ad with --go |
/ads-cooking:pulse | Read-only check of spend, leads and cost per lead | No, never |
Rules that hold across all of them
- Never run a
--gocommand without the user asking for it in that turn. Dry run first, show them what it would do, then wait. This is someone's advertising budget. - Never set anything ACTIVE. The kit creates everything paused on purpose. Going live is a person's decision, made in Ads Manager where they can see the preview.
- Never print the token, or paste it into a file the user is reading, or into chat.
- If Meta returns an error, read
${CLAUDE_PLUGIN_ROOT}/context/api-notes.mdbefore guessing. Most of the confusing ones are in there with the actual fix.
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
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.