Skip to content
SkillModel-led205 tokens in use

ads-launch

Turn a campaign plan into a draft launch plan with exact objects, before and after state, rollback and an audit trail, applied only after approval.

11,191 stars on the repository MIT LicenseAgriciDaniel/claude-ads · skills/ads-launch
/plugin install claude-ads@ai-marketing-hub-claude-ads
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing ads-launch costs

45tokens idle
205tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Fair
  • Frontmatter8/15
  • Structure12/25
  • Examples0/15
  • Output10/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity84
  • Maintenance100
  • Community56
  • Maturity32
  • Momentum40

ads-launch prepares a paid-ad campaign launch. By default it runs as a draft: it loads your setup profile, account snapshot, campaign plan, creative manifest, capability manifest, policy findings and tracking checks, and produces a mutation plan without touching the account.

An apply run needs the exact operation to be enabled and tested, plus explicit approval of that plan. Missing budget ceilings, stale account state, incomplete tracking or a failed policy review block it.

What You Get

  • A deterministic mutation plan listing the exact proposed objects and their before and after state
  • Blast radius, learning impact, owner, success measure and verification window for the launch
  • An idempotency key, audit destination and rollback for each change
  • A clear refusal that names what is missing when inputs are incomplete

Common Use Cases

  • Preparing a new campaign launch for review by the account owner
  • Checking that tracking, policy and creative are ready before activating ads
  • Writing an auditable record of what a launch will change
  • Applying an approved plan with the smallest reversible change

What Makes It Unique

Many ad automation tools push changes as soon as they are asked. This skill defaults to a draft and treats applying as a separate, gated step: the operation must be enabled and independently tested, the exact plan must be approved, and remote state is verified before and after. Permanent deletion is not supported at all.

Under The Hood

The skill is a short instruction file that loads files produced by the other Claude Ads skills (setup profile, account snapshot, plan, creative manifest, capability manifest) and writes a mutation plan. In apply mode it asks the platform adapters to change the live ad account, so it can reach advertising platform APIs and write an audit and rollback record. It does not ship its own scripts.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers