agentleFS
Sign inStart free
windsor-aiwindsor-ai/claude-windsor-ai-plugin/skills/windsor-optimize/SKILL.md

windsor-optimize

Skill1 starsChanged 50 days agoMITView on GitHub

Find and fix wasted ad spend across Google Ads, Meta Ads, TikTok Ads, LinkedIn Ads, Microsoft Ads and Amazon Ads through Windsor.ai - spend with no conversions, campaigns and ad sets far above the account's cost per conversion, non-converting search terms, and budgets on paused-worthy items. Use when the user asks where money is wasted, how to cut spend, or to optimize campaigns. Proposes changes and applies them only after explicit approval.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 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.

  • 3

    Very specific

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

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

    Call get_connectors and list the connected ad accounts.

    line 11
  2. Distinctive:

    Use the last 30 days unless the user gives a range.

    line 12
  3. Distinctive:

    Wait for an explicit yes to the exact list.

    line 25
  4. Very specific:

    Call list_actions for each connector and build params from the returned schema (pause_campaign, pause_adset, set_campaign_budget and …

    line 26
  5. Very specific:

    Call execute_action once per approved change and report what changed, before and after, and anything the platform rejected.

    line 27
  6. Distinctive:

    If write actions are not enabled for the account, send the user to https://onboard.windsor.ai/app/settings/account and retry after they …

    line 28

≈ “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

Optimize ad spend

Find spend that is not paying off, show the evidence, and apply the fixes the user approves.

1. Scope

  • Call get_connectors and list the connected ad accounts. Ask which accounts to include if there are several; default to all. If there are more than five accounts or several clients, delegate the read to the portfolio-analyst agent instead of reading them all here.
  • Use the last 30 days unless the user gives a range. State the currency per account and never sum across currencies.

2. Find waste, per platform

For each ad connector, read field ids from get_fields first, then call get_data with campaign (and ad set or ad group) name and id, spend, clicks, impressions and conversions.

  • Zero-conversion spend: items with spend above zero and no conversions, sorted by spend.
  • Expensive conversions: items whose cost per conversion (spend / conversions) is more than twice the account average; show both numbers.
  • Search terms (Google Ads): hand off to /search-terms for the negative keyword flow.
  • Ignore items with too little data to judge (for example under 1,000 impressions) and say so.

3. Propose

Present one table per account: item, spend, conversions, cost per conversion, suggested action (pause, lower budget by an absolute amount, or add negatives), and the expected saving. Never propose touching brand campaigns or items the user marked as intentional.

4. Apply only what is approved

  • Wait for an explicit yes to the exact list. Partial approval is fine.
  • Call list_actions for each connector and build params from the returned schema (pause_campaign, pause_adset, set_campaign_budget and similar; the live set is what list_actions returns). Google Ads budgets are in micros; show both values.
  • Call execute_action once per approved change and report what changed, before and after, and anything the platform rejected.
  • If write actions are not enabled for the account, send the user to https://onboard.windsor.ai/app/settings/account and retry after they confirm.

Hand-offs

  • Reporting only -> /windsor-insights
  • Creating replacement campaigns or ads -> /windsor-create
  • More than five accounts or several clients at once -> portfolio-analyst agent

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