Skip to content
SkillModel-led174 tokens in use

Ad Budget and Bidding

Plans and reviews paid media budgets, bidding and pacing from break-even boundaries and marginal returns, and returns a plan with owners and rollback triggers.

11,191 stars on the repository MIT LicenseAgriciDaniel/claude-ads · skills/ads-budget
/plugin marketplace add agricidaniel/claude-ads /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 Ad Budget and Bidding costs

62tokens idle
174tokens 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
  • Structure11/25
  • Examples0/15
  • Output12/15
  • 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

The budget skill helps decide how much to spend and where. It starts from the objective, conversion value, gross margin, cash limits, sales capacity, attribution uncertainty and seasonality, then compares hold, reallocate, scale, reduce or experiment options.

The result is a decision-complete plan: amount per platform or campaign, timing, owner, guardrails, success measure and rollback trigger. Calculations are handed to the ads-math skill.

What You Get

  • Break-even boundaries with shown formulas and sensitivity cases
  • A comparison of hold, reallocate, scale, reduce and experiment options
  • A budget plan with amounts, timing, owner, guardrails and success measure
  • Rollback triggers for each change

Common Use Cases

  • Splitting a monthly budget across Google, Meta and TikTok
  • Deciding whether to scale a campaign that meets its ROAS target
  • Reviewing pacing and bidding strategy before a seasonal peak
  • Setting a reserve for tests

What Makes It Unique

It treats common rules as optional heuristics. Fixed splits like 70/20/10, fixed CPA multiples, budget-to-CPA ratios and fixed percentage scaling are never authorization on their own. Margin, cash constraints and sales capacity are inputs from the start.

Under The Hood

This is a prompt-only skill with no scripts. The agent works from the numbers you supply, shows its formulas and inputs, and points to the ads-math skill for calculations and forecasts. It makes no calls and writes no files by itself, and any account change it suggests stays a draft until the main mutation gate passes.

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