Skip to content
Agentmart
Submit a tool

adspirer-search-optimize

Analyze Google paid-search waste and budget pacing, inspect Microsoft campaigns, and apply only explicitly approved changes.

Skill by Adspirer

IndexedMIT
Write a review

Chalk Labs

Need help deploying adspirer-search-optimize?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/adspirer-adspirer-search-optimize

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Analyze Google paid-search waste and budget pacing, inspect Microsoft campaigns, and apply only explicitly approved changes.

Use cases: finance

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/adspirer-search-optimize

What's inside

Skill name
adspirer-search-optimize
Description
Analyze Google paid-search waste and budget pacing, inspect Microsoft campaigns, and apply only explicitly approved changes.
License
MIT
Instructions
44 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Cutting waste and pacing budgets

Adapted from adspirer-optimize. Load adspirer-search-mcp and the relevant platform skill.
Propose changes, then execute only after approval of the specific action and account.

## Find waste

Discover Google analyze_wasted_spend and analyze_search_terms through google_ads_read. For Microsoft, inspect available campaign configuration; do not invent equivalent reporting tools.
Distinguish zero conversions, high CPA, irrelevant traffic, placement/audience mismatch,
tracking gaps, and weak creative. Do not label small samples or conversion lag as failure.

## Before cutting

Check audit_conversion_tracking where supported. Broken tracking limits conversion-based
decisions; missing events do not prove no business results occurred.
Assess sample size, spend relative to the goal, attribution, and upper-funnel contribution.
Avoid universal click counts, CPA multiples, or frequency cutoffs as automatic pause rules.

## Propose the smallest effective change

For irrelevant search terms, propose negatives with exact scope and match type before broad pauses.
Consider exclusions or creative tests, then pausing the narrowest resource needed.
Prefer reversible actions. Deletion/removal requires explicit authorization and explanation
of what is actually irreversible; do not assume all historical reporting disappears.
Do not automatically apply the output of a tool whose name says optimize.

## Budget allocation and pacing

Compare period spend with elapsed time, remaining budget, and campaign constraints.
Show proposed before/after amounts, daily/monthly implications, account currency, and total.
Identify what constrains delivery before recommending more budget.
Avoid fixed percentage increases or promises that reallocations will yield a set number of leads.
Label forecasts as conditional estimates. Discover budget-tool schemas and check whether
an operation recommends or mutates before calling it.

## Verify and repeat

After approved changes, read back affected resources and report partial failures honestly.
Inspect state before retrying uncertain writes. Do not enable paused campaigns implicitly.
Offer a host schedule only if supported and authorized; disclose quota implications.
The specialist endpoint does not expose the main monitoring_and_reporting router.
Do not claim continuous monitoring unless an actual configured scheduler confirms it.

From Adspirer/adspirer-search-ads-cursor-plugin, MIT.

More from Adspirer/adspirer-search-ads-cursor-plugin

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 8, 2026 (23 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Adspirer

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get adspirer-search-optimize running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying adspirer-search-optimize?

CallGet help
Cite this page

adspirer-search-optimize skill. Agent Mart. https://agentmart.dev/skills/adspirer-adspirer-search-optimize (last updated 2026-10-24)