AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Workflow Automation/
claude-ads
claude-ads logo

claude-ads

Active·★ 11.1k·MIT·Updated 2026-11-01
★ Most Popular

Claude Ads is relevant to teams that already have advertising data and need a consistent way to organize findings and supporting evidence. It connects exports, missing inputs and reports through inspectable artifacts. Before evaluating the usefulness of generated recommendations, we would check whether those artifacts faithfully represent the supplied data.

The most important finding is that this revision does not enable account-health scoring. All twelve platform profiles are disabled. With insufficient evidence, the actual result was health_score: null and insufficient_evidence. This is not a tool that our test established can turn any export into a reliable account score. An absent score also does not mean an account is performing badly.

On November 4, 2026, we fixed commit fc3908e786c318776df89a3a098333da377364be and ran the deterministic core with Python 3.12.13. The core declares version 2.0.0, but the commit should accompany that number when reproducing this review. The README describes the repository as a development candidate.

Read the full review, verification scope and sources →

Hands-on tested · Tested on 2026-11-04 with core 2.0.0 at fc3908e786c318776df89a3a098333da377364be (deterministic evidence path).

Setup: CPython 3.12.13, macOS arm64; synthetic daily CSV and the upstream local demo with its returned policy root

Commands run

python3.12 doc/review-fixtures/claude-ads/verify.py --source-root <pinned-checkout>

What we saw

  • Two synthetic daily rows normalized to USD 20; duplicate grain, mixed currencies and negative spend were rejected.
  • Unknown findings validated, invalid status and invented control IDs failed; all twelve health profiles stayed disabled with null score.
  • A local synthetic HTML report rendered, while a forged health score was rejected before writing. No credentials, account, model, delivery or ROI test.

Data as of 2026-11-12.

License
MIT
Latest release
v2.1.0 · 2026-10-16
Last commit
2026-11-01
Contributors
2
Forks
1,591
Open issues and PRs
5
First published
2026-02-11

Source: GitHub, npm and PyPI public APIs.

#agent-skills#ai#ai-marketing#claude-code#claude-code-skill#dev-tooling#google-ads#marketing-automation
$ Install
$ /plugin marketplace add agricidaniel/claude-ads && /plugin install claude-ads@ai-marketing-hub-claude-ads
↗ Visit site★ GitHub
01

Features

01/ads audit reports passed, failed and unchecked items, each with its evidence
02/ads plan produces channel, budget, measurement and competitor plans
03/ads create makes copy, image, video and product-photo briefs and assets
04/ads monitor checks pacing, delivery, tracking, ad fatigue and policy
05/ads optimize --draft writes suggested changes as drafts
02

Why choose it

+The tested CSV adapter rejected duplicate observation grain, mixed currencies and negative spend instead of silently aggregating them.
+Unknown findings remain explicit; disabled profiles returned no invented account-health score.
+The tested renderer rejected a forged score before writing an HTML report.
03

Trade-offs

!The pinned repository is a development candidate and all twelve account-health scoring profiles are disabled.
!Generic CSV headers and additive grain must be mapped correctly; this is not proof that every platform export works unchanged.
!Our local evidence checks establish no model-audit quality, live-account capability or advertising-return result.
05

Maintenance check

ActiveChecked: 2026-11-10
Last commit
2026-10-17
Commits, last 90 days
43
Releases, last 90 days
5
Latest release
v2.1.0 (2026-10-16)
Open issues
5
Recent issues with at least one comment
15/16
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 4, 0, 13, 0, 0, 0, 3, 19, 0, 0, 0, 0

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #98 Main plugin does not install on claude.ai: plugin name "claude-ads" is reserved0 comments · 2026-10-20

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

04

Who it fits

Pick it if
  • You have export data and need traceable findings, unknowns and reports.
  • You can reconcile data grain and totals before testing the skill in your chosen host.
Look elsewhere if
  • You need an enabled account-health score or a verified improvement in advertising returns.
  • You expect the generic export adapter to qualify every live platform integration automatically.
06

Compatibility

Claude Code
Canonical host per README; host activation not tested here
Verified via docs
Python
Core tested on CPython 3.12.13
Verified via docs
07

Quick start

1
$ /plugin marketplace add agricidaniel/claude-ads
2
$ /plugin install claude-ads@ai-marketing-hub-claude-ads
08

Use cases

↳Audit a Google Ads account from a CSV or JSON export
↳Decide how to split budget across channels
↳Design a test or read out the result of a finished ad experiment
09

Alternatives

⚡Top VS:
VSlinkedin-skills★6.0k→VShermes-agent★264.2k→VSclaude-blog★2.8k→VSnanoclaw★31.1k→
linkedin-skills logo
linkedin-skills★ 6.0k
Claude skills for LinkedIn. 12 Claude Code and Codex skills that write human-sounding LinkedIn posts, craft comments that get noticed, analyze your feed, and build a publishing cadence, all from your terminal. Content engineering by Creative Content Crafts. MIT.
VSCompare→
hermes-agent logo
hermes-agent★ 264.2k
The agent that grows with you
VSCompare→
claude-blog logo
claude-blog★ 2.8k
Free, open source blog writer for Claude Code. Researches current sources, writes answer-first posts for Google and AI answers, has an independent reviewer score each one out of 100 and ships only after five delivery gates. 32 skills, 30 /blog commands, 5 agents. Active development at AI-Marketing-Hub/claude-blog; public releases ship here.
VSCompare→
nanoclaw logo
nanoclaw★ 31.1k
A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK
VSCompare→
dashi-ppt-skill logo
dashi-ppt-skill★ 10.8k
An AI-agent skill that generates browser-editable presentations from multiple visual themes, exportable to HTML, PDF, and PPTX.
VSCompare→
taste-skill logo
taste-skill★ 117.7k
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
VSCompare→
impeccable logo
impeccable★ 112.2k
The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.
VSCompare→
diagram-design logo
diagram-design★ 67.9k
Editorial diagram design for Claude Code, Codex, GitHub Copilot, Cursor, Factory Droid, Qoder, and Pi. 45 diagram types. Self-contained HTML + SVG. No shadows. No Mermaid slop.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs05Maintenance check04Who it fits06Compatibility07Quick start08Use cases09Alternatives
AgriciDaniel /
claude-ads
↗

Organize advertising evidence and findings without inventing missing scores

11.1k1.6kMIT
Last commit2w ago
StatusActive
CategoryWorkflow Automation
Contributors2
Latest releasev2.1.0
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.