This runs a 28-point audit of TikTok ad accounts, weighted heavily toward creative quality because TikTok is a creative-first platform where your hook and vertical video format matter more than targeting finesse. It checks technical basics like Pixel and Events API setup, but the real value is in evaluating whether you have enough creative variants per ad group, whether your videos respect the safe zone (X:40-940, Y:150-1470), and if you're testing Spark Ads and Smart+ campaigns. Also assesses TikTok Shop integration if you're running e-commerce. Outputs a scored report with pass/warning/fail status on each check. Use this when you need to diagnose why TikTok campaigns aren't performing or before scaling spend.

skills.sh installs
4.3K
GitHub stars
10.9K
last updated
Aug 21, 2026

Install

$ npx -y skills add agricidaniel/claude-ads --skill ads-tiktok --agent claude-code

Installs into .claude/skills of the current project.

Files

TikTok Ads Audit

Procedure

  1. Read the main ads operating contract and thinking framework.
  2. Collect objective, conversion definition, account and campaign age, geography, date window, timezone, currency, spend, targets, and available data sources.
  3. Read ads/references/tiktok-audit.md (resolve it from the plugin root, the directory that holds ads/ and skills/, or from the skills directory in a standalone install) and only the relevant shared measurement, benchmark, creative, automation, policy, and scoring references.
  4. Normalize inputs and retain lineage to each export, screenshot, API result, or manual value.
  5. Evaluate applicable controls covering measurement, mobile-native creative, audiences, Smart+, commerce, bidding, budgets, pacing, attribution, and policy.
  6. Separate observations, diagnoses, recommendations, opportunities, and proposed mutations. Mark uncertainty and contradictions.
  7. Return schema-valid findings to the conductor. Do not calculate final scores in the prompt or write a shared result file.
  8. Render a platform report only from the validated JSON run bundle.

Boundaries

Sponsors

Details

Repository
github.com/agricidaniel/claude-ads
Categories
Backend & APIs, Mobile Development
First seen
May 16, 2026

More from agricidaniel/claude-ads

All 23
1dotnet avatartest-gap-analysisdotnet/skillsPerforms pseudo-mutation analysis on production code in any language to find gaps in existing tests. Use when the user asks to find weak or shallow tests, disco4.3Kskills.sh installs
2jeffallan avatarvue-expert-jsjeffallan/claude-skillsCreates Vue 3 components, builds vanilla JS composables, configures Vite projects, and sets up routing and state management using JavaScript only — no TypeScrip4.3Kskills.sh installs
3ant-design avatarant-designant-design/antd-skillDecision guide for antd 6.x, Ant Design Pro 5/ProComponents, Ant Design X v2, and the offline `@ant-design/cli`. Use for component selection, theming/tokens, SS4.3Kskills.sh installs
4trailofbits avatartrailmark-structuraltrailofbits/skillsRuns full Trailmark structural analysis by building a graph, running `preanalysis()`, and reporting hotspots, taint, blast radius, privilege boundaries, attack 4.3Kskills.sh installs
5getsentry avatarsentry-create-alertgetsentry/sentry-for-aiCreate Sentry alerts using the workflow engine API. Use when asked to create alerts, set up notifications, configure issue priority alerts, or build workflow au4.2Kskills.sh installs
6upstash avatarupstashupstash/skillsWork with any Upstash TypeScript/JavaScript SDK including Redis, Box, QStash, Workflow, Vector, Search and Ratelimit. Use when the user is working with any Upst4.2Kskills.sh installs