TikTok Shop Video Generator
Turn any viral TikTok video into an ad for your own product in one click. For TikTok Shop sellers and affiliates — no filming, no editing. Free to try.
Adwarp is a free, open-source ad agent that runs in your terminal. Size audiences, draft campaigns and pull reports on LinkedIn Ads and Google Ads.
MarketingJavaScriptGitHub @adwarp-devOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
Owners of public repositories under a personal GitHub account can sign in to verify ownership and manage the introduction themselves. No administrator approval is needed.
Sign in, generate a verification file, and commit it to this repository’s default branch within 30 minutes. Files on other branches or forks do not count. Then check the file below to manage the project without administrator approval. Keep the file to retain your access.
If needed, you will go to sign-in. After signing in, return here and press your chosen verification button again.
Run /nomorevibe verify in your project folder to verify ownership and manage the introduction yourself.
Verify in one minuteAsk about other verification options
Paid ads skills for Claude Code, Codex and Cursor. LinkedIn Ads and Google Ads audits, reviews, pause rules and launch briefs, from a CSV export or live through Adwarp.
Taken from the repository README
Loading the full README.
Read the full README ↗Skills for performance marketers who run LinkedIn Ads and Google Ads with an AI agent. Each one is a playbook your agent follows: what to pull, how to judge it, the thresholds that matter, and a report you can act on the same day.
They work in Claude Code, Codex, Cursor and any agent that reads SKILL.md files. Every skill runs from a CSV export, so you don't need another tool. If you use Adwarp, the free, open-source ad agent, the same skills pull live data and draft the changes for you.
| Skill | Ask it | What you get |
|---|---|---|
linkedin-ads-audit | "Audit my LinkedIn ads account" | A scored check of tracking, structure, targeting, delivery settings, bidding, creative and UTMs, with fixes ranked by the spend at risk |
linkedin-ads-performance-review | "How are my LinkedIn ads doing?" | Scale, pause and watch lists, week over week direction and creative fatigue, with floors so small numbers don't drive decisions |
linkedin-ads-spend-analysis | "Where is my LinkedIn budget going?" | Where the money goes, how concentrated it is, spend with nothing back, and the reallocation moves worth making |
linkedin-ads-lead-drivers | "Which LinkedIn ads drive leads?" | A drivers list, a pause list with the money each ad burned, and the copy angles that convert |
linkedin-ads-pause-rules | "Which LinkedIn ads should I pause?" | Pause rules you approve up front, and a dry-run table before anything is switched off |
linkedin-audience-sizing | "How big should this audience be?" | A narrowing plan that lands the audience in range before you spend |
linkedin-audience-ops | "Audit my matched audiences" | Audience health (stuck, too small, stale, unused), clean list uploads with a dry run, and CRM refreshes |
linkedin-abm-builder | "Build 1:1 ads for these accounts" | An ad set plan per account: the audience, 3 ads and a fixed flight |
linkedin-campaign-launch | "Launch a LinkedIn campaign for this" | A confirmed brief, sized before spend, built with safe defaults, created as drafts |
linkedin-ad-library-teardown | "What LinkedIn ads is this company running?" | Themes, offers, formats, run length and the gaps you can use |
| Skill | Ask it | What you get |
|---|---|---|
google-ads-account-audit | "Audit my Google Ads account" | 40 to 50 checks with a GAQL query for each, and the fixes ranked |
google-ads-search-campaign-builder | "Build a search campaign for this product" | Keywords, structure and responsive search ads, ending in a paused launch brief |
google-ads-search-terms | "Where is my search budget leaking?" | Wasted spend and negative keyword candidates from the search terms report |
| Skill | Ask it | What you get |
|---|---|---|
paid-media-weekly-report | "Write the weekly paid report" | The last 7 days against the 7 before, the movers, flags and 3 actions |
paid-media-health-check | "Anything on fire in our ads?" | A daily check that stays silent unless something is wrong: no delivery, spend spikes, cost blowouts, spend with nothing back |
ad-experiment-lift | "Did that change work?" | A hypothesis logged before the change, then before and after lift with the confounds stated |
ad-budget-pacing | "Are we on pace this month?" | Projected spend against your cap, quiet unless spend runs ahead |
With the open skills installer, for Claude Code, Codex, Cursor and other agents:
npx skills add adwarp-dev/paid-ads-skills
As a Claude Code plugin:
/plugin marketplace add adwarp-dev/paid-ads-skills
/plugin install paid-ads-skills@adwarp
Or copy any folder under skills/ into ~/.claude/skills/, or into your agent's skills folder. Each folder is self-contained.
From an export. Download the report the skill asks for from Campaign Manager or Google Ads, put the CSV in your working folder, and ask. Nothing connects to your ad account.
Connected, through Adwarp. Adwarp is a free, open-source MCP server and CLI for LinkedIn Ads and Google Ads. With it installed, the skills pull live data and can draft the changes they recommend. Everything Adwarp creates on LinkedIn starts as a draft, and Google campaigns start paused. Setup takes about 15 minutes: adwarp.dev/docs/install. For Google Ads reads, Google's official read-only MCP server works too.
The skills only read by default. A skill that can change an account, like pausing ads or drafting a campaign, shows you the exact change first and acts only after you confirm. Changes go through Adwarp, which creates LinkedIn drafts and paused Google campaigns, so nothing spends until you switch it on.
Every benchmark in a skill cites a public source and the date it was checked. Thresholds that are judgment calls, like waiting for 1,000 impressions before calling an ad, are labeled as defaults you can change. The data under examples/ is made up, for trying the skills out.
Not affiliated with or endorsed by LinkedIn or Google. MIT licensed, maintained by Stan Rymkiewicz.