Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add coupler-io/skills --skill tiktok-ads-audience-targeting-analysisgit clone --depth 1 https://github.com/coupler-io/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/coupler-io/skills/tiktok-ads-audience-targeting-analysis)<a href="https://agentmods.dev/skills/coupler-io/skills/tiktok-ads-audience-targeting-analysis"><img src="https://agentmods.dev/badge/skills/coupler-io/skills/tiktok-ads-audience-targeting-analysis/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/coupler-io/skills/tiktok-ads-audience-targeting-analysis"><img src="https://agentmods.dev/badge/skills/coupler-io/skills/tiktok-ads-audience-targeting-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00113 | $0.02983 |
| Opus 5.5 | $0.00045 | $0.01193 |
| Sonnet 5.5 | $0.00023 | $0.00597 |
| Haiku 4.5 | $0.00011 | $0.00298 |
Grade A, and why
tiktok-ads-audience-targeting-analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TikTok Ads Audience Targeting Analysis
Shows which TikTok audiences bring results and whether your targeting does better than simply going broad. TikTok Ads Audience Targeting Analysis is a Coupler.io AI agent skill that works with live data from TikTok Ads.
Tells you which audiences earn their spend on TikTok, and whether your targeting is doing any work the creative was not already doing.
TikTok is the one major platform where the honest answer to "which audience should I target" is often "none of them". Delivery is creative-led: the same video handed to a tight interest stack and to broad frequently lands on similar people at similar cost, and the tight stack pays a premium for the privilege. But nobody can prove that from Ads Manager, because the interface shows what was targeted, not what was reached — and those are different things once the system starts optimising. Meanwhile the audience report holds age, gender, interest and behaviour breakdowns that most accounts never open.
What you get back
- A segment table ranked on cost per result, not on volume, with the volume floor stated so you know which lines are real.
- The targeting-versus-creative read — how much of the variance between ad groups is explained by who they targeted and how much by which video ran, computed across ad groups that share creative.
- The demographic picture — age and gender by cost per result and conversion rate, with the bid and exclusion moves each one supports.
- The interest and behaviour verdict — which segments beat broad, which match it, and which are paying a premium for nothing.
- The reached-versus-targeted caveat, priced — how much of the account's spend sits in ad groups where the delivered audience has drifted from the intended one.
- A coverage statement for anything the data could not answer.
Read-only. It never changes targeting or a bid.
Call budget
| Calls to a spoken answer | |
|---|---|
| Cold — nothing known | find the dataset → coverage verdict (spoken) → one combined query = 3 |
| Warm — dataset already known | coverage verdict (spoken) → one combined query = 2 |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 217 lines · 113 tokens per session scan A d1013b767cc4
tiktok-ads-audience-targeting-analysis is a skill published in the GitHub repository coupler-io/skills (41 stars, last pushed 4d ago), licensed MIT. It adds 113 tokens to every session and 2,983 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-15.
tiktok-ads-audience-targeting-analysis compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tiktok-ads-audience-targeting-analysiscoupler-io/skills | Skill | 41 | 4d ago | MIT | A | 113 | Claude Code |
| jobs-to-be-donewondelai/skills | Skill | 2.8k | today | MIT | A | 137 | Claude Code |
| remotion-best-practicesguanyang/open-agent-hub | Skill | 1.0k | yesterday | MIT | A | 116 | Claude Code |
| asc-subscription-localizationrorkai/app-store-connect-cli-skills | Skill | 1.1k | 6d ago | MIT | A | 60 | Claude Code |
| etsy-social-media-marketingnexscope-ai/eCommerce-Skills | Skill | 1.5k | 11d ago | MIT | A | 23 | Claude Code, Codex |
| walmart-price-trackernexscope-ai/eCommerce-Skills | Skill | 1.5k | 11d ago | MIT | A | 0 | Claude Code, Codex |
| happiness-skillkangarooking/cangjie-skill | Skill | 13k | 1mo ago | MIT | A | 136 | Claude Code, Codex |