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 swan-gtm/gtm-skills --skill linkedin-ads-ctr-signalgit clone --depth 1 https://github.com/swan-gtm/gtm-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/swan-gtm/gtm-skills/linkedin-ads-ctr-signal)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/linkedin-ads-ctr-signal"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/linkedin-ads-ctr-signal/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/swan-gtm/gtm-skills/linkedin-ads-ctr-signal"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/linkedin-ads-ctr-signal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00082 | $0.01052 |
| Opus 5 | $0.00041 | $0.00526 |
| Sonnet 5 | $0.00016 | $0.00210 |
| Haiku 4.5 | $0.00008 | $0.00105 |
Grade A, and why
linkedin-ads-ctr-signal 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 9d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run this daily to turn LinkedIn Ads engagement into prioritized, pre-drafted outbound. The premise: if a company is clicking your ads at an unusually high rate, they're paying attention right now — reach them while the intent is warm. The skill pulls LinkedIn Ads analytics, finds the high-CTR companies, suppresses anyone you shouldn't touch, and drafts outreach informed by whichever ad themes are actually landing — all saved as drafts for human review, never sent automatically.
When to use it
- You run LinkedIn Ads and want ad engagement to feed outbound instead of sitting in a dashboard.
- You want a daily, low-effort signal that surfaces "who's warming up" without a rep watching analytics.
- You want outreach angles grounded in the messaging your audience is currently responding to.
Skip it if you don't run LinkedIn Ads, or if your motion is purely inbound.
Step 1 — Find the active ad accounts
Pull the LinkedIn ad accounts connected to your org and note the account ID(s). Every analytics query below is scoped to these.
Step 2 — Company-level analytics (the engagement signal)
Query LinkedIn Ads analytics for the last 7 days, pivoted by company, returning impressions and clicks, aggregated across the period, filtered to the active ad accounts. This returns engagement by the LinkedIn company of the member who interacted — the raw intent signal.
Step 3 — Creative-level analytics (ad-theme intelligence)
In parallel, run a second query at the individual-ad (creative) level for the same 7 days — impressions, clicks, and each row's creative reference. Compute CTR per creative and rank by clicks. For the top 5 creatives, fetch the full creative details (post reference, headline, intro text, copy) and build a ranked list: clicks and CTR, headline and intro, and the inferred content theme/angle. If a creative resolves only to a post reference, infer the theme from the campaign name instead — an acceptable fallback. This ranked summary is the ad-theme context passed to every company handled in Step 6.
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.
- 9d ago First seen · 57 lines · 82 tokens per session scan A f274595ade42
linkedin-ads-ctr-signal is a skill published in the GitHub repository swan-gtm/gtm-skills (150 stars, last pushed 2d ago), licensed MIT. It adds 82 tokens to every session and 1,052 once invoked, about $0.0004 per session on Opus 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 2026-09-03.
Other skills, from other repositories
signals-hooks
Comprehensive reactive state hooks for integration with flutterhooks.
signals-dart
Advanced reactive state primitives, collections, mixins, and utilities of signalscore.
signals-flutter
Highly optimized Flutter UI bindings and GPU rendering for reactive signals.
signals-migration-6-to-7
Detailed guidelines, patterns, and rules for migrating codebases from signals.dart version 6.x to version 7.x.
signals-preact-dart
Core reactive programming best practices and primitive definitions for preactsignals in Dart.
signals-lint
Standardized compiler diagnostics, static analysis lints, and automated IDE quick-fixes.