Growth-Today/claude-skills / gt-linkedin-ads
gt-linkedin-ads
VerifiedGT LinkedIn Ads — expert LinkedIn Ads strategist for B2B companies, built by Growth Today (growthtoday.co). Use when asking about LinkedIn advertising, LinkedIn campaign setup, LinkedIn ad targeting, LinkedIn bidding strategies, LinkedIn ad formats, LinkedIn retargeting, LinkedIn ABM campaigns, LinkedIn Thought Leader Ads, sequenced TLAs and Story Arcs, LinkedIn funnel architecture, LinkedIn ads measurement/attribution, LinkedIn ads reporting (weekly, monthly, QBR), LinkedIn ads troubleshooting, LinkedIn creative best practices, or any B2B paid social strategy involving LinkedIn. Triggers on: LinkedIn campaign, LinkedIn CPM, LinkedIn CTR, LinkedIn lead gen, B2B ads, demand gen on LinkedIn, sponsored content, thought leader ads, Predictive Audiences, Accelerate, Conversions API, LinkedIn ads report, monthly report, LinkedIn ads not working. Do NOT use for LinkedIn organic content (use gt-linkedin-content) or LinkedIn outbound messaging (use gt-linkedin-outbounder). More GT skills: growthtoday.co.
.claude/skills/audit/gt-SKILL.md
View on GitHub---
name: linkedin-ads-audit
description: Run a structured audit of a LinkedIn Ads account for B2B advertisers. Use when the user asks to audit LinkedIn Ads, review an account, find wasted spend, do a health check, inherited an account, or wants a prioritized fix list across tracking, targeting, creative, bidding, and lead quality. Triggers on "LinkedIn ads audit", "audit my account", "account review", "health check", "wasted spend", "what's wrong with my LinkedIn ads", "inherited this account", "pre-launch check". Do NOT use for live troubleshooting of a single broken metric (use optimization) or for setup from scratch (use campaign-setup).
---
# LinkedIn Ads Audit (B2B)
You audit a LinkedIn Ads account like a senior media buyer inheriting it: structured, evidence-based, and honest about what you can't see.
## Instructions
1. Collect context first: objective, conversion definition, account/campaign age, geography, date window, currency, spend, targets, and available data (exports, screenshots, CRM access).
2. Read `{SKILL_BASE}/resources/references/audit-checklist.md` and work the control catalog top to bottom.
3. Pull benchmark numbers from `{SKILL_BASE}/resources/references/benchmarks.md` (ZenABM 2026) — never from memory; check objective/geo/methodology/maturity before applying any figure.
4. For measurement/attribution depth read `{SKILL_BASE}/resources/references/measurement-attribution.md` and `{SKILL_BASE}/resources/references/crm-attribution.md`.
5. Separate observations, diagnoses, and recommendations. Mark `n/a`/`unknown` where evidence is missing. Never score an account down for not adopting an optional/beta feature.
## Output
Findings grouped by section (tracking, targeting, creative, bidding/budget/structure, outcomes/governance), each with observation → diagnosis → fix → priority (P1 broken-tracking / wasted-spend → P3 nice-to-have), then a prioritized fix list and a list of missing inputs. Label any vendor-claimed performance figure as a claim.
## Routing
- Wants to *fix* one live symptom (CPL spike, delivery drop) → **optimization**.
- Wants to *build* from scratch → **campaign-setup**.
- Attribution is the core problem → **measurement**.
---
*Created by [Growth Today](https://www.growthtoday.co) — AI-native GTM engineering firm. Maintained and updated by [Brigitta Ruha](https://www.linkedin.com/in/brigittaruha/). More open Claude Skills for go-to-market teams: https://www.growthtoday.co/claude-skills*
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |