12 Claude Skills for LinkedIn Ads

LinkedIn Ads is not just expensive search with a different logo. It reaches buyers by job title, seniority, and company, it costs several times what other networks cost per click, and it reports leads that your sales team quietly throws away. Running it well is its own discipline, and generic paid-media advice does not cover it.

This is a free, open-source pack of 12 Claude Skills for running LinkedIn Ads like the pipeline channel it is supposed to be, not the form-fill machine it defaults to. Each skill is a self-contained SKILL.md file with explicit triggers, required inputs, an analysis workflow, decision rules, a worked example, and guardrails. Drop them into Claude and they activate when the conversation matches. Every skill is data-first: it reads the Campaign Manager export or the CRM numbers you give it, tells you when data is missing, stops at an approval-ready recommendation, and never touches your ad account.

Why LinkedIn Ads needs its own pack

Three things make LinkedIn its own discipline, and this pack is built around them.

1. The demographics layer. LinkedIn shows you delivery by job title, seniority, function, company industry, and company size. No other major ad platform exposes budget waste at that firmographic granularity, and almost nobody audits it.
1. The lead-quality gap. LinkedIn reports a cheap cost per lead. Sales bins most of those leads. The reported number and the pipeline number disagree more here than on any other channel, so reconciliation against the CRM is core, not optional.
1. Small audiences and high costs. Tiny B2B audiences fatigue fast, costs run high, and two quiet levers (Audience Expansion and the LinkedIn Audience Network) leak budget to off-target members by default.

The two problems the pack is really about

Cheap leads, zero pipeline. Campaign Manager celebrates a low cost per lead. Then sales works the list and most of it goes nowhere. The reconciliation skill joins LinkedIn-reported leads to your CRM stages so you see cost per qualified lead and cost per opportunity by campaign, then moves budget toward what produces pipeline. It also closes the loop by feeding your qualified stages back into LinkedIn through offline conversion import, so bidding learns to chase pipeline value instead of form-fill volume.

Budget delivered to the wrong people. A campaign can hit its target cost per lead on average while spending half its budget on seniorities and industries that will never buy. Averages hide it. The demographics report reveals it, and the demographics-leak-finder skill reads that report against your ICP and quantifies the reallocation pool.

Install

Clone the repo and copy the skill folders into your Claude skills directory.

git clone https://github.com/mardab96/linkedin-ads-claude-skills.git
mkdir -p ~/.claude/skills
cp -r linkedin-ads-claude-skills/*-linkedin-ads ~/.claude/skills/

Start a new Claude Code session and the skills activate automatically when their description matches what you ask. In other Claude environments, paste the relevant SKILL.md into context.

What is inside

Start here.

• account-triage: runs an ordered triage of an unfamiliar account and routes you to the right deep-dive skill, so you start where it is actually broken

Diagnose.

• wasted-spend-finder: finds spend without conversion across campaigns, placements (feed vs LinkedIn Audience Network), Audience Expansion, and dayparting
• audience-targeting-audit: flags audiences too small or too broad, cross-campaign overlap, expansion and network leakage, and weak ABM match rates
• demographics-leak-finder: quantifies budget delivered to the wrong seniorities, industries, and company sizes versus your ICP
• frequency-fatigue-check: catches when a small B2B audience is just seeing the same ad too many times

Measure.

• conversion-tracking-audit: audits the Insight Tag, the Conversions API, offline conversion import, duplicate or missing conversions, and where view-through is padding results
• cpl-vs-crm-reconciliation: joins LinkedIn leads to CRM stages for true cost per qualified lead and per opportunity, then reallocates toward pipeline

Optimise.

• bid-budget-sanity-check: matches Maximum delivery, Cost cap, or Manual to objective, audience size, conversion volume, and budget
• creative-fatigue-audit: reads ad-level decay and format mix (single image, document, video, thought leader) and says what to refresh, retire, or scale
• lead-gen-form-optimizer: decides native form vs landing page, then cuts form friction, tied to downstream lead quality

Plan and report.

• scaling-planner: decides where to add budget, hold, reduce, or pause against audience-size ceilings and fatigue
• weekly-operator-digest: a recurring readout that serves both the operator who needs detail and the stakeholder who needs the headline

The math is done for you, not eyeballed

Two skills lean on numbers you should not eyeball, so the pack ships deterministic helper scripts that do the arithmetic exactly. One reconciles cost per qualified lead across campaigns from your LinkedIn and CRM stage counts. The other reads a demographics export and quantifies off-ICP delivery, falling back to an impression-share proxy (clearly labeled) when LinkedIn omits per-slice cost.

# True cost per qualified lead per campaign, from LinkedIn plus CRM stages
python3 scripts/cpl-reconciliation.py campaigns.csv

# Off-ICP spend share from a Demographics export
python3 scripts/demographics-leak.py demographics.csv --icp "director,vp,cxo,owner"

How to use it

Describe what you want in plain language and hand over the export. Some examples:

• "We just took over this LinkedIn Ads account, where do we start?" activates account triage.
• "LinkedIn says our leads are cheap but sales says they are garbage." activates the CPL versus CRM reconciliation.
• "Half our budget is going to managers and juniors, show me." activates the demographics leak finder.
• "Is Audience Expansion or the Audience Network wasting our spend?" activates the wasted spend finder.

The skills do not log in and do not change anything live. They read what you give them and stop at a recommendation you approve and apply yourself.

A note on thresholds

Numeric thresholds in these skills are starting heuristics, not rules LinkedIn published. The 300-member audience floor and the 50,000-member recommendation are LinkedIn's own. Everything else (waste multiples, fatigue frequency, cost-per-lead targets) shifts by vertical, offer, sales-cycle length, and account maturity. Every skill says so and tells you when it adjusted a threshold and why. Treat any skill that hands you a confident number without stating its assumptions as one worth ignoring, including these.

If you run Google Ads too, there is a companion pack: 20 Claude Skills for Google Ads. The pack is free and MIT licensed, so use it, fork it, and adapt it to your own account.