Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

/ads linkedin — LinkedIn Ads Deep Analysis · miosa-osa | DecimalAI

miosa-osa/ads linkedin

NewSkillScoreMaintained

LinkedIn Ads deep analysis for B2B advertising. Evaluates 25 checks across technical setup, audience targeting, creative quality, lead gen forms, and bidding strategy. Includes Thought Leader Ads, ABM, and predictive audiences. Triggers on: "LinkedIn Ads", "B2B ads", "sponsored content", "lead gen forms", "InMail", "LinkedIn campaign", "LinkedIn audit"

marketingby miosa-osa

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Marketing & Content pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/miosa-osa-ads-linkedin/SKILL.md

decimalai skills pull miosa-osa-ads-linkedin --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/miosa-osa-ads-linkedin/SKILL.md https://app.decimal.ai/s/miosa-osa-ads-linkedin/SKILL.md

Raw file: /s/miosa-osa-ads-linkedin/SKILL.md ↗ · machine-readable summary at /s/miosa-osa-ads-linkedin.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 45h ago

Yes — +22% lift · at higher cost+46% tokens0% turns91% of whole cases pass with skill (21/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-03	✗→✓	▲ Improved	213%	0%
case-09	✗→✓	▲ Improved	19%	0%
case-12	✗→✓	▲ Improved	14%	0%
case-22	✗→✓	▲ Improved	17%	0%
case-23	✗→✓	▲ Improved	2%	0%

Showing 5 of 23 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

miosa-osa / canopy

library/skills/paid-media/ads-linkedin/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

Skill contents

SKILL.md

/ads linkedin — LinkedIn Ads Deep Analysis

> 25-check audit of LinkedIn Ads accounts with B2B-specific strategy assessment.

Usage

bash
/ads linkedin

Process

Collect LinkedIn Ads data (Campaign Manager export, Insight Tag status)
Evaluate all applicable checks as PASS, WARNING, or FAIL
Calculate LinkedIn Ads Health Score (0-100)
Generate findings report with action plan

What to Analyze

Technical Setup (25% weight)

Insight Tag installed and firing on all pages (L01)
Conversions API (CAPI) active — launched 2025 (L02)
Conversion events configured for full funnel
Revenue attribution tracking enabled

Audience Targeting (25% weight)

Job title targeting uses specific titles, not just functions (L03)
Company size filtering matches ICP (L04)
Seniority level appropriate for offer (L05)
Matched Audiences active: retargeting + contact lists (L06)
ABM company lists uploaded (up to 300,000 companies) (L07)
Audience expansion OFF for precision campaigns, ON for scale (L08)
Predictive audiences tested — replaced Lookalikes Feb 2024 (L09)

Creative Quality (20% weight)

Thought Leader Ads active, >=30% budget allocation for B2B (L10)
Ad format diversity: >=2 formats tested (L11)
Video ads tested (L12)
Creative refresh every 4-6 weeks (L13)

Lead Gen & Performance (15% weight)

Lead Gen Form <=5 fields (13% CVR benchmark) (L14)
Lead Gen Form synced to CRM in real-time (L15)
Campaign objective matches funnel stage (L18)
A/B testing active: creative or audience (L19)
Message ad frequency <=1 per 30-45 days (L20)

Bidding & Budget (15% weight)

Bid strategy: CPS for Messages, Max Delivery for Content (L16)
Daily budget >=$50 for Sponsored Content (L17)
CTR >=0.44% for Sponsored Content (L21)
CPC within benchmark: $5-7 average, senior $6.40+ (L22)
Lead-to-opportunity rate tracked, not just CPL (L23)
Attribution: 30-day click / 7-day view configured (L24)
Demographics report reviewed monthly (L25)

Thought Leader Ads (TLA) Assessment

CPC typically $2.29-$4.14 vs $13.23 for standard Sponsored Content
CTR typically 2-3x higher than corporate-branded ads
Best for: B2B thought leadership, brand awareness, engagement
Are TLAs being used? (If not, HIGH priority recommendation)
Are they getting >=30% of total LinkedIn budget?

ABM Strategy Assessment

For B2B Enterprise accounts:

Company list uploaded and segmented by tier
Custom content per tier
Account penetration tracking
Integration with CRM/ABM platform (Demandbase, 6sense, etc.)

Key Thresholds

| Metric | Pass | Warning | Fail | |--------|------|---------|------| | CTR (Sponsored Content) | >=0.44% | 0.30-0.44% | <0.30% | | CPC (average) | <=$7.00 | $7-10 | >$10.00 | | Lead Gen CVR | >=10% | 5-10% | <5% | | Message frequency | <=1/30 days | 1/15-30 days | >1/15 days | | TLA budget share | >=30% | 15-30% | <15% |

Output

Deliverables

LINKEDIN-ADS-REPORT.md — Full 25-check findings with pass/warning/fail
TLA adoption roadmap (if not using)
ABM strategy recommendations (for B2B)
Lead Gen Form optimization priorities
Quick Wins sorted by impact

Want to see if miosa-osa/ads linkedin would activate on your phrasing? Try it before you install — no LLM call, no signup.

Latest benchmark · publisher runVerified

8/27/2026, 13:15 UTC · 23 cases

Lift

+22%

91% vs 70%

Agent turns

1.0 vs 1.0

Tokens

+46%

3,773.13 vs 2,588.78

fail → pass · 5pass → pass · 16fail → fail · 2

Per-case results (23)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-01 Can you perform a full strategic and technical audit on our LinkedIn Campaign Manager account data? Please analyze our tracking setup, job and company targeting, ad formats, lead forms, and spend efficiency. I'd like a complete breakdown markdown report with pass, warning, or failure indicators across all evaluated checks, an overall account health score, guidance on our thought leadership ad usage and account-based strategy, and a prioritized list of quick wins.	fail→fail	49,200	46,586	-5%	1	1	0%	8,276	9,269	+12%	0	0	—
case-02 We need an in-depth health check on our B2B LinkedIn Ads performance. Please evaluate our Insight Tag and CAPI tracking, audience segmentation, creative mix, lead generation forms, and bidding strategies. Provide an output report formatted as a markdown file containing pass/warning/fail statuses for each check, an overall health score from 0 to 100, specific recommendations for ABM and Thought Leader Ad adoption, and an action plan featuring quick wins ranked by impact.	fail→fail	48,104	51,599	+7%	1	1	0%	7,920	7,955	+0%	0	0	—
case-03 Run a comprehensive audit on our LinkedIn Ads campaign manager exports and conversion tag setup using the /ads linkedin command. I want a generated report saved to LINKEDIN-ADS-REPORT.md detailing findings across technical setup, audience precision, creative diversity, lead forms, and budget management. Make sure the output includes an overall numerical health score, an assessment of our enterprise ABM and thought leadership strategy, and actionable next steps organized by impact.	fail→pass	21,604	47,238	+119%	1	1	0%	2,658	8,314	+213%	0	0	—
case-04 We want to audit our Google Ads search and display accounts. Can you analyze our keyword match types, Quality Scores, negative keyword lists, Smart Bidding performance, and responsive search ad strength across our SaaS campaigns?	pass→pass	19,963	23,322	+17%	1	1	0%	3,155	4,645	+47%	0	0	—
case-05 Please evaluate our company's organic LinkedIn page and executive profiles. Analyze our employee advocacy rates, profile banner design, post publishing frequency, page follower growth, and hashtag strategies.	pass→pass	11,619	22,288	+92%	1	1	0%	1,789	4,489	+151%	0	0	—
case-06 Can you perform an audit of our Meta Advantage+ campaigns, Facebook Pixel setup, CAPI event match quality scores, custom audiences, and Advantage+ creative optimizations?	pass→pass	16,803	48,671	+190%	1	1	0%	2,584	7,140	+176%	0	0	—
case-07 When auditing our LinkedIn campaign bid settings, our team currently uses Cost Per Send (CPS) for sponsored content to control per-view costs, and Manual CPC for Message Ads. Should we keep this setup or change the bidding strategies for these formats?	pass→pass	15,573	35,802	+130%	1	1	0%	2,430	3,353	+38%	0	0	—
case-08 Our LinkedIn Sponsored Content ad campaigns currently show an average CTR of 0.35%. Should this be marked as a PASS, WARNING, or FAIL in our LinkedIn performance review?	pass→pass	13,245	10,617	-20%	1	1	0%	1,744	2,395	+37%	0	0	—
case-09 In our B2B LinkedIn campaign evaluation, our average CPC across standard campaigns came out to $8.50. What evaluation status should this metric receive based on standard B2B benchmarks?	fail→pass	12,699	5,770	-55%	1	1	0%	1,637	1,945	+19%	0	0	—
case-10 Our LinkedIn Lead Gen Form campaign has a conversion rate of 4.2%. Is this CVR considered a PASS, WARNING, or FAIL?	pass→pass	9,880	7,307	-26%	1	1	0%	1,552	1,916	+23%	0	0	—
case-11 We set our LinkedIn Message Ad frequency limit to send once every 12 days to maximize touchpoints. How should this cadence be rated in an account audit?	pass→pass	16,134	13,443	-17%	1	1	0%	2,276	3,056	+34%	0	0	—
case-12 Our B2B company allocates 10% of our LinkedIn advertising budget to Thought Leader Ads (TLA) and 90% to standard corporate Sponsored Content. How should this budget distribution be rated?	fail→pass	14,611	10,697	-27%	1	1	0%	2,301	2,634	+14%	0	0	—
case-13 To keep our LinkedIn target audience broad and reduce cost, we targeted the general job function 'Engineering' rather than specific job titles like 'VP of Software Engineering' or 'Lead DevOps Engineer'. Does this targeting approach pass audit standards?	pass→pass	15,856	11,341	-28%	1	1	0%	2,024	2,708	+34%	0	0	—
case-14 For our high-precision enterprise ABM LinkedIn campaign targeting a list of 50 key accounts, we turned Audience Expansion ON to reach more decision-makers. Is this considered correct setup for precision B2B campaigns?	pass→pass	11,596	12,569	+8%	1	1	0%	1,889	2,833	+50%	0	0	—
case-15 We are setting up new LinkedIn target audiences and plan to rely primarily on Lookalike Audiences built from our customer list. Is this current best practice for LinkedIn targeting?	pass→pass	13,730	18,872	+37%	1	1	0%	2,056	3,529	+72%	0	0	—
case-16 Our marketing team wants to collect 8 fields on our LinkedIn Lead Gen Form (Name, Work Email, Phone, Title, Company, Industry, Country, Budget) to thoroughly qualify leads. What is the recommended field limit for optimal conversion rate?	pass→pass	12,019	12,426	+3%	1	1	0%	1,905	3,153	+66%	0	0	—
case-17 We are preparing a massive account list for LinkedIn ABM matching. What is the maximum number of companies that can be uploaded in a single LinkedIn matched account list?	pass→pass	6,190	7,515	+21%	1	1	0%	1,052	2,097	+99%	0	0	—
case-18 When evaluating conversions in LinkedIn Campaign Manager, our team is currently using a 90-day click / 30-day view attribution window. What standard conversion attribution window configuration should be audited for?	pass→pass	12,461	58,513	+370%	1	1	0%	2,044	2,628	+29%	0	0	—
case-19 We set up a Sponsored Content campaign with a $20/day budget to test messaging quietly. Does a $20 daily budget meet the recommended threshold for LinkedIn Sponsored Content campaigns?	pass→pass	12,677	14,251	+12%	1	1	0%	2,062	2,724	+32%	0	0	—
case-20 Our LinkedIn Sponsored Content ad creatives have been running continuously unchanged for 6 months because their performance has stayed steady. What is the recommended creative refresh timeframe?	pass→pass	13,885	11,915	-14%	1	1	0%	1,857	2,459	+32%	0	0	—
case-21 We have the LinkedIn Insight Tag installed on our website but have not implemented the LinkedIn Conversions API (CAPI) because we think pixel tracking alone is sufficient for 2025. How does this impact the technical tracking audit?	pass→pass	16,229	14,544	-10%	1	1	0%	2,457	3,232	+32%	0	0	—
case-22 Our team is debating whether to launch Thought Leader Ads (TLA) vs traditional corporate Sponsored Content on LinkedIn. What is the typical CPC range advantage of TLAs compared to standard corporate ads?	fail→pass	15,450	11,671	-24%	1	1	0%	2,349	2,751	+17%	0	0	—
case-23 In our overall LinkedIn Ads Health Score calculation, how are the five audit categories (Technical Setup, Audience Targeting, Creative Quality, Lead Gen & Performance, Bidding & Budget) weighted?	fail→pass	12,379	3,028	-76%	1	1	0%	1,525	1,557	+2%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +22 percentage points is the difference between those two pass rates over the 23 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 69.6%
Pass rate with the skill: 91.3%
Cases attempted: 23
Cases counted toward lift: 23
Cases that regressed: 0
Skill version measured: v1
Run completed: 8/27/2026, 13:15 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-03

Prompt

Run a comprehensive audit on our LinkedIn Ads campaign manager exports and conversion tag setup using the /ads linkedin command. I want a generated report saved to LINKEDIN-ADS-REPORT.md detailing findings across technical setup, audience precision, creative diversity, lead forms, and budget management. Make sure the output includes an overall numerical health score, an assessment of our enterprise ABM and thought leadership strategy, and actionable next steps organized by impact.

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signalsno signals yet

BenchmarkRun a verified benchmark with positive lift

Live evalNeeds ≥20 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

No signals yet — run a benchmark or collect evaluated traces to earn a score.

Verified on gemini-3.6-flash · re-tested yesterday

Other measured skills in the registry, with their headline benchmark lift.