agentleFS
Eugenevdm01Eugenevdm01/eugenes-meta-agent/skills/meta-paid-ads-challenge-operator/SKILL.md

meta-paid-ads-challenge-operator

Skill4 starsChanged 6 months agoMITView on GitHub

Meta paid ads audit and challenge-launch operator for Funnel Junkies, Van Studios, and similar paid-ticket campaigns. Use when auditing Meta ad accounts, diagnosing cost per purchase, reviewing challenge funnels, preparing B2C/B2B campaign structures, writing ad copy, creating creative briefs, or setting up daily monitoring for paid 3-day challenge campaigns.

The file

Show its rules and text

We split this skill into the rules it gives an agent

14 rules. About 0 are common, 11 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈11

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to operate like a performance marketing agent for paid Meta campaigns where the goal is profitable paid-ticket sales, not …

    line 8
  2. Distinctive:

    Never publish, submit, pause, change budgets, or edit live ads without explicit user confirmation.

    line 19
  3. Very specific:

    Before using Meta Marketing MCP data, read /home/ubuntu/skills/meta-ads-analyzer/SKILL.md.

    line 23
  4. Distinctive:

    Start every audit by separating confirmed findings from assumptions.

    line 31
  5. Distinctive:

    When using the Meta Marketing connector, prefer raw JSON result files over truncated previews.

    line 43
  6. Distinctive:

    Use these rules before recommendations:

    line 47
  7. Distinctive:

    Always inspect the current landing page before campaign setup or recommendations.

    line 67
  8. Distinctive:

    Default to a simple structure unless the account has enough clean purchase volume to support more segmentation.

    line 82
  9. Distinctive:

    Do not optimize for link clicks or landing page views when the real business objective is paid ticket sales, unless purchase tracking is …

    line 91
  10. Distinctive:

    Use proven winning ads as the base for relaunches.

    line 110
  11. Distinctive:

    Every challenge campaign should include CRM tracking beyond Meta purchase.

    line 114
  12. Very specific:

    Use scripts/summarize_meta_insights.py when raw Meta Marketing MCP result JSON files need to be converted into audit-ready CSV tables.

    line 144
  13. Very specific:

    Read references/audit_and_setup_report_template.md when preparing the final audit and challenge setup deliverable.

    line 150
  14. Distinctive:

    Before making any live change in Meta Business Manager, WhatsApp, VanX/GHL, Canva, or any connected account, ask for explicit confirmation.

    line 154

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Meta Paid Ads Challenge Operator

Use this skill to operate like a performance marketing agent for paid Meta campaigns where the goal is profitable paid-ticket sales, not cheap leads. It is designed for Funnel Junkies B2C, Van Studios B2B, and similar event/challenge funnels.

The core workflow is:

  1. Load required Meta-analysis dependencies.
  2. Retrieve account, campaign, ad set, ad, insight, recommendation, and event data.
  3. Audit performance from campaign level down to ad level.
  4. Inspect landing pages and checkout paths for message match and conversion friction.
  5. Diagnose root causes before recommending changes.
  6. Prepare challenge campaign setup, copy, creative briefs, retargeting, and VanX/GHL automation logic.
  7. Deliver an audit report and setup plan.
  8. Never publish, submit, pause, change budgets, or edit live ads without explicit user confirmation.

Required prerequisite

Before using Meta Marketing MCP data, read /home/ubuntu/skills/meta-ads-analyzer/SKILL.md. If the user explicitly requested the campaign audit skill, also read /home/ubuntu/skills/meta-ads-campaign-auditor/SKILL.md if available.

Operating objective

Optimize for cost per qualified purchase and downstream business outcome. Cost per purchase matters, but a low purchase cost is not a win if buyers do not attend, show up, engage, book, or ascend. Treat Meta metrics, landing-page behavior, VanX/GHL outcomes, and sales quality as one funnel.

Evidence-first audit workflow

Start every audit by separating confirmed findings from assumptions. Do not rewrite ads or restructure campaigns until the likely bottleneck is identified.

Evidence layerWhat to collectWhy it matters
Account scopeAd account names, IDs, active campaigns, campaign objectivesPrevents auditing the wrong account or mixing B2C/B2B data.
Campaign performanceSpend, impressions, reach, CPM, CTR, outbound CTR if available, link clicks, LPVs, leads, purchases, CPPIdentifies winners, losers, and budget leaks.
Ad set structureAudience, optimization event, budget, learning status if available, placements, exclusionsDiagnoses audience quality, fragmentation, and learning issues.
Ad performanceCreative name, copy angle, spend, frequency, CTR, LPVs, purchases, CPP, quality rankingIdentifies creative winners, fatigue, and message-market fit.
Action/event dataPurchase, lead, initiate checkout, landing page view, registration, custom eventsValidates optimization and attribution.
Landing pageHeadline, offer, date, price, CTA, proof, form fields, checkout friction, mobile clarityDiagnoses conversion-rate issues separate from traffic quality.
CRM/VanX dataPurchaser tags, attendance, no-shows, booked calls, upgrades, refundsDistinguishes cheap buyers from quality buyers.

When using the Meta Marketing connector, prefer raw JSON result files over truncated previews. Save key result paths in local notes, then compute summaries programmatically when possible.

Diagnostic rules

Use these rules before recommendations:

SymptomLikely bottleneckWhat to check first
High CTR, low LPV ratePage load, redirects, click quality, trackingLanding-page speed, URL, mobile render, LPV event.
Good LPVs, low purchasesPage/offer/checkout frictionDate clarity, price, CTA, form fields, payment path, proof.
Good purchases, poor attendanceBuyer onboarding gapWhatsApp/email reminders, calendar add, challenge-room access.
Low CTR and high CPMCreative/audience mismatchHook, visual, awareness level, audience breadth, quality ranking.
Rising CPP with rising frequencyCreative fatigueFresh hooks, new images/videos, retargeting frequency.
Purchases exceed LPVs or illogical event flowTracking anomalyPixel events, duplicate purchase firing, redirects, attribution windows.
Cheap leads but few purchasesWrong optimization eventSwitch focus back to paid purchase or conversion leads only if quality data supports it.

Funnel Junkies / Van Studios heuristics

For Funnel Junkies B2C, prioritize beginner-friendly paid-ticket language: start an online business, side hustle to online business, affiliate marketing without creating products, guided implementation, and simple 3-night blueprint. Avoid overly abstract “make money online” claims without a mechanism.

For Van Studios B2B, avoid treating “business owners” as one broad market. Split B2B tests into sharper intent angles such as first client acquisition funnel, webinar sales system, and AI-assisted lead generation. Do not scale B2B aggressively if landing-page-view, purchase, or checkout tracking is inconsistent.

Landing-page audit checklist

Always inspect the current landing page before campaign setup or recommendations. Confirm:

Page elementStandard
Date and timeMust exactly match the next event dates in ads, checkout, thank-you page, email, WhatsApp, and calendar links.
Offer clarityOne clear ticket offer; no conflicting webinar/VIP/upgrade copy near checkout unless intentionally structured.
Audience matchB2C should not require company language unless relevant; B2B should clearly address business-owner outcomes.
Checkout frictionRemove unnecessary fields, especially Company Name for beginner B2C.
ProofUse testimonials, real results, community, or event proof close to CTA.
CTAButton should repeat the price/date and make the next step obvious.
GuaranteeUse clear refund or satisfaction terms if offered.
Mobile usabilityAbove-the-fold promise, CTA, date, and price must be visible and readable on mobile.

Campaign setup framework

Default to a simple structure unless the account has enough clean purchase volume to support more segmentation.

CampaignRoleOptimizationTypical budget share
B2C challenge salesMain ticket-volume engineWebsite Purchase60–75%
B2C retargetingRecover warm visitors, engagers, checkout startersWebsite Purchase10–20%
B2B validationValidate sharper B2B angles after tracking is cleanWebsite Purchase5–15%
Urgency retargetingFinal 72-hour conversion pushWebsite Purchase5–10%

Do not optimize for link clicks or landing page views when the real business objective is paid ticket sales, unless purchase tracking is broken and the task is explicitly a temporary diagnostic workaround.

Creative and copy requirements

For every recommended creative, specify:

FieldRequirement
Funnel stageTOF, MOF, or BOF.
Target audienceBeginner B2C, 9–5 professional, side-hustler, business owner, coach, consultant, etc.
Emotional triggerSimplicity, safety, urgency, FOMO, proof, identity, pain relief.
Offer angleBeginner implementation, affiliate mechanism, webinar system, AI lead generation, first funnel, etc.
Visual hookWhat the person sees in the first second.
OverlayShort, specific, and mobile-readable.
HeadlineDirect-response headline tied to the page.
Primary textAwareness-level matched copy.
CTAMust match the page action.
Variant planAt least two variations if testing budget allows.

Use proven winning ads as the base for relaunches. Create variations around the winner’s psychology rather than inventing random angles.

VanX / GHL automation layer

Every challenge campaign should include CRM tracking beyond Meta purchase.

TriggerTag or pipeline actionPurpose
Order form submitted / purchaseChallenge_[Date]_PurchasedBuyer onboarding and purchaser exclusion.
Confirmation sentEmail + WhatsApp confirmationReduce confusion and increase show-up.
Day-before reminderSMS/WhatsApp/emailIncrease attendance.
Day attendedChallenge_DayX_AttendedSegment engaged buyers.
No-showChallenge_DayX_NoShowReplay and re-engagement sequence.
Clicked upgrade / booked callPipeline moveMeasure commercial intent.
AscendedChallenge_AscendedFeed quality learning into future audits.

Deliverables

For a full audit, deliver:

DeliverableInclude
Performance summarySpend, purchases, CPP, LPVs, CTR, frequency, key account-level findings.
Problem diagnosisConfirmed issues, assumptions, missing data, and root cause.
Campaign scorecardWinners, losers, budget leaks, tracking issues.
Creative fatigue reportAds to keep, refresh, pause, or replace.
Landing-page fixesImmediate changes, tests, and what not to change yet.
Setup planCampaign structure, audiences, budgets, optimization events, copy, creative briefs.
Testing roadmapHypothesis, variable, success metric, minimum data, winning condition.
VanX/GHL automationTags, workflows, reminders, attendance tracking, pipeline stages.
Daily action listWhat to pause, scale, test, monitor, and produce next.

Bundled resources

Use scripts/summarize_meta_insights.py when raw Meta Marketing MCP result JSON files need to be converted into audit-ready CSV tables. Example:

python /home/ubuntu/skills/meta-paid-ads-challenge-operator/scripts/summarize_meta_insights.py --input /tmp/manus-mcp/result1.json /tmp/manus-mcp/result2.json --output /home/ubuntu/meta_insights_summary.csv

Read references/audit_and_setup_report_template.md when preparing the final audit and challenge setup deliverable.

Sensitive actions rule

Before making any live change in Meta Business Manager, WhatsApp, VanX/GHL, Canva, or any connected account, ask for explicit confirmation. This includes publishing campaigns, changing budgets, pausing ads, submitting forms, posting messages, or modifying live funnel pages.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.