Paid media analysis
Skill duandigi/duandigi-growth-marketing-skill/skills/paid-media-analysis
Use this skill when analyzing Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads, or other paid media from account totals down to campaign, ad group, audience, keyword, search term, creative, placement, landing page, qualified lead, revenue, and margin.From its SKILL.md
npx -y skills add duandigi/duandigi-growth-marketing-skill --skill paid-media-analysisAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 29 days oldThe repository was created 29 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its file declares
Copied from the file, not written here
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
3.9 KB, 652 tokens by cl100k_base, as published. Nobody here has run it
Paid Media Analysis
Purpose
Evaluate paid acquisition by both platform efficiency and downstream business quality while identifying waste, scale opportunities, saturation, and measurement risk.
Inputs
- Spend, impressions, reach, clicks, delivery, conversion, and attribution data
- Campaign, ad group, keyword, search term, audience, creative, placement, device, location, and time dimensions
- Landing-page analytics and conversion events
- CRM qualification, sales, revenue, refund, and margin data where available
- Budgets, bidding constraints, policy limitations, and recent changes
If a required input is unavailable, label it unknown, state how it limits the decision, and create a collection, mapping, validation, or instrumentation task. Never invent credentials, assets, metrics, permissions, or business outcomes.
Workflow
- Validate account mapping, currency, attribution window, conversion actions, and data lag.
- Analyze delivery, cost, click quality, conversion efficiency, qualified-outcome efficiency, and revenue efficiency separately.
- Drill down to campaigns, targeting, queries or audiences, creatives, placements, devices, locations, times, and landing pages.
- Detect wasted spend, low-volume uncertainty, creative fatigue, audience saturation, query mismatch, budget constraint, tracking loss, and lead-quality differences.
- Compare platform-reported conversions with analytics and CRM outcomes without forcing equality.
- Estimate whether an action is a measurement fix, negative targeting, creative test, landing-page test, budget reallocation, bid change, or stop decision.
- Prepare changes as drafts and require approval before modifying spend or delivery.
Required output
Return a concise, decision-oriented result containing:
- Paid-media health and efficiency summary
- Spend-to-qualified-outcome and revenue analysis
- Campaign, targeting, creative, and landing-page findings
- Measurement and attribution limitations
- Draft actions and experiments with budget risk and approval level
Label material statements as confirmed, calculated, inferred, assumed, or unknown. Include the data period, last complete period, source lineage, and confidence whenever they can change the decision.
Guardrails
-
Do not optimize only to platform conversion count when CRM quality is available.
-
Do not pause or increase budgets based on one incomplete day or small sample.
-
Do not automatically change bids, budgets, targeting, creative, or campaign status.
-
Do not combine currencies or attribution windows without normalization.
-
Do not claim guaranteed growth or present an estimate as observed fact.
-
Do not reveal secrets, personal data, private provider payloads, or cross-project information.
-
When an action can spend money, publish, contact people, alter access, modify production, or delete data, prepare an approval request instead of executing automatically.
Completion check
Before finishing, verify that the output:
- answers a specific business or implementation decision;
- uses the correct organization, project, asset, date range, time zone, and currency;
- separates performance problems from data, connection, and attribution problems;
- includes evidence, uncertainty, affected scope, and a measurable next step;
- respects least privilege, approval, audit, and rollback requirements;
- is no longer than necessary for the decision.
What ships with it: 1 file
829 B alongside SKILL.md
evals/
- evals.json829 B