[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M718MS8TH4N1PFPNX503Z6KN":3,"skill-same:01M718MS8TH4N1PFPNX503Z6KN":71},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":28,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":6,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M718MS8TH4N1PFPNX503Z6KN","campaign-analyzer",null,"Analyze paid media performance across dimensions, funnels, cohorts, and channels — turning data into actionable insights and business narratives.","narayan-metaflow\u002Fmetaflow-marketing-skills","narayan-metaflow","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F181216517?v=4","01M718MB0Y27AYKTC9ZKT16V86","narayan","01M718MB209XRYRTS3ZZFK0JXS",19,"MIT","https:\u002F\u002Fgithub.com\u002Fnarayan-metaflow\u002Fmetaflow-marketing-skills\u002Fblob\u002Fmain\u002Fskills\u002Fcampaign-analyzer\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000019","营销推广","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000035","市场营销","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"campaign","campaign analyzer","analyzer","Media","paid","actionable","performance","insights","dimensions","across","analyze","data","paid media","business","channels","2026-11-10 10:12:30",false,"---\nname: campaign-analyzer\ndescription: \"Analyze paid media performance across dimensions, funnels, cohorts, and channels — turning data into actionable insights and business narratives.\"\n---\n\n## Process\n\n1. **Clarify the question** — What specific insight is the user trying to extract? (\"Why is CPA rising?\" vs \"What's the LTV by channel?\")\n2. **Select analysis type** — Match the question to the right framework (pulse, strategic, dimensional, funnel, cohort, incrementality, cross-channel)\n3. **Gather required data** — Request exports needed for the analysis\n4. **Run the analysis** — Apply the specific method\n5. **Identify the story** — What happened, why it happened, what to do about it\n6. **Deliver findings** — Structured output with insights, not just metrics\n\n## Analysis Type Selector\n\n| Question | Analysis Type | Time Horizon |\n|----------|--------------|-------------|\n| \"Is anything broken right now?\" | Daily pulse monitoring | 1-7 days |\n| \"How are we trending this week\u002Fmonth?\" | Weekly\u002Fmonthly strategic review | 7-30 days |\n| \"Where is performance coming from\u002Fgoing to?\" | Multi-dimensional analysis | 30-90 days |\n| \"Where are users dropping off?\" | Funnel analysis | 7-30 days |\n| \"How valuable are acquired customers over time?\" | Cohort & LTV analysis | 30-365+ days |\n| \"Is this channel actually driving incremental results?\" | Incrementality testing | 30-90 days |\n| \"How do channels compare and work together?\" | Cross-channel analysis | 30-90 days |\n\n## Daily Pulse Monitoring\n\n**What to check:**\n- Cost, impressions, clicks, conversions, spend pacing vs budget\n- Sudden metric changes (CPC spikes, conversion drops, budget exhaustion)\n- Meta: learning phase status per ad set\n- Disapprovals, policy flags, payment issues\n\n**Alert thresholds:** Automated alerts for >20% deviation from 7-day averages on key metrics.\n\n**What NOT to do:** Don't optimize during daily pulse. Daily review is for catching emergencies, not making strategic changes. Save optimization decisions for weekly reviews.\n\n**Cadence insight (Supermetrics research):** Most successful performance marketers prioritize basic metrics (cost, impressions, clicks, conversions) for daily decisions. Deeper analysis (frequency, LTV, attribution) is purposeful, not constant.\n\n## Weekly\u002FMonthly Strategic Review\n\n**Key metrics by platform:**\n\n| Google Ads | Meta Ads |\n|-----------|---------|\n| CTR, CPC, CPA, ROAS | CPM, CPC, CPA, ROAS |\n| Conversion rate | Frequency, Conversion rate |\n| Impression share | Reach, Delivery status |\n| Quality Score trends | Learning phase status |\n| Search term movement | Creative performance |\n\n**Review structure:**\n1. **Scaling candidates** — Campaigns with strong ROAS + available impression share (Google) or frequency headroom (Meta) → recommend budget increases\n2. **Pause\u002Fpullback candidates** — Campaigns with high CPA + declining trend → recommend reductions\n3. **Creative performance** — Which ads\u002Fcreatives are winning, which are fatiguing\n4. **Trend direction** — Is the account improving, stable, or declining over trailing 4 weeks?\n\n## Multi-Dimensional Performance Analysis\n\nSlice performance across dimensions to find hidden drivers.\n\n### Dimensions to Analyze\n\n| Dimension | What to Look For |\n|-----------|-----------------|\n| Device type | Mobile vs desktop vs tablet CPA\u002FROAS differences |\n| Geography | Regional performance variance (country, state, DMA) |\n| Time of day | Hour-by-hour conversion rate patterns |\n| Day of week | Day-by-day performance patterns |\n| Audience segment | Segment-level CPA\u002FROAS comparison |\n| Match type (Google) | Broad vs phrase vs exact performance |\n| Placement (Meta) | Feed vs Stories vs Reels vs Audience Network |\n| Creative concept | Concept-level performance patterns |\n| Landing page | Landing page-level conversion rate |\n| Funnel stage | TOF vs MOF vs BOF performance |\n\n### Cross-Tab Analysis\n\nCombine dimensions to find non-obvious patterns:\n\n| Cross-Tab | What It Reveals | Example |\n|-----------|----------------|---------|\n| Device × Time of day | When mobile converts vs desktop | Mobile converts 3x better in evening hours |\n| Audience × Creative | Which creatives resonate with which audiences | UGC wins with Lookalike, studio wins with cold broad |\n| Geography × Product | Regional product preferences | Coastal states prefer product A, interior prefer product B |\n| Day × Creative concept | Which concepts work when | Emotional creative wins Sunday, rational wins Tuesday |\n| Placement × Video length | Optimal length per placement | 15s wins Stories, 30s wins Feed |\n\n### Red Flags to Watch\n\n- **One dimension dominating cost but not conversions** → Budget misallocation\n- **Large variance across segments** → Opportunity to isolate winners\n- **Hidden loss leaders** → Specific segments dragging average down\n\n## Funnel Analysis\n\nMap every stage from impression to final conversion.\n\n### Standard Funnel Stages\n\n| Stage | Metric | Benchmark to Check |\n|-------|--------|-------------------|\n| Impression | Impressions | Reach sufficient for audience? |\n| Click | CTR, clicks | Industry CTR benchmarks |\n| Landing page view | Landing page views | Bounce rate, load speed |\n| Micro-conversion | AddToCart, video 50%, scroll depth | Stage-specific |\n| Macro-conversion | Purchase, Lead, Signup | Target CPA \u002F ROAS |\n\n**Calculate stage-by-stage conversion rates.** Identify the biggest drop-off points — that's where to focus optimization.\n\n### Drop-Off Diagnostics\n\n| Drop-Off Point | Likely Cause | Fix |\n|---------------|-------------|-----|\n| Impression → Click | Low CTR | Ad copy, ad creative, targeting |\n| Click → Landing Page View | Slow page, 404s, disconnected UX | Page speed, fix broken flows |\n| Landing Page View → Add to Cart | Landing page message mismatch, bad UX | Rewrite headlines, improve CTA |\n| Add to Cart → Checkout | Friction, unexpected costs | Simplify checkout, show total costs |\n| Checkout → Purchase | Payment issues, trust concerns | Add trust signals, multiple payment options |\n\n**Meta-specific (June 2025):** Instant Experience is no longer counted as a landing page view. If your Meta funnel metrics suddenly showed a drop in mid-2025, this is likely why. Adjust funnel definitions accordingly.\n\n## Cohort & Lifetime Value Analysis\n\n### Cohort Windows\n\nTrack customer cohorts at standard intervals:\n- Day 1, 7, 14, 30 (short-term retention)\n- Day 30, 60, 90 (medium-term)\n- Day 180, 365 (long-term LTV)\n\n### Metrics to Track per Cohort\n\n| Metric | What It Tells You |\n|--------|------------------|\n| Repeat purchase rate | Customer stickiness |\n| Average order value over time | Purchase behavior evolution |\n| Time to second purchase | Engagement health |\n| LTV (revenue per cohort) | True customer value |\n| CAC : LTV ratio | Channel\u002Fcampaign profitability |\n\n### LTV by Acquisition Source\n\nCompare LTV by channel, campaign, and audience segment:\n\n| Channel | CPA | 30-day LTV | 90-day LTV | 365-day LTV | LTV:CAC |\n|---------|-----|-----------|-----------|-------------|---------|\n| Google Search (brand) | $45 | $180 | $250 | $380 | 8.4x |\n| Meta ASC | $52 | $145 | $210 | $340 | 6.5x |\n| Google PMax | $58 | $120 | $180 | $290 | 5.0x |\n| Meta Prospecting | $65 | $95 | $150 | $250 | 3.8x |\n\n**What this reveals:** Channels with higher short-term CPA may still be profitable if LTV is strong. Channels with low CPA but poor LTV are actually expensive.\n\n### POAS > ROAS\n\n**POAS (Profit On Ad Spend):** Gross profit ÷ ad spend. Better than ROAS for ecommerce because it factors in actual product margin.\n\nExample: $500 ROAS looks great until you learn the product has 8% margin → true profit is $40 per $100 spent. Another channel at 300% ROAS with 40% margin returns $120 profit per $100 spent.\n\n**Implementation:** Feed LTV data back into value-based bidding. Use Google's Maximize Conversion Value + tROAS and Meta's ROAS Goal with dynamic conversion values.\n\n## Incrementality & Lift Testing\n\nPlatform-reported ROAS often overstates channel impact (credit-grabbing from organic demand).\n\n### Methods\n\n| Method | How | When |\n|--------|-----|------|\n| **Google Conversion Lift** | Holdout test within Google Ads | 2025 update: lower spend\u002Fconversion minimums. Can run at campaign level or manager account level |\n| **Meta Conversion Lift** | Holdout group excluded from ads | Need sufficient volume; request via Meta rep |\n| **Geo-based lift test** | Turn off campaigns in specific regions, compare | Need multi-region footprint; works cross-platform |\n| **MMM (Marketing Mix Modeling)** | Statistical model of all channels vs outcomes | Larger budgets; Google's Meridian is open-source |\n| **Holdout experiments** | Target cohort gets no ads, measure difference | Requires first-party audience control |\n\n### Questions Incrementality Answers\n\n- \"If I turned off YouTube, what happens to non-brand search?\"\n- \"If I turned off Meta prospecting, does total revenue change?\"\n- \"Is brand search capturing demand created by upper-funnel channels?\"\n- \"Are retargeting conversions incremental or would they have happened anyway?\"\n\n**MMM + incrementality calibration:** Google's Meridian (open-source MMM, 2025) combines granular media signals with incrementality calibration. The right way to do cross-channel budget planning at scale.\n\n## Cross-Channel Analysis\n\n### Marketing Efficiency Ratio (MER)\n\n**MER = Total Revenue ÷ Total Ad Spend (all channels)**\n\n- Blended metric. Resilient to attribution changes\n- Goal: maintain or improve over time\n- Doesn't tell you which channel deserves credit, but tells you overall efficiency\n\n### Marginal ROAS\n\nAs you increase spend in a channel, each additional dollar produces less return (diminishing returns). The question: at what spend level does marginal ROAS drop below target?\n\n**Method:**\n1. Plot spend vs revenue for a channel over 6-12 months\n2. Fit a diminishing returns curve\n3. Find the spend level where marginal ROAS = target ROAS\n4. That's your efficient frontier for that channel\n\n### Channel Role Assignment\n\nNot every channel should optimize to the same metric. Assign roles:\n\n| Role | Primary Metric | Example Channels |\n|------|---------------|-----------------|\n| **Awareness** | Reach, CPM, Ad Recall Lift | YouTube Demand Gen, Meta Awareness |\n| **Consideration** | CTR, engagement, ViewContent | Meta Prospecting, Google Display |\n| **Conversion** | CPA, ROAS | Google Search Brand, Meta Retargeting |\n| **Full-funnel scale** | MER, blended ROAS | Google PMax, Meta ASC |\n\n**2025 Google feature:** Import cost data from Meta, TikTok, Pinterest directly into GA4 for cross-platform comparison in one place.\n\nFor multi-channel budget reallocation, use the **ad-spend-allocator** skill.\n\n## Output Format\n\n```\n## Campaign Performance Analysis\n\n### Question Analyzed\n[Specific question the analysis addresses]\n\n### Data Sources\n- [Platforms]\n- [Date range]\n- [Segments included]\n\n### Key Findings\n1. **[Finding 1]** — [Data point] — [Why this matters]\n2. **[Finding 2]** — [Data point] — [Why this matters]\n3. **[Finding 3]** — [Data point] — [Why this matters]\n\n### Supporting Data\n[Tables and metrics supporting findings]\n\n### Narrative\n[Story: what happened, why it happened, what to do]\n\n### Recommended Actions\n| Priority | Action | Impact | Owner | Timeline |\n|----------|--------|--------|-------|----------|\n| 1 | [action] | [expected impact] | [who] | [when] |\n\n### Data Confidence & Caveats\n- [What the data supports reliably]\n- [What needs more information or isn't certain]\n```\n\n## Example\n\n**Input:** \"Our ecommerce account's blended ROAS dropped from 3.8x to 2.9x over the last quarter. Google is steady, Meta declined hard. I have 90 days of data by channel, campaign, and creative. Help me figure out what's happening.\"\n\n**Output:**\n\n## Campaign Performance Analysis\n\n### Question Analyzed\nWhy did blended ROAS decline from 3.8x to 2.9x in Q1 2026, and which channel\u002Fcampaign\u002Fcreative drove the decline?\n\n### Data Sources\n- Google Ads + Meta Ads exports\n- 90-day window (January–March 2026)\n- Segmented by channel, campaign, creative\n\n### Key Findings\n1. **Meta drove 85% of the blended decline** — Google ROAS held at 4.1x (down from 4.2x — flat). Meta ROAS dropped from 3.5x to 2.1x (-40%). Blended decline is almost entirely Meta\n2. **Meta decline is creative fatigue, not audience or tracking** — Top 3 creatives running 50+ days each. Average creative frequency climbed from 3.1 to 5.8 over 90 days. Meta research: 45% conversion drop at 4+ exposures\n3. **CPM inflation contributed ~15% of Meta decline** — Meta average ad price up 9% in 2025. For this account, CPMs rose from $12.40 to $14.20 (+15%). This is real cost pressure, not just creative failure\n4. **Google is stable because Smart Bidding is managing efficiency** — PMax and Search are both on tROAS with regular n-gram review. No similar discipline on Meta creative\n\n### Supporting Data\n\n**Channel-level ROAS trend:**\n| Channel | Jan | Feb | Mar | Change |\n|---------|-----|-----|-----|--------|\n| Google Search | 4.5x | 4.3x | 4.0x | -11% |\n| Google PMax | 3.8x | 3.9x | 4.1x | +8% |\n| Google blended | 4.2x | 4.1x | 4.1x | -2% |\n| Meta ASC | 3.6x | 2.9x | 2.2x | -39% |\n| Meta Retargeting | 5.2x | 3.8x | 2.4x | -54% |\n| Meta blended | 3.5x | 2.8x | 2.1x | -40% |\n| **Blended total** | **3.8x** | **3.2x** | **2.9x** | **-24%** |\n\n**Meta creative frequency trend:**\n| Creative | Jan freq | Feb freq | Mar freq | Status |\n|---------|---------|---------|---------|--------|\n| Creative A (static) | 2.8 | 4.5 | 6.2 | Severely fatigued |\n| Creative B (video) | 3.2 | 5.1 | 6.8 | Severely fatigued |\n| Creative C (carousel) | 2.9 | 4.2 | 5.4 | Fatigued |\n| Creative D (UGC video) | 1.8 | 2.4 | 3.1 | Healthy (recent addition) |\n\n### Narrative\nYour blended ROAS decline is a Meta creative fatigue story with a CPM inflation chaser. Google is fine — Smart Bidding + disciplined n-gram review keeps it healthy. On Meta, you've run the same 3 creatives for 50+ days, frequency is at 5.8 across top creatives, and Meta's research shows 45% conversion rate drop at 4+ exposures. Meta's CPM increase (+9% industry-wide in 2025, +15% for your account) adds background pressure but is secondary — even at old CPMs, fatigue would still be dragging ROAS.\n\nThe silver lining: your one recent creative addition (D — UGC video, frequency 3.1) is performing well. This is the signal that creative rotation works for your audience; you just haven't been doing it.\n\n### Recommended Actions\n| Priority | Action | Impact | Owner | Timeline |\n|----------|--------|--------|-------|----------|\n| 1 | Pause Creative A and B (highest frequency). Launch 6 new variants (3 UGC video, 3 static) | Restore Meta ROAS toward 3.0x+ | Media buyer + creative | Week 1 |\n| 2 | Build weekly creative rotation pipeline — minimum 4 new variants per week | Prevent fatigue recurrence | Creative team | Ongoing |\n| 3 | Add Meta frequency automation rule — pause creatives at freq >5 | Automated fatigue protection | Media buyer | Week 1 |\n| 4 | Reprice remaining Meta budget against new CPM reality — may need 10-15% budget increase to maintain same volume | Offset CPM inflation | Finance + media buyer | Week 2 |\n| 5 | Replicate Google's n-gram discipline for Meta placement\u002Fcreative reviews | Build sustainable Meta process | Media buyer | Ongoing |\n\n### Data Confidence & Caveats\n- **High confidence:** Creative fatigue is the primary driver. Frequency data, ROAS decline timing, and the Creative D performance all point to the same conclusion\n- **Medium confidence:** CPM inflation contribution (~15%) is a rough estimate based on industry averages; your specific CPM trend confirms it's real but the exact split with creative fatigue can't be precisely calculated without an A\u002FB test\n- **Untested:** Incrementality — platform-reported ROAS may overstate true channel impact. Consider running a Meta Conversion Lift test in Q2 to validate blended ROAS represents actual business lift\n- **Not included:** LTV analysis — if Meta retargeting has higher LTV, the CPA increase may be tolerable. Recommend 90-day LTV analysis as follow-up\n- Use the **meta-ads-creative-engine** skill for creative testing framework implementation\n- Use the **ad-spend-allocator** skill for cross-channel budget reallocation after creative rotation stabilizes\n\n## Guidelines\n\n- **Don't confuse correlation with causation.** Two trends moving together (ROAS down, frequency up) correlate. To confirm causation, test the intervention (refresh creative, see if ROAS recovers).\n- **Don't analyze without a question.** \"Tell me about the account\" produces vanity dashboards. \"Why did CPA rise in March?\" produces insight. Always start with the specific question.\n- **Don't ignore base rates.** An account with 10 conversions\u002Fday has huge daily variance. A change that looks significant may be noise. Require statistical meaningfulness (50+ conversions per segment for reliable segment analysis).\n- **Don't overweight platform-reported ROAS.** Both Google and Meta take credit for conversions that may have happened anyway. For strategic decisions, triangulate platform ROAS with MER, incrementality, and LTV.\n- **Don't report metrics without narrative.** \"CPA is $62\" is data. \"CPA rose from $48 to $62 because creative fatigue hit in mid-February, same period frequency exceeded 4, confirmed by Creative D's outperformance proving rotation works\" is insight. Insight drives action.\n- **Don't skip segmentation.** Account averages hide winning and losing segments. Always break down by device, geo, audience, creative, placement. Hidden patterns drive hidden wins.\n- **Meta Instant Experience change (June 2025):** No longer counts as a landing page view. If Meta funnel metrics look broken mid-2025, this is why.\n- **Meta attribution API change (October 2025):** `7d_view` and `28d_view` windows removed from Insights API. Reports pulling these need updates.\n- **Don't overreact to a single week.** Weekly variance is normal. Look for 2+ week trends before declaring changes.\n- **Cross-references:** For Google-specific optimization actions, use the **google-ads-optimizer** skill. For Meta-specific optimization, use the **meta-ads-optimizer** skill. For creative testing frameworks, use the **meta-ads-creative-engine** skill. For cross-channel budget reallocation, use the **ad-spend-allocator** skill. For reporting the analysis to stakeholders, use the **paid-media-reporter** skill. For full audits, use **google-ads-audit** or **meta-ads-audit**.\n- **Confidence:** Channel attribution is inherently imperfect. All multi-touch attribution models make assumptions. State what the data supports clearly and what requires incrementality testing to confirm.\n","## Process\n\n1. **Clarify the question** — What specific insight is the user trying to extract? (\"Why is CPA rising?\" vs \"What's the LTV by channel?\")\n2. **Select analysis type** — Match the question to the right framework (pulse, strategic, dimensional, funnel, cohort, incrementality, cross-channel)\n3. **Gather required data** — Request exports needed for the analysis\n4. **Run the analysis** — Apply the specific method\n5. **Identify the story** — What happened, why it happened, what to do about it\n6. **Deliver findings** — Structured output with insights, not just metrics\n\n## Analysis Type Selector\n\n| Question | Analysis Type | Time Horizon |\n|----------|--------------|-------------|\n| \"Is anything broken right now?\" | Daily pulse monitoring | 1-7 days |\n| \"How are we trending this week\u002Fmonth?\" | Weekly\u002Fmonthly strategic review | 7-30 days |\n| \"Where is performance coming from\u002Fgoing to?\" | Multi-dimensional analysis | 30-90 days |\n| \"Where are users dropping off?\" | Funnel analysis | 7-30 days |\n| \"How valuable are acquired customers over time?\" | Cohort & LTV analysis | 30-365+ days |\n| \"Is this channel actually driving incremental results?\" | Incrementality testing | 30-90 days |\n| \"How do channels compare and work together?\" | Cross-channel analysis | 30-90 days |\n\n## Daily Pulse Monitoring\n\n**What to check:**\n- Cost, impressions, clicks, conversions, spend pacing vs budget\n- Sudden metric changes (CPC spikes, conversion drops, budget exhaustion)\n- Meta: learning phase status per ad set\n- Disapprovals, policy flags, payment issues\n\n**Alert thresholds:** Automated alerts for >20% deviation from 7-day averages on key metrics.\n\n**What NOT to do:** Don't optimize during daily pulse. Daily review is for catching emergencies, not making strategic changes. Save optimization decisions for weekly reviews.\n\n**Cadence insight (Supermetrics research):** Most successful performance marketers prioritize basic metrics (cost, impressions, clicks, conversions) for daily decisions. Deeper analysis (frequency, LTV, attribution) is purposeful, not constant.\n\n## Weekly\u002FMonthly Strategic Review\n\n**Key metrics by platform:**\n\n| Google Ads | Meta Ads |\n|-----------|---------|\n| CTR, CPC, CPA, ROAS | CPM, CPC, CPA, ROAS |\n| Conversion rate | Frequency, Conversion rate |\n| Impression share | Reach, Delivery status |\n| Quality Score trends | Learning phase status |\n| Search term movement | Creative performance |\n\n**Review structure:**\n1. **Scaling candidates** — Campaigns with strong ROAS + available impression share (Google) or frequency headroom (Meta) → recommend budget increases\n2. **Pause\u002Fpullback candidates** — Campaigns with high CPA + declining trend → recommend reductions\n3. **Creative performance** — Which ads\u002Fcreatives are winning, which are fatiguing\n4. **Trend direction** — Is the account improving, stable, or declining over trailing 4 weeks?\n\n## Multi-Dimensional Performance Analysis\n\nSlice performance across dimensions to find hidden drivers.\n\n### Dimensions to Analyze\n\n| Dimension | What to Look For |\n|-----------|-----------------|\n| Device type | Mobile vs desktop vs tablet CPA\u002FROAS differences |\n| Geography | Regional performance variance (country, state, DMA) |\n| Time of day | Hour-by-hour conversion rate patterns |\n| Day of week | Day-by-day performance patterns |\n| Audience segment | Segment-level CPA\u002FROAS comparison |\n| Match type (Google) | Broad vs phrase vs exact performance |\n| Placement (Meta) | Feed vs Stories vs Reels vs Audience Network |\n| Creative concept | Concept-level performance patterns |\n| Landing page | Landing page-level conversion rate |\n| Funnel stage | TOF vs MOF vs BOF performance |\n\n### Cross-Tab Analysis\n\nCombine dimensions to find non-obvious patterns:\n\n| Cross-Tab | What It Reveals | Example |\n|-----------|----------------|---------|\n| Device × Time of day | When mobile converts vs desktop | Mobile converts 3x better in evening hours |\n| Audience × Creative | Which creatives resonate with which audiences | UGC wins with Lookalike, studio wins with cold broad |\n| Geography × Product | Regional product preferences | Coastal states prefer product A, interior prefer product B |\n| Day × Creative concept | Which concepts work when | Emotional creative wins Sunday, rational wins Tuesday |\n| Placement × Video length | Optimal length per placement | 15s wins Stories, 30s wins Feed |\n\n### Red Flags to Watch\n\n- **One dimension dominating cost but not conversions** → Budget misallocation\n- **Large variance across segments** → Opportunity to isolate winners\n- **Hidden loss leaders** → Specific segments dragging average down\n\n## Funnel Analysis\n\nMap every stage from impression to final conversion.\n\n### Standard Funnel Stages\n\n| Stage | Metric | Benchmark to Check |\n|-------|--------|-------------------|\n| Impression | Impressions | Reach sufficient for audience? |\n| Click | CTR, clicks | Industry CTR benchmarks |\n| Landing page view | Landing page views | Bounce rate, load speed |\n| Micro-conversion | AddToCart, video 50%, scroll depth | Stage-specific |\n| Macro-conversion | Purchase, Lead, Signup | Target CPA \u002F ROAS |\n\n**Calculate stage-by-stage conversion rates.** Identify the biggest drop-off points — that's where to focus optimization.\n\n### Drop-Off Diagnostics\n\n| Drop-Off Point | Likely Cause | Fix |\n|---------------|-------------|-----|\n| Impression → Click | Low CTR | Ad copy, ad creative, targeting |\n| Click → Landing Page View | Slow page, 404s, disconnected UX | Page speed, fix broken flows |\n| Landing Page View → Add to Cart | Landing page message mismatch, bad UX | Rewrite headlines, improve CTA |\n| Add to Cart → Checkout | Friction, unexpected costs | Simplify checkout, show total costs |\n| Checkout → Purchase | Payment issues, trust concerns | Add trust signals, multiple payment options |\n\n**Meta-specific (June 2025):** Instant Experience is no longer counted as a landing page view. If your Meta funnel metrics suddenly showed a drop in mid-2025, this is likely why. Adjust funnel definitions accordingly.\n\n## Cohort & Lifetime Value Analysis\n\n### Cohort Windows\n\nTrack customer cohorts at standard intervals:\n- Day 1, 7, 14, 30 (short-term retention)\n- Day 30, 60, 90 (medium-term)\n- Day 180, 365 (long-term LTV)\n\n### Metrics to Track per Cohort\n\n| Metric | What It Tells You |\n|--------|------------------|\n| Repeat purchase rate | Customer stickiness |\n| Average order value over time | Purchase behavior evolution |\n| Time to second purchase | Engagement health |\n| LTV (revenue per cohort) | True customer value |\n| CAC : LTV ratio | Channel\u002Fcampaign profitability |\n\n### LTV by Acquisition Source\n\nCompare LTV by channel, campaign, and audience segment:\n\n| Channel | CPA | 30-day LTV | 90-day LTV | 365-day LTV | LTV:CAC |\n|---------|-----|-----------|-----------|-------------|---------|\n| Google Search (brand) | $45 | $180 | $250 | $380 | 8.4x |\n| Meta ASC | $52 | $145 | $210 | $340 | 6.5x |\n| Google PMax | $58 | $120 | $180 | $290 | 5.0x |\n| Meta Prospecting | $65 | $95 | $150 | $250 | 3.8x |\n\n**What this reveals:** Channels with higher short-term CPA may still be profitable if LTV is strong. Channels with low CPA but poor LTV are actually expensive.\n\n### POAS > ROAS\n\n**POAS (Profit On Ad Spend):** Gross profit ÷ ad spend. Better than ROAS for ecommerce because it factors in actual product margin.\n\nExample: $500 ROAS looks great until you learn the product has 8% margin → true profit is $40 per $100 spent. Another channel at 300% ROAS with 40% margin returns $120 profit per $100 spent.\n\n**Implementation:** Feed LTV data back into value-based bidding. Use Google's Maximize Conversion Value + tROAS and Meta's ROAS Goal with dynamic conversion values.\n\n## Incrementality & Lift Testing\n\nPlatform-reported ROAS often overstates channel impact (credit-grabbing from organic demand).\n\n### Methods\n\n| Method | How | When |\n|--------|-----|------|\n| **Google Conversion Lift** | Holdout test within Google Ads | 2025 update: lower spend\u002Fconversion minimums. Can run at campaign level or manager account level |\n| **Meta Conversion Lift** | Holdout group excluded from ads | Need sufficient volume; request via Meta rep |\n| **Geo-based lift test** | Turn off campaigns in specific regions, compare | Need multi-region footprint; works cross-platform |\n| **MMM (Marketing Mix Modeling)** | Statistical model of all channels vs outcomes | Larger budgets; Google's Meridian is open-source |\n| **Holdout experiments** | Target cohort gets no ads, measure difference | Requires first-party audience control |\n\n### Questions Incrementality Answers\n\n- \"If I turned off YouTube, what happens to non-brand search?\"\n- \"If I turned off Meta prospecting, does total revenue change?\"\n- \"Is brand search capturing demand created by upper-funnel channels?\"\n- \"Are retargeting conversions incremental or would they have happened anyway?\"\n\n**MMM + incrementality calibration:** Google's Meridian (open-source MMM, 2025) combines granular media signals with incrementality calibration. The right way to do cross-channel budget planning at scale.\n\n## Cross-Channel Analysis\n\n### Marketing Efficiency Ratio (MER)\n\n**MER = Total Revenue ÷ Total Ad Spend (all channels)**\n\n- Blended metric. Resilient to attribution changes\n- Goal: maintain or improve over time\n- Doesn't tell you which channel deserves credit, but tells you overall efficiency\n\n### Marginal ROAS\n\nAs you increase spend in a channel, each additional dollar produces less return (diminishing returns). The question: at what spend level does marginal ROAS drop below target?\n\n**Method:**\n1. Plot spend vs revenue for a channel over 6-12 months\n2. Fit a diminishing returns curve\n3. Find the spend level where marginal ROAS = target ROAS\n4. That's your efficient frontier for that channel\n\n### Channel Role Assignment\n\nNot every channel should optimize to the same metric. Assign roles:\n\n| Role | Primary Metric | Example Channels |\n|------|---------------|-----------------|\n| **Awareness** | Reach, CPM, Ad Recall Lift | YouTube Demand Gen, Meta Awareness |\n| **Consideration** | CTR, engagement, ViewContent | Meta Prospecting, Google Display |\n| **Conversion** | CPA, ROAS | Google Search Brand, Meta Retargeting |\n| **Full-funnel scale** | MER, blended ROAS | Google PMax, Meta ASC |\n\n**2025 Google feature:** Import cost data from Meta, TikTok, Pinterest directly into GA4 for cross-platform comparison in one place.\n\nFor multi-channel budget reallocation, use the **ad-spend-allocator** skill.\n\n## Output Format\n\n```\n## Campaign Performance Analysis\n\n### Question Analyzed\n[Specific question the analysis addresses]\n\n### Data Sources\n- [Platforms]\n- [Date range]\n- [Segments included]\n\n### Key Findings\n1. **[Finding 1]** — [Data point] — [Why this matters]\n2. **[Finding 2]** — [Data point] — [Why this matters]\n3. **[Finding 3]** — [Data point] — [Why this matters]\n\n### Supporting Data\n[Tables and metrics supporting findings]\n\n### Narrative\n[Story: what happened, why it happened, what to do]\n\n### Recommended Actions\n| Priority | Action | Impact | Owner | Timeline |\n|----------|--------|--------|-------|----------|\n| 1 | [action] | [expected impact] | [who] | [when] |\n\n### Data Confidence & Caveats\n- [What the data supports reliably]\n- [What needs more information or isn't certain]\n```\n\n## Example\n\n**Input:** \"Our ecommerce account's blended ROAS dropped from 3.8x to 2.9x over the last quarter. Google is steady, Meta declined hard. I have 90 days of data by channel, campaign, and creative. Help me figure out what's happening.\"\n\n**Output:**\n\n## Campaign Performance Analysis\n\n### Question Analyzed\nWhy did blended ROAS decline from 3.8x to 2.9x in Q1 2026, and which channel\u002Fcampaign\u002Fcreative drove the decline?\n\n### Data Sources\n- Google Ads + Meta Ads exports\n- 90-day window (January–March 2026)\n- Segmented by channel, campaign, creative\n\n### Key Findings\n1. **Meta drove 85% of the blended decline** — Google ROAS held at 4.1x (down from 4.2x — flat). Meta ROAS dropped from 3.5x to 2.1x (-40%). Blended decline is almost entirely Meta\n2. **Meta decline is creative fatigue, not audience or tracking** — Top 3 creatives running 50+ days each. Average creative frequency climbed from 3.1 to 5.8 over 90 days. Meta research: 45% conversion drop at 4+ exposures\n3. **CPM inflation contributed ~15% of Meta decline** — Meta average ad price up 9% in 2025. For this account, CPMs rose from $12.40 to $14.20 (+15%). This is real cost pressure, not just creative failure\n4. **Google is stable because Smart Bidding is managing efficiency** — PMax and Search are both on tROAS with regular n-gram review. No similar discipline on Meta creative\n\n### Supporting Data\n\n**Channel-level ROAS trend:**\n| Channel | Jan | Feb | Mar | Change |\n|---------|-----|-----|-----|--------|\n| Google Search | 4.5x | 4.3x | 4.0x | -11% |\n| Google PMax | 3.8x | 3.9x | 4.1x | +8% |\n| Google blended | 4.2x | 4.1x | 4.1x | -2% |\n| Meta ASC | 3.6x | 2.9x | 2.2x | -39% |\n| Meta Retargeting | 5.2x | 3.8x | 2.4x | -54% |\n| Meta blended | 3.5x | 2.8x | 2.1x | -40% |\n| **Blended total** | **3.8x** | **3.2x** | **2.9x** | **-24%** |\n\n**Meta creative frequency trend:**\n| Creative | Jan freq | Feb freq | Mar freq | Status |\n|---------|---------|---------|---------|--------|\n| Creative A (static) | 2.8 | 4.5 | 6.2 | Severely fatigued |\n| Creative B (video) | 3.2 | 5.1 | 6.8 | Severely fatigued |\n| Creative C (carousel) | 2.9 | 4.2 | 5.4 | Fatigued |\n| Creative D (UGC video) | 1.8 | 2.4 | 3.1 | Healthy (recent addition) |\n\n### Narrative\nYour blended ROAS decline is a Meta creative fatigue story with a CPM inflation chaser. Google is fine — Smart Bidding + disciplined n-gram review keeps it healthy. On Meta, you've run the same 3 creatives for 50+ days, frequency is at 5.8 across top creatives, and Meta's research shows 45% conversion rate drop at 4+ exposures. Meta's CPM increase (+9% industry-wide in 2025, +15% for your account) adds background pressure but is secondary — even at old CPMs, fatigue would still be dragging ROAS.\n\nThe silver lining: your one recent creative addition (D — UGC video, frequency 3.1) is performing well. This is the signal that creative rotation works for your audience; you just haven't been doing it.\n\n### Recommended Actions\n| Priority | Action | Impact | Owner | Timeline |\n|----------|--------|--------|-------|----------|\n| 1 | Pause Creative A and B (highest frequency). Launch 6 new variants (3 UGC video, 3 static) | Restore Meta ROAS toward 3.0x+ | Media buyer + creative | Week 1 |\n| 2 | Build weekly creative rotation pipeline — minimum 4 new variants per week | Prevent fatigue recurrence | Creative team | Ongoing |\n| 3 | Add Meta frequency automation rule — pause creatives at freq >5 | Automated fatigue protection | Media buyer | Week 1 |\n| 4 | Reprice remaining Meta budget against new CPM reality — may need 10-15% budget increase to maintain same volume | Offset CPM inflation | Finance + media buyer | Week 2 |\n| 5 | Replicate Google's n-gram discipline for Meta placement\u002Fcreative reviews | Build sustainable Meta process | Media buyer | Ongoing |\n\n### Data Confidence & Caveats\n- **High confidence:** Creative fatigue is the primary driver. Frequency data, ROAS decline timing, and the Creative D performance all point to the same conclusion\n- **Medium confidence:** CPM inflation contribution (~15%) is a rough estimate based on industry averages; your specific CPM trend confirms it's real but the exact split with creative fatigue can't be precisely calculated without an A\u002FB test\n- **Untested:** Incrementality — platform-reported ROAS may overstate true channel impact. Consider running a Meta Conversion Lift test in Q2 to validate blended ROAS represents actual business lift\n- **Not included:** LTV analysis — if Meta retargeting has higher LTV, the CPA increase may be tolerable. Recommend 90-day LTV analysis as follow-up\n- Use the **meta-ads-creative-engine** skill for creative testing framework implementation\n- Use the **ad-spend-allocator** skill for cross-channel budget reallocation after creative rotation stabilizes\n\n## Guidelines\n\n- **Don't confuse correlation with causation.** Two trends moving together (ROAS down, frequency up) correlate. To confirm causation, test the intervention (refresh creative, see if ROAS recovers).\n- **Don't analyze without a question.** \"Tell me about the account\" produces vanity dashboards. \"Why did CPA rise in March?\" produces insight. Always start with the specific question.\n- **Don't ignore base rates.** An account with 10 conversions\u002Fday has huge daily variance. A change that looks significant may be noise. Require statistical meaningfulness (50+ conversions per segment for reliable segment analysis).\n- **Don't overweight platform-reported ROAS.** Both Google and Meta take credit for conversions that may have happened anyway. For strategic decisions, triangulate platform ROAS with MER, incrementality, and LTV.\n- **Don't report metrics without narrative.** \"CPA is $62\" is data. \"CPA rose from $48 to $62 because creative fatigue hit in mid-February, same period frequency exceeded 4, confirmed by Creative D's outperformance proving rotation works\" is insight. Insight drives action.\n- **Don't skip segmentation.** Account averages hide winning and losing segments. Always break down by device, geo, audience, creative, placement. Hidden patterns drive hidden wins.\n- **Meta Instant Experience change (June 2025):** No longer counts as a landing page view. If Meta funnel metrics look broken mid-2025, this is why.\n- **Meta attribution API change (October 2025):** `7d_view` and `28d_view` windows removed from Insights API. Reports pulling these need updates.\n- **Don't overreact to a single week.** Weekly variance is normal. Look for 2+ week trends before declaring changes.\n- **Cross-references:** For Google-specific optimization actions, use the **google-ads-optimizer** skill. For Meta-specific optimization, use the **meta-ads-optimizer** skill. For creative testing frameworks, use the **meta-ads-creative-engine** skill. For cross-channel budget reallocation, use the **ad-spend-allocator** skill. For reporting the analysis to stakeholders, use the **paid-media-reporter** skill. For full audits, use **google-ads-audit** or **meta-ads-audit**.\n- **Confidence:** Channel attribution is inherently imperfect. All multi-touch attribution models make assumptions. State what the data supports clearly and what requires incrementality testing to confirm.\n",{"name":5,"description":7},"main","c137446804eb85b2cc0ba009c62068253a7c47be","skills\u002Fcampaign-analyzer",2,"https:\u002F\u002Fgithub.com\u002Fnarayan-metaflow\u002Fmetaflow-marketing-skills","https:\u002F\u002Fgithub.com\u002Fnarayan-metaflow","engineer by education, marketer by profession, building rn","2026-09-16 13:41:44",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add narayan-metaflow\u002Fmetaflow-marketing-skills --skill campaign-analyzer",{"tool":63,"command":64},"bunx","bunx skills add narayan-metaflow\u002Fmetaflow-marketing-skills --skill campaign-analyzer",{"tool":66,"command":67},"pnpm","pnpm dlx skills add narayan-metaflow\u002Fmetaflow-marketing-skills --skill campaign-analyzer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnarayan-metaflow\u002Fmetaflow-marketing-skills\u002Fblob\u002Fmain\u002Fskills\u002Fcampaign-analyzer\u002FSKILL.md",true,[],[72,99,127,148,177,205],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":80,"publishedAt":44},"01M718Q16XB7D7ZMGNNA1226G5","technical-seo-ai-crawler-audit","Diagnose and prioritize the technical issues blocking a site from being crawled, indexed, ranked, and cited. Modern technical SEO has two audiences: Google's crawler\u002Findexer and AI answer engines (GPTBot, PerplexityBot, ClaudeBot, etc.). Both need HTML-visible content and a clean crawl path.","https:\u002F\u002Fgithub.com\u002Fnarayan-metaflow\u002Fmetaflow-marketing-skills\u002Fblob\u002Fmain\u002Fskills\u002Ftechnical-seo-ai-crawler-audit\u002FSKILL.md",[78,79],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98],"seo","technical","technical seo","technical seo ai crawler audit","audit","crawler","crawl","diagnose","answer","issues","clean","indexer","google","prioritize","site","content","html","path",{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":110,"publishedAt":44},"01M718PY2PKA7BYS5KNJ2A9DRT","seo-reporting-measurement","Build reports that stakeholders trust, rooted in data sources that are actually reliable. Modern SEO measurement has to reckon with a very specific constraint: **the primary data source (GSC) is ~75% incomplete**, and the AI visibility layer is **probabilistic**, not deterministic. Building reports that ignore these realities produces false confidence.","https:\u002F\u002Fgithub.com\u002Fnarayan-metaflow\u002Fmetaflow-marketing-skills\u002Fblob\u002Fmain\u002Fskills\u002Fseo-reporting-measurement\u002FSKILL.md",[105,106,109],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":107,"categoryName":108,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000033","数据分析师",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[111,112,113,114,81,115,116,117,118,119,40,120,121,122,123,124,125,126],"seo reporting","seo reporting measurement","reporting","measurement","sources","gsc","false","reports","data sources","layer","source","deterministic","trust","with","build","constraint",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":135,"publishedAt":44},"01M718PVF0SP35J6S9EHRGQZQ1","seo-max-kt","Long-form SEO and AEO methodology bundle; read SEO_AND_AEO_KT.md for the full corpus.","https:\u002F\u002Fgithub.com\u002Fnarayan-metaflow\u002Fmetaflow-marketing-skills\u002Fblob\u002Fmain\u002Fskills\u002Fseo-max-kt\u002FSKILL.md",[133,134],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[136,81,137,138,139,140,141,142,143,144,145,146,147],"kt","seo max kt","max","aeo","long-form","methodology","form","for","bundle","full","read","long",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":159,"publishedAt":44},"01M718PRQNX2JF71GBFTH3MV19","seo-keyword-research-intent-mapping","Build a keyword universe that reflects how both humans *and* AI answer engines search. Traditional keyword research looks at standalone terms; modern research also maps the **fan-out sub-queries** AI tools generate when breaking down a user prompt.","https:\u002F\u002Fgithub.com\u002Fnarayan-metaflow\u002Fmetaflow-marketing-skills\u002Fblob\u002Fmain\u002Fskills\u002Fseo-keyword-research-intent-mapping\u002FSKILL.md",[154,155,158],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":156,"categoryName":157,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[81,160,161,162,163,164,165,166,167,168,89,169,170,171,172,173,174,125,175,176],"seo keyword research","seo keyword research intent mapping","research","intent","keyword research","mapping","ai tools","standalone","down","search","prompt","when","maps","queries","generate","how","at",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":191,"publishedAt":44},"01M718PNDT3A19SV7KVWC9083P","seo-aeo-content-strategy","Design content systems that earn both Google rankings *and* AI citations. The core insight: AI answer engines read content differently than humans — they extract the highest-information-gain sentences and treat H2 headings as prompts. The \"ski ramp\" structure optimizes for both.","https:\u002F\u002Fgithub.com\u002Fnarayan-metaflow\u002Fmetaflow-marketing-skills\u002Fblob\u002Fmain\u002Fskills\u002Fseo-aeo-content-strategy\u002FSKILL.md",[183,186,187,188],{"categoryNo":184,"categoryName":185,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},{"categoryNo":189,"categoryName":190,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000036","内容创作者",[81,139,192,193,194,96,195,196,197,143,89,198,199,200,201,146,202,203,93,204],"strategy","seo aeo content strategy","content strategy","Citations","as","core","design","information","earn","structure","systems","ramp","prompts",{"skillNo":206,"name":207,"nameZh":6,"description":208,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":209,"categories":210,"keywords":214,"publishedAt":44},"01M718PJM103BE7581G6NRCC7T","prompt-picker","Build a prompt library that reveals how a brand shows up across the full buyer journey in AI search systems. The library is designed for actual LLM visibility tracking, not theoretical SEO keyword research.","https:\u002F\u002Fgithub.com\u002Fnarayan-metaflow\u002Fmetaflow-marketing-skills\u002Fblob\u002Fmain\u002Fskills\u002Fprompt-picker\u002FSKILL.md",[211],{"categoryNo":212,"categoryName":213,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[215,170,216,217,81,143,160,169,218,219,220,38,162,125,175,202,164,221,222,145],"prompt picker","llm visibility","brand","up","journey","prompt library","library","tracking"]