Ads Execution Hub
Purpose
Core mission:
- Serve as the dedicated ad operations and optimization interface.
- Manage planning, launch, monitoring, and scaling across ad channels.
- Standardize decision policies for bidding, budget, and performance recovery.
- Output clear operator actions for media teams.
When To Trigger
Use this skill when the user asks for:
- campaign setup, optimization, or scaling in one or more channels
- budget and bidding decision support with performance constraints
- anomaly diagnosis and recovery actions for live campaigns
- cross-channel media operation playbooks
High-signal keywords:
- ads execution hub, run ads, campaign, media buyer
- bidding, budget, allocation, optimize, scale
- cpa, roas, performance, monitor, abtest
Input Contract
Required:
- campaign_objective
- channel_scope
- budget_constraints
- recent_performance_snapshot
Optional:
- creative_state
- audience_state
- tracking_health
- policy_or_account_flags
Output Contract
- Campaign Action Plan
- Bidding and Budget Policy
- AB Test and Scale Model
- Monitoring and Alert Plan
- Operator Handoff Checklist
Workflow
- Normalize objective and KPI constraints.
- Evaluate channel readiness and structure quality.
- Produce bid and allocation actions.
- Attach testing and scaling rules.
- Return monitoring triggers and operator checklist.
Decision Rules
- If measurement confidence is low, limit scale and improve tracking first.
- If ROAS is stable above threshold, allow staged budget increases.
- If CPA is unstable, reduce concurrency of experiments.
- If anomaly risk is high, prefer containment actions first.
Platform Notes
Primary scope:
- Meta (Facebook/Instagram), Google Ads, TikTok Ads, YouTube Ads, Amazon Ads, Shopify Ads, DSP/programmatic
Platform behavior guidance:
- Keep channel recommendations execution-specific and auditable.
- Align bid logic with each platform's optimization mechanics.
Constraints And Guardrails
- No irreversible changes without rollback conditions.
- Keep every recommendation tied to KPI impact.
- Respect policy and account health constraints.
Failure Handling And Escalation
- If required platform data is missing, return minimum data request list.
- If policy or account block appears, route to compliance/account helper.
- If spend risk is severe, trigger emergency control mode.
Code Examples
Campaign Control Spec
objective: improve_roas
channels: [Meta, GoogleAds, TikTokAds]
budget_mode: staged_scale
cpa_ceiling: 42
roas_floor: 2.5
Alert Trigger Rule
if roas_drop_pct > 20 and spend_up_pct > 25:
severity: high
action: cap_budget_and_notify
Examples
Example 1: Launch and stabilize
Input:
- New campaign across Meta and TikTok Ads
Output focus:
- launch checklist
- first-week controls
- fallback rules
Example 2: Scale after validation
Input:
Output focus:
- scale ladder
- bid policy updates
- monitoring checkpoints
Example 3: Cross-channel anomaly
Input:
- Spend surge, mixed conversion signals
Output focus:
- anomaly triage
- containment actions
- next validation steps
Quality Checklist
1---2name: ads-execution-hub3description: Ads Execution Hub control skill for ad campaign management and optimization across Meta (Facebook/Instagram), Google Ads, TikTok Ads, YouTube Ads, Amazon Ads, Shopify Ads, and DSP/programmatic.4---56# Ads Execution Hub78## Purpose9Core mission:10- Serve as the dedicated ad operations and optimization interface.11- Manage planning, launch, monitoring, and scaling across ad channels.12- Standardize decision policies for bidding, budget, and performance recovery.13- Output clear operator actions for media teams.1415## When To Trigger16Use this skill when the user asks for:17- campaign setup, optimization, or scaling in one or more channels18- budget and bidding decision support with performance constraints19- anomaly diagnosis and recovery actions for live campaigns20- cross-channel media operation playbooks2122High-signal keywords:23- ads execution hub, run ads, campaign, media buyer24- bidding, budget, allocation, optimize, scale25- cpa, roas, performance, monitor, abtest2627## Input Contract28Required:29- campaign_objective30- channel_scope31- budget_constraints32- recent_performance_snapshot3334Optional:35- creative_state36- audience_state37- tracking_health38- policy_or_account_flags3940## Output Contract411. Campaign Action Plan422. Bidding and Budget Policy433. AB Test and Scale Model444. Monitoring and Alert Plan455. Operator Handoff Checklist4647## Workflow481. Normalize objective and KPI constraints.492. Evaluate channel readiness and structure quality.503. Produce bid and allocation actions.514. Attach testing and scaling rules.525. Return monitoring triggers and operator checklist.5354## Decision Rules55- If measurement confidence is low, limit scale and improve tracking first.56- If ROAS is stable above threshold, allow staged budget increases.57- If CPA is unstable, reduce concurrency of experiments.58- If anomaly risk is high, prefer containment actions first.5960## Platform Notes61Primary scope:62- Meta (Facebook/Instagram), Google Ads, TikTok Ads, YouTube Ads, Amazon Ads, Shopify Ads, DSP/programmatic6364Platform behavior guidance:65- Keep channel recommendations execution-specific and auditable.66- Align bid logic with each platform's optimization mechanics.6768## Constraints And Guardrails69- No irreversible changes without rollback conditions.70- Keep every recommendation tied to KPI impact.71- Respect policy and account health constraints.7273## Failure Handling And Escalation74- If required platform data is missing, return minimum data request list.75- If policy or account block appears, route to compliance/account helper.76- If spend risk is severe, trigger emergency control mode.7778## Code Examples79### Campaign Control Spec8081 objective: improve_roas82 channels: [Meta, GoogleAds, TikTokAds]83 budget_mode: staged_scale84 cpa_ceiling: 4285 roas_floor: 2.58687### Alert Trigger Rule8889 if roas_drop_pct > 20 and spend_up_pct > 25:90 severity: high91 action: cap_budget_and_notify9293## Examples94### Example 1: Launch and stabilize95Input:96- New campaign across Meta and TikTok Ads9798Output focus:99- launch checklist100- first-week controls101- fallback rules102103### Example 2: Scale after validation104Input:105- Stable ROAS for 10 days106107Output focus:108- scale ladder109- bid policy updates110- monitoring checkpoints111112### Example 3: Cross-channel anomaly113Input:114- Spend surge, mixed conversion signals115116Output focus:117- anomaly triage118- containment actions119- next validation steps120121## Quality Checklist122- [ ] Required sections are complete and non-empty123- [ ] Trigger keywords include at least 3 registry terms124- [ ] Input and output contracts are operationally testable125- [ ] Workflow and decision rules are capability-specific126- [ ] Platform references are explicit and concrete127- [ ] At least 3 practical examples are included