Ads Campaign Monitor

Monitor live campaign health and anomalies across Meta (Facebook/Instagram), Google Ads, TikTok Ads, YouTube Ads, Amazon Ads, and DSP/programmatic.

Security Scan

The skill claims real-time, cross-platform campaign monitoring but provides no integration mechanism, credentials, or install steps — it's unclear how it would access live advertising data.

Purpose & Capability

The skill's stated purpose is real-time monitoring across many ad platforms (Meta, Google Ads, TikTok, YouTube, Amazon Ads, DSP). Yet the package declares no required environment variables, no connectors, no binaries, and no install steps. Real-time monitoring of those platforms normally requires API credentials, SDKs, or connector configuration; the SKILL.md does not describe how to obtain or use such credentials, so the capability and requirements are mismatched unless the caller always supplies all raw data in the input contract.

Instruction Scope

SKILL.md contains scoped runtime instructions (anomaly detection, triage, ticket payloads) and does not instruct the agent to read arbitrary system files, environment variables, or external endpoints. It assumes the caller provides entity_ids, time windows, and optionally logs_or_events; this is coherent if the skill is purely a decision/triage assistant that operates on provided data. However the document is ambiguous about whether it will (or is allowed to) fetch live data itself — that ambiguity matters for security and operational expectations.

Install Mechanism

No install spec and no code files are present. That minimizes filesystem/network install risk. Because this is instruction-only, there is nothing downloaded or written by the skill bundle itself.

Credentials

The skill declares no required credentials or env vars despite targeting multiple ad platforms. Either (a) it expects callers to supply all platform data in inputs (which should be documented and enforced), or (b) the skill omitted needed API keys/connectors. The omission is disproportionate for the claimed functionality and creates ambiguity about how the skill will operate in practice. If it later requests credentials at runtime, that should be made explicit and limited to necessary scopes.

Persistence & Privilege

always is false and there is no install that alters agent configuration or other skills. The skill does not request permanent presence or elevated agent-level privileges in the manifest.

What to consider before installing

This skill's goal (real-time, cross-platform ad monitoring) normally requires API keys, connectors, or installation of adapters; the bundle provides none. Before installing or using it: (1) Ask the author how it is intended to obtain live platform data — should callers supply logs/events? If it needs API access, require explicit declared env vars and limited scopes. (2) Do not paste credentials into chat; prefer secure connectors or scoped service accounts. (3) Request documented input examples showing how to supply data safely (sanitized/test data first). (4) If you expect autonomous runs, require provenance (who published the skill) and an explanation of what external endpoints it will call. (5) Because source is unknown, treat it cautiously: test with non-sensitive data and require the skill author to add explicit integration/credential declarations before giving it access to real accounts.

Purpose

Core mission:

• real-time thresholding, anomaly triage, alert playbook

This skill is specialized for advertising workflows and should output actionable plans rather than generic advice.

When To Trigger

Use this skill when the user asks for:

• ad execution guidance tied to business outcomes
• growth decisions involving revenue, roas, cpa, or budget efficiency
• platform-level actions for: Meta (Facebook/Instagram), Google Ads, TikTok Ads, YouTube Ads, Amazon Ads, DSP/programmatic
• this specific capability: real-time thresholding, anomaly triage, alert playbook

High-signal keywords:

• ads, advertising, campaign, growth, revenue, profit
• roas, cpa, roi, budget, bidding, traffic, conversion, funnel
• meta, googleads, tiktokads, youtubeads, amazonads, shopifyads, dsp

Input Contract

Required:

• entity_ids: account, campaign, adset, or ad identifiers
• incident_or_audit_scope
• time_window

Optional:

• logs_or_events
• policy_flags
• alert_thresholds
• owner_contacts

Output Contract

1. Operational Status Summary
2. Severity-ranked Findings
3. Mitigation Actions
4. Escalation Ticket Payload
5. Monitoring Checklist

Workflow

1. Confirm operational scope and impacted entities.
2. Validate data freshness and event completeness.
3. Detect anomalies, policy flags, or setup gaps.
4. Rank fixes by spend risk and recovery speed.
5. Emit owner-ready action and ticket payload.

Decision Rules

• If data is stale, block final judgement and request refresh timestamp.
• If high-severity risk is found, recommend containment action first.
• If root cause is uncertain, provide top hypotheses with validation order.

Platform Notes

Primary scope:

• Meta (Facebook/Instagram), Google Ads, TikTok Ads, YouTube Ads, Amazon Ads, DSP/programmatic

Platform behavior guidance:

• Keep recommendations channel-aware; do not collapse all channels into one generic plan.
• For Meta and TikTok Ads, prioritize creative testing cadence.
• For Google Ads and Amazon Ads, prioritize demand-capture and query/listing intent.
• For DSP/programmatic, prioritize audience control and frequency governance.

Constraints And Guardrails

• Never fabricate metrics or policy outcomes.
• Separate observed facts from assumptions.
• Use measurable language for each proposed action.
• Include at least one rollback or stop-loss condition when spend risk exists.

Failure Handling And Escalation

• If critical inputs are missing, ask for only the minimum required fields.
• If platform constraints conflict, show trade-offs and a safe default.
• If confidence is low, mark it explicitly and provide a validation checklist.
• If high-risk issues appear (policy, billing, tracking breakage), escalate with a structured handoff payload.

Code Examples

Incident Ticket Example

ticket_id: INC-ads-001
severity: high
impact: spend_waste_risk
owner: media-ops
next_check_at: 2026-03-03T10:00:00Z

Health Rule Example

rule: delivery_drop
condition: impressions_down_pct > 40
action: alert_and_pause_review

Examples

Example 1: Pixel breakage before launch

Input:

• Purchase event missing
• Campaign start in 24h

Output focus:

• severity ranking
• immediate mitigation
• relaunch checklist

Example 2: Account health audit

Input:

• Multiple platform accounts
• Unknown policy or billing status

Output focus:

• readiness scorecard
• blocking risks
• owner-level actions

Example 3: Live anomaly handling

Input:

• Spend spikes with no conversion lift
• Multiple campaigns impacted

Output focus:

• anomaly triage path
• containment actions
• incident ticket payload

Quality Checklist

• Required sections are complete and non-empty
• Trigger keywords include at least 3 registry terms
• Input and output contracts are operationally testable
• Workflow and decision rules are capability-specific
• Platform references are explicit and concrete
• At least 3 practical examples are included