Install
$ agentstack add skill-adform-agentic-skills-adform-campaign-performance ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Campaign Delivery Overview
Portfolio-level campaign delivery metrics including spend, pacing, projected delivery, and budget deviation across all campaigns for an advertiser.
Metrics availability
Delivery indications (from campaignDeliveryIndications):
- Current spend and budget utilization
- Pacing status and delivery projections
- Budget deviation and flight progress
- Delivery schedule status
Performance metrics (from mcpStats):
- Impressions, clicks, CTR, eCPM, cost
- Viewability rate (IAB), viewable impressions
- Video completion rate, video starts
- Conversions, eCPA, sales
For a portfolio-level delivery sweep use the delivery indications pattern below. For performance metrics add an mcpStats call scoped to the same advertiser and date range — see adform-stats-performance for the full query reference.
Connection & tooling
Runs on the Adform GraphQL MCP. Use graphql_execute to run queries. Use graphql_search to look up field names; use graphql_introspect for complex nested types. Keep calls sequential (~1–2s apart).
The pattern
- Resolve the advertiser:
advertisers(search: "name")→ get advertiser ID - List campaigns:
campaigns(advertisers: "$advertiserId")→ get all campaign IDs and names - Pull delivery per campaign:
campaignDeliveryIndications(id:)— one call per campaign - Assemble, sort, and present client-side
Step 1 — List campaigns
{
campaigns(
advertisers: "2247935"
limit: 50
offset: 0
) {
campaigns { id name status startDate endDate budget currency }
totalCount
}
}
Step 2 — Campaign delivery indications
Run once per campaign ID. Returns the active budget flight state.
{
campaignDeliveryIndications(id: "4221341") {
status
goalType
effectiveFlightTotalGoal
effectiveFlightCurrentDelivery
effectiveFlightProjectedDelivery
effectiveFlightRemainingDelivery
effectiveFlightDeviationPercentage
effectiveFlightTotalCost
effectiveFlightDailyCost
effectiveBudgetFlightStartDate
effectiveBudgetFlightEndDate
}
}
Field reference
goalType:Money|Impressions|Clicks|Unlimitedstatus:Active|ScheduleGap|FinishedeffectiveFlightDeviationPercentage— negative = under-delivering; positive = over-deliveringeffectiveFlightTotalCost— monetary spend regardless of goalType
Step 3 — Daily trend (optional)
For a day-by-day spend view across multiple campaigns (max 30-day window):
{
campaignDailyDeliveryIndications(
ids: ["4221341", "4221349", "4221354"]
from: "2026-06-01"
until: "2026-06-11"
) {
id
deliveryDate
deliveryIndications {
effectiveFlightTotalCost
effectiveFlightDailyCost
effectiveFlightDeviationPercentage
status
}
}
}
Step 4 — Performance metrics per campaign (mcpStats)
Retrieve CTR, viewability, and cost efficiency metrics for the same campaign set and date range. Validated query:
{
mcpStats {
totalRowCount
totals
columns {
dimensions { date { date } campaign { id } }
metrics {
impressions
clicks
ctr
cost
ecpm
viewImpressionsIab
viewImpressionsPercentIAB
videoCompleteCount
videoCompletionRate
conversions
}
}
rows(
filter: {
date: { from: "2026-06-01", to: "2026-06-30" }
campaign: { ids: ["4221341"] }
}
paging: { offset: 0, limit: 100 }
sort: [{ column: 0, direction: asc }]
)
}
}
Merge the mcpStats result with delivery indications client-side using campaign ID as the join key.
Presenting
Table with one row per campaign: name, goal type, flight dates, budget goal, current spend, projected spend, deviation %, and status. Include an account totals row. Flag campaigns with deviation below −20% as under-delivering and above +10% as approaching overspend. Sort by deviation ascending to surface the largest gaps first.
For creative trafficking checks use adform-creative-discrepancy-audit. For detailed reporting use adform-reporting.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: adform
- Source: adform/agentic-skills
- License: MIT
- Homepage: https://site.adform.com
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.