Install
$ agentstack add skill-adform-agentic-skills-adform-inventory-availability-forecast ✓ 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
Adform inventory availability forecast
Projects forward supply two ways: across an advertiser's PMP deals using recent traffic as a baseline, and across open-auction inventory filtered by geo and format. Read-only.
Connection & tooling
Runs on the Adform GraphQL MCP. Use graphql_execute to run queries. Use graphql_search to look up field names. Keep calls sequential (~1–2s apart).
Deal availability (PMP)
Step 1 — Find the advertiser's deals
{
buyerDealListItems(
pagination: { offset: 0, limit: 50 }
) {
buyerDeals {
id dealId name type price currencyCode status startDate endDate
inventorySource { id name }
healthIndications { status }
}
totalCount
}
}
Step 2 — Past traffic baseline per deal
{
inventoryMarketplaceDealPastTraffic(
deals: [{ inventoryId: 42, dealId: "12345" }]
) {
dealId
trafficCounts { cookies requests }
}
}
Project forward: use mean daily requests from the last 30 days as a baseline for the forecast horizon. State this is an extrapolation from observed supply.
Open-auction sizing
Step 1 — Browse available inventory sources
{
inventoryMarketplaceListItems(
pagination: { offset: 0, limit: 100 }
) {
inventorySources { id name adExchange { id name } channels environments }
hasMoreItems totalCount
}
}
Step 2 — Past traffic for identified inventory sources
{
inventoryMarketplaceInventoryPastTraffic(inventoryIds: [42, 55]) {
inventoryId
trafficCounts { cookies requests }
}
}
Resolve geo IDs for filtering using adform-geo-reference.
Presenting
Deals: table with deal name, status, floor price, baseline daily requests, and projected 30-day available impressions. Open auction: table by inventory source with addressable cookies and requests. Lead with the headline total and the largest sources. State that projections extrapolate recent supply and are not guarantees.
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.