agentsclimarketplace

Ops ticket intake and triage

Skill scumunna/programmatic-skills/skills/ops-ticket-intake-and-triage

Agent skills for programmatic trading, analytics, and account operations. DV360 first, multi-DSP and multi-runtime (Claude Code and Codex).

Install
npx -y skills add scumunna/programmatic-skills --skill ops-ticket-intake-and-triage

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Turn messy campaign requests into actionable programmatic operations tickets with required fields, severity, SLA, owner, evidence, acceptance criteria, and rejection rules for unclear asks. Use for Jira, Asana, Monday, spreadsheet queues, launch requests, trafficking requests, reporting asks, and client service tickets.

SKILL.md

5.8 KB, ~1.3k tokens by cl100k_base, as published. Nobody here has run it

Ops ticket intake and triage

A programmatic desk fails when requests enter as vague sentences: "launch this", "fix spend", "update creative", "pull a report". This skill converts requests into operational tickets that can be accepted, rejected, prioritized, assigned, and audited.

The assistant helps operators enforce intake quality. It does not approve work, change live campaigns, or bypass the desk's priority model.

When to use this skill

  • A user asks to triage programmatic tickets or clean up a queue.
  • A request is missing platform, campaign, budget, flight, creative, targeting, tags, or owner.
  • A launch, trafficking, reporting, creative, taxonomy, billing, or optimization ask needs an SLA and acceptance criteria.
  • The team wants a standard ticket template across Jira, Asana, Monday, Sheets, or email.

Required fields

Reject or return the ticket if a required field is missing and cannot be inferred from an attached source of truth.

FieldWhy it matters
Request typeLaunch, edit, optimization, reporting, creative, tag, access, support, billing
Advertiser and platformPrevents cross-account mistakes
Campaign, order, line item, ad group, or placement IDsNames alone are not enough
Requested changeThe exact thing being asked
Business reasonWhy this matters and what outcome is expected
Deadline and time zonePrevents false urgency and missed launches
Owner and approverMakes the next decision explicit
Evidence or sourceBrief, IO, platform export, screenshot, report, spec, or client email
Acceptance criteriaWhat must be true for the ticket to be done
Risk flagsSpend, brand safety, regulated category, consent, billing, legal, client-visible

Severity model

SeverityDefinitionDefault response
Sev 1Live spend, brand, or legal risk active nowAcknowledge immediately, contain first
Sev 2Material delivery, launch, tracking, or client deadline riskSame business day owner and plan
Sev 3Routine edit, QA, report, creative, or access requestStandard SLA
Sev 4Nice-to-have cleanup, analysis, or future planningBacklog or scheduled

Severity is based on risk and time sensitivity, not on who asked loudest.

Core process

  1. Normalize the ask. Rewrite the request into a single clear action: "Add Creative A to Line Items 123, 124, and 125 in DV360 for Advertiser X by July 7, 2026, pending creative approval." If the action cannot be written, the ticket is not ready.
  2. Validate required fields. Check the ticket against the required field table. Do not accept a live-change request without platform, advertiser, IDs, deadline, source, and acceptance criteria.
  3. Assign category and severity. Category routes the ticket to the right owner. Severity sets the response clock. A launch blocker due today is not a routine ticket.
  4. Check approval requirements. Use approval-and-escalation-governance for budget, bidding, brand-safety, targeting expansion, access, or client-facing changes.
  5. Attach the evidence package. Store the source artifact that proves the request is real: client email, signed IO, media plan, tag sheet, export, screenshot, or report.
  6. Set acceptance criteria. Done is not "updated". Done is "line items 123 to 125 have the approved creative assigned, creative preview passes, click URL works, and the launch QA row is updated."
  7. Route or return. Route accepted tickets to the owner. Return unclear tickets with the exact missing fields, not a vague "need more info".

Routing rules

Ticket typePrimary ownerSupporting skill
Launch or preflightprogrammatic-ops-leadcross-platform-launch-qa
Bulk editaccount-operations-specialistbulk-change-governance-and-rollback
Creative add or swapad-ops-traffickercreative-review-and-approval-queue
Conversion or tag issuemeasurement-and-tagging-engineertag-and-pixel-governance
Delivery or pacing issueoptimization-specialistPlatform troubleshooting skill
Support caseprogrammatic-ops-leadplatform-support-escalation
Access or permissionaccount-operations-specialistplatform-access-and-permissions-governance
Billing or closemeasurement-analystprogrammatic-month-end-close

Intake template

Ticket title:
Request type:
Advertiser:
Platform:
Campaign/order/line/ad group IDs:
Requested change:
Business reason:
Deadline and time zone:
Owner:
Approver:
Source evidence:
Risk flags:
Acceptance criteria:

Return-to-requester message

I cannot accept this ticket yet. Please add:
- Platform and advertiser
- Exact entity IDs
- Requested change
- Deadline with time zone
- Source evidence
- Acceptance criteria

Once those are attached, I can triage severity, owner, approval path, and next action.

Common pitfalls

  • Accepting names instead of IDs. Names can duplicate and drift.
  • Letting "urgent" replace severity. Urgency must tie to spend, launch, brand, legal, or client deadline risk.
  • Finishing tickets without evidence. If the desk cannot prove the state changed, the ticket is not closed.
  • Hiding approvals inside comments. Approval needs an explicit approver, timestamp, and scope.

Related artifacts

  • templates/ops/ticket-intake-template.md
  • programmatic-ops-control-center
  • approval-and-escalation-governance
  • change-management-and-incident-response

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most debug triage skills give in ~1.3k tokens

Counted across 839 of the 1,149 authors here whose files we hold, read 2026-08-07

  • Investigate root cause before proposing any fixin 102 of 839, across 67 files
  • Read error messages completelyin 89 of 839, across 49 files
  • Create a failing test case before fixingin 84 of 839, across 46 files
  • Reproduce the issue consistentlyin 82 of 839, across 41 files
  • Change one variable at a timein 82 of 839, across 42 files
  • Check recent changesin 74 of 839, across 36 files
  • Write the regression test before fixingin 74 of 839, across 40 files
  • Fix the root cause not the symptomin 60 of 839, across 45 files
  • Implement a single fix at a timein 59 of 839, across 20 files
  • Trace data flow backward to the sourcein 50 of 839, across 20 files
  • Remove all debug instrumentationin 49 of 839, across 13 files
  • Form a single hypothesisin 48 of 839, across 18 files

Said here and by no other author read

  • Rewrite the request into a single clear action
  • Reject tickets missing required fields
  • Assign category and severity based on risk
  • Check approval requirements for live changes
  • Attach evidence proving the request is real
  • Set explicit acceptance criteria

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,984. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.