agentleFS
scumunnascumunna/programmatic-skills/skills/creative-review-and-approval-queue/SKILL.md

creative-review-and-approval-queue

Skill1 starsChanged 5 months agoMITView on GitHub

Manage creative intake, spec QA, legal or brand approval, platform review, trafficking readiness, rejection handling, swaps, expirations, and evidence for programmatic campaigns. Use when creative assets, VAST tags, HTML5, native, CTV, audio, DOOH, landing pages, click URLs, or approval statuses block launch or in-flight delivery.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use platform-specific creative skills for exact specs.

    line 12
  2. Distinctive:

    Run spec QA: Check file type, dimensions, duration, bitrate, audio, weight, safe zones, click URL, landing page, macros, VAST or tag …

    line 58
  3. Very specific:

    Verify live state: After launch, confirm impressions, click URL, tag firing, creative preview, and reporting rows.

    line 67
  4. Distinctive:

    Manage swaps and expiry: When assets fatigue, expire, reject, or need a legal update, create a swap ticket and run it through the same …

    line 69
  5. Distinctive:

    Do not describe a rejection as "platform issue" unless support is actually needed.

    line 90
  6. Distinctive:

    Never swap creative without checking reporting and creative code continuity.

    line 98
  7. Distinctive:

    Do not run unapproved claims while waiting on legal.

    line 99

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Creative review and approval queue

Creative is often the launch blocker that looks small until the day before go-live. This skill gives operators a queue for asset intake, spec QA, platform approval, trafficking readiness, rejections, and in-flight swaps across programmatic platforms.

Use platform-specific creative skills for exact specs. Use this skill to run the queue and make sure each asset has a state, owner, evidence, and next action.

When to use this skill

  • A campaign needs creative intake, asset QA, or approval tracking.
  • Creative review, rejection, spec failure, click URL issue, or VAST issue blocks launch.
  • Assets need to be swapped, retired, refreshed, or mapped to line items.
  • Legal, brand, medical, financial, or regulated-category approval is required.
  • The user asks for a creative tracker or creative queue.

Queue states

StateMeaning
RequestedAsset needed but not received
ReceivedAsset received but not QA'd
Spec QAOperator checking dimensions, duration, weight, format, text, URL, tags
Brand/legal reviewInternal or client approval in progress
Platform reviewSubmitted to platform or publisher review
ApprovedCleared and ready to assign
RejectedRejected by spec, brand, legal, platform, publisher, or policy
TraffickedAssigned to the correct entities
Live verifiedServing, click, tags, and reporting verified
RetiredRemoved, expired, or replaced

Required fields

FieldRequirement
Asset ID or file nameStable identifier, not only a friendly title
Creative codeJoins to taxonomy and reporting
Format and sizeDisplay, HTML5, video, CTV, audio, native, DOOH, etc.
Platform and placementWhere the asset will run
Landing page and click URLFinal URL, tracker, UTM, and redirect path
Approval ownerBrand, legal, client, platform, publisher, or internal owner
Review statusOne of the queue states
Rejection reasonExact reason and screenshot or policy text where available
Assigned entitiesCampaign, line, ad group, placement, or creative shell IDs
Expiry or rotation ruleEnd date, refresh date, or replacement condition

Core process

  1. Intake against the plan. Confirm every asset requested in the media plan or trafficking sheet has arrived, has a creative code, and maps to a platform, line item, placement, or ad group.
  2. Run spec QA. Check file type, dimensions, duration, bitrate, audio, weight, safe zones, click URL, landing page, macros, VAST or tag response, SSL, and policy-sensitive claims.
  3. Check approval needs. Regulated categories, claims, endorsements, financial language, health language, alcohol, political, and client legal processes may require approval before platform submission.
  4. Submit and track platform review. Record platform review ID, submitted date, expected SLA, rejection reason, and appeal or resubmission path.
  5. Traffic only approved assets. Assign assets to the correct entities, confirm rotations, weights, dates, and companion assets, then hand to launch QA.
  6. Verify live state. After launch, confirm impressions, click URL, tag firing, creative preview, and reporting rows. Mark Live verified only with evidence.
  7. Manage swaps and expiry. When assets fatigue, expire, reject, or need a legal update, create a swap ticket and run it through the same queue.

Rejection handling

Creative rejection
Asset:
Platform:
Entity IDs:
Rejected by:
Reason:
Policy or spec cited:
Screenshot or evidence:
Impact:
Owner:
Fix path:
Resubmission time:
Launch or delivery risk:

Do not describe a rejection as "platform issue" unless support is actually needed. Many rejections are local spec, landing-page, claim, or targeting-policy issues.

Decision rules

  • Approved does not mean trafficked. Trafficked does not mean live verified.
  • A click URL that redirects incorrectly is a launch blocker.
  • A video asset that passes file spec but has an invalid VAST response is still blocked.
  • Never swap creative without checking reporting and creative code continuity.
  • Do not run unapproved claims while waiting on legal. Hold launch or substitute approved copy.

Common pitfalls

  • Tracking creative in email threads instead of a queue with states.
  • Losing creative-code mapping during swaps, which breaks asset-level reads.
  • Treating platform approval as brand approval.
  • Forgetting companions, end cards, captions, click trackers, and landing-page redirects.
  • Letting expired creative keep serving because it was approved earlier.

Related artifacts

  • templates/ops/creative-review-tracker.csv
  • direct-response-creative-testing
  • dv360-creative-trafficking
  • dv360-video-creative-specs
  • ttd-creative-and-formats
  • stackadapt-creative-and-formats
  • cross-platform-launch-qa

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.