CtrlK
BlogDocsLog inGet started
Tessl Logo

openai-ads-conversions-setup

Guide Codex through instrumenting or extending repositories with OpenAI Ads Measurement Pixel and optional Conversions API (CAPI). Use when adding Ads conversion tracking, browser pixel events, server-side conversion events, event_id deduplication, CAPI secret placeholders, incremental conversion coverage, or validating Ads conversion setup. Applies to local repositories and PR review contexts; prioritize safe, reviewable diffs and never place API keys or secrets in source code or client bundles.

75

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with a clear, validated workflow and good progressive disclosure into real reference files. Its main weakness is conciseness: several safety rules are repeated across sections, inflating the token budget without adding new guidance.

Suggestions

Consolidate the source_url, oppref, and secret-exposure rules into their canonical section (CAPI Rules / Pixel Rules) and reference them from the Workflow and Verification sections instead of restating them, to reduce repetition.

Consider folding the long 'High-priority failure cases' list into references/verification-checklist.md so the main body stays a lean overview while preserving the checklist for verification.

Tighten step 2 of the Workflow, which bundles many conditionals into single bullets; splitting the source_url/oppref planning sub-bullets would let some be moved to the reference without loss of clarity.

DimensionReasoningScore

Conciseness

The body is dense and avoids explaining basics Claude knows, but rules around source_url sanitization, oppref handling, dedupe, and secret exposure are restated across Workflow, Pixel Rules, CAPI Rules, and the Verification failure cases, adding token cost without new information.

2 / 3

Actionability

Concrete env var names (e.g. NEXT_PUBLIC_OPENAI_ADS_PIXEL_ID), executable verification commands with flags, specific SDK calls (oaiq("init", {pixelId})), and exact field/event names make the guidance copy-paste ready.

3 / 3

Workflow Clarity

A clear five-step sequence (inspect, confirm plan, implement, verify, report) is paired with explicit validation commands, a 'When To Stop And Ask' gate, and a reporting step that captures blockers and residual risk.

3 / 3

Progressive Disclosure

The body is an overview with well-signaled one-level-deep references (measurement-pixel.md, conversions-api.md, framework-patterns.md, verification-checklist.md, report-schema.md), all of which exist, keeping the main file navigable.

3 / 3

Total

11

/

12

Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, action-oriented, and includes an explicit 'Use when' trigger clause covering both what and when. It occupies a clear niche with low conflict risk against other skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions such as 'instrumenting or extending repositories with OpenAI Ads Measurement Pixel and optional Conversions API (CAPI)', 'event_id deduplication', and 'CAPI secret placeholders' rather than vague language.

3 / 3

Completeness

Explicitly answers both what ('Guide Codex through instrumenting or extending repositories...') and when via a clear 'Use when adding Ads conversion tracking...' clause.

3 / 3

Trigger Term Quality

Natural user-facing terms like 'Ads conversion tracking', 'browser pixel events', 'server-side conversion events', and 'validating Ads conversion setup' map well to what a user would actually say.

3 / 3

Distinctiveness Conflict Risk

The 'OpenAI Ads' niche is specific and unlikely to trigger for unrelated skills; the scoped PR-review/local-repo context further narrows the trigger surface.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openai/plugins
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.