Tessl • The management layer for AI agent skills

SkillPublic

performance-max-optimizer

Optimize Google Ads Performance Max campaigns including asset groups, audience signals, search term insights, and channel allocation. Use when managing PMax campaigns, analyzing asset performance, configuring audience signals, or optimizing product feeds.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%Weight 40%Scale 1-5

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

Highly actionable content with executable GAQL, specific thresholds, and well-sequenced workflows that mostly include monitoring checkpoints. Its weaknesses are the monolithic single-file structure with no progressive disclosure of reference data, a promotional footer that wastes context, and implicit rather than explicit feedback loops.

Suggestions

Split reference data into bundle files (e.g., references/asset-requirements.md, references/benchmarks.md, references/examples.md) and keep SKILL.md as a concise overview with clearly signaled one-level-deep links.

Remove the promotional 'About this skill' footer and the intro paragraph that duplicates the frontmatter description — neither earns its token cost.

Add explicit feedback loops to the workflows (e.g., after applying negatives: re-check in 7-14 days, and if impression share drops significantly, remove over-broad negatives) and verification steps to Workflows 4 and 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly dense, high-signal tables, thresholds, and GAQL queries that assume Claude's competence, but the opening paragraph duplicates the frontmatter description and the ~10-line promotional 'About this skill' footer (Synter links with UTM parameters) is wasted context that should be trimmed.	4 / 5
Actionability	Copy-paste-ready GAQL queries, concrete decision thresholds ('Conversion rate < 50% of campaign average', 'CPA > 2× campaign target'), exact UI navigation paths ('Admin → Account settings → Negative keyword lists'), and three worked examples with real numbers cover the common cases fully.	5 / 5
Workflow Clarity	Five workflows are clearly numbered and sequenced with monitoring checkpoints ('wait 7-14 days and compare…', 'After 30 days, check Insights tab', 'wait 2 weeks between changes'), but feedback loops are implicit rather than structured validate-fix-retry, and Workflows 4 and 5 lack verification steps.	4 / 5
Progressive Disclosure	The skill is a single 360-line monolithic file with no references/, scripts/, or assets/ directories; benchmark tables, asset-requirement reference data, and extended examples are all inlined where separate one-level-deep reference files belong. Internal headers keep it navigable, so it sits above the minimal-structure anchor but below good separation.	3 / 5
	Total	16 / 20 Passed

Description

83%Weight 40%Scale 1-5

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

A strong description with explicit what-and-when structure, third-person voice, specific named components, and natural trigger terms including the PMax/Performance Max synonym pair. The only gaps are a single-verb action list and minor overlap with general Google Ads skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete components ('asset groups, audience signals, search term insights, and channel allocation') and multiple action verbs ('managing… analyzing… configuring… optimizing'), but the 'what' leans on a single verb with an object list rather than multiple distinct concrete actions, so it falls just below the comprehensive anchor.	4 / 5
Completeness	Explicitly answers both 'what' ('Optimize Google Ads Performance Max campaigns including…') and 'when' with a concrete 'Use when…' clause listing four distinct triggers, matching the anchor-5 example structure; not 4 because the when-clause is fully explicit rather than vague.	5 / 5
Trigger Term Quality	Good natural-term coverage — 'PMax campaigns', 'asset performance', 'audience signals', 'product feeds', plus the synonym pair 'Performance Max'/'PMax' — but a few natural variations users would say (e.g., 'Shopping', 'listing groups', 'ad strength') are missing.	4 / 5
Distinctiveness Conflict Risk	Clear PMax niche with distinct, specific triggers; slight overlap risk remains with a broader Google Ads management skill that would also fire on 'managing PMax campaigns', keeping it below the minimal-conflict anchor.	4 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Synter-Media-AI/free-skills
Path: skills/performance-max-optimizer/SKILL.md
Revision: 3df48f1

Reviewed: 1 day ago

Discovery Implementation Validation

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.

performance-max-optimizer

Table of Contents

Is this your skill?