CtrlK
BlogDocsLog inGet started
Tessl Logo

google-ads

Query, audit, and optimize Google Ads campaigns. Supports two modes: (1) API mode for bulk operations with the google-ads Python SDK, (2) attached-browser mode for users without API access. Use when asked to check ad performance, pause campaigns or keywords, find wasted spend, audit conversion tracking, or optimize Google Ads accounts.

69

Quality

86%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

A well-structured, highly actionable skill with concrete code and a strong safety/change-control framework, undermined only by mild verbosity and a missing inline validation checkpoint in the browser pause workflow. Progressive disclosure and actionability are excellent.

Suggestions

Add an explicit 'snapshot/verify selection before confirming Pause' checkpoint inside the Browser Mode pause workflow so the batch destructive action has an inline validation step rather than relying only on the later safety section.

Remove the empty '## Troubleshooting' heading (it precedes '## Safety Boundaries' with no content) and either merge troubleshooting into the relevant mode sections or populate it.

Trim redundancy between the Audit Checklist table's filter syntax and the Common Workflows steps, and consolidate the API setup-check bash snippets into a single concise block.

DimensionReasoningScore

Conciseness

Mostly efficient with executable snippets, but setup-check commands are partly redundant, the audit table restates filter syntax already shown in workflows, and an empty '## Troubleshooting' heading adds clutter — efficient but could be tightened.

2 / 3

Actionability

Provides fully executable GAQL queries and mutate operations in Python plus specific browser navigation URLs and click paths (e.g. 'Add filter → Conversions → Less than → 1'), copy-paste ready.

3 / 3

Workflow Clarity

Workflows are sequenced and the safety boundaries / change-control addendum supply confirmation checkpoints for mutating actions, but the inline browser pause workflow lacks an explicit verify-before-confirm checkpoint for the batch/destructive pause operation, which caps workflow clarity at 2.

2 / 3

Progressive Disclosure

SKILL.md serves as a clear overview with two well-signaled, one-level-deep references ('Load browser-workflows.md', 'Load api-setup.md'), both of which exist as real bundle files, splitting detail appropriately.

3 / 3

Total

10

/

12

Passed

Description

100%

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, third-person description that pairs concrete capabilities with explicit 'Use when' triggers and a clear two-mode design. It hits all four anchors at the top of the scale with no fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Query, audit, and optimize', 'bulk operations', 'pause campaigns or keywords', 'find wasted spend', 'audit conversion tracking' — matching the score-3 anchor of multiple specific concrete actions.

3 / 3

Completeness

Explicitly answers what ('Query, audit, and optimize Google Ads campaigns' plus two named modes) and when ('Use when asked to check ad performance...'), mirroring the score-3 example with an explicit 'Use when' clause.

3 / 3

Trigger Term Quality

Covers natural user phrasing — 'check ad performance', 'pause campaigns or keywords', 'find wasted spend', 'conversion tracking', 'optimize Google Ads accounts' — the kind of terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

Narrow Google Ads niche with distinct triggers and two explicit access modes; unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
jdrhyne/agent-skills
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.