ads-monitor

Monitor paid-ad account pacing, delivery, performance, creative fatigue, tracking, policy, and data quality across supported platforms. Use for daily or weekly checks, anomaly review, budget pacing, post-launch verification, or campaign monitoring.

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/ads-monitor/SKILL.md

Quality

Content

75%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.

A lean, well-sequenced monitoring procedure with an explicit validation checkpoint and useful guardrails. Its main weakness is actionability: it tells Claude what to check but not how to mechanically load snapshots or where the data comes from.

Suggestions

Add a concrete example of how to load and align two normalized snapshots (data source, file format, and the compatibility fields to check) so the procedure is executable rather than purely procedural.

Specify an explicit feedback loop after step 2's validation — e.g. 'If freshness or finalization checks fail, flag the gap and stop before comparing periods.'

Show a small worked input/output example of the step-5 return (observations, confidence, likely causes, decision thresholds) to make the expected deliverable unambiguous.

Dimension	Reasoning	Score
Conciseness	Roughly 20 lines with no padding and no explanation of concepts Claude already knows; every step adds specific guidance (finalization windows, separating learning/seasonality, decision thresholds), so every token earns its place per anchor 5.	5 / 5
Actionability	The numbered steps give concrete procedural direction and decision rules ("Do not alert on percentage changes with trivial denominators"), but as an instruction-only skill it omits key execution details — no data source, tool, snapshot format, or worked input/output example — landing at the incomplete-but-concrete anchor 3 rather than 4.	3 / 5
Workflow Clarity	A clear six-step sequence with an explicit validation checkpoint (step 2 "Validate data freshness and finalization windows before comparing periods") and a non-mutation guard, but it lacks an explicit if-invalid-then-fix feedback loop, so it is below the anchor 5 with full error-recovery loops.	4 / 5
Progressive Disclosure	Under 50 lines with no external references needed and organized as a clean numbered procedure plus a guardrail paragraph; it falls short of anchor 5 only because there is a single heading rather than distinct navigable sections.	4 / 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 that clearly states the monitoring domain and gives explicit use-when trigger phrases. It is comprehensive on completeness but slightly less distinctive and slightly less varied in action verbs than the top anchors.

Dimension	Reasoning	Score
Specificity	Names multiple concrete monitored domains ("pacing, delivery, performance, creative fatigue, tracking, policy, and data quality") but relies on a single action verb "Monitor" applied broadly rather than several distinct actions, so it sits below the comprehensive multi-action anchor 5.	4 / 5
Completeness	Explicitly answers both what ("Monitor paid-ad account pacing, delivery...") and when ("Use for daily or weekly checks, anomaly review...") with concrete trigger phrases, matching the anchor 5 example structure.	5 / 5
Trigger Term Quality	"daily or weekly checks, anomaly review, budget pacing, post-launch verification, or campaign monitoring" are natural phrases a paid-media user would say, but coverage lacks common synonyms (e.g. ad spend, ROAS, PPC), keeping it just below the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	The paid-ad account framing carves a clear niche with distinct triggers, but generic terms like "anomaly review" and "campaign monitoring" leave minor overlap risk with general analytics skills, so it is not the minimal-conflict anchor 5.	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: AgriciDaniel/claude-ads
Path: skills/ads-monitor/SKILL.md
Commit: ac21644

Reviewed: 1 day ago

Table of Contents

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.