ads-report

Render Markdown, HTML, or PDF paid-advertising reports from a validated Claude Ads JSON run bundle. Use for ads report, client report, audit PDF, executive audience reporting, or exporting prior audit and plan results.

Quality

80%

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-report/SKILL.md

Quality

Content

72%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 concise, well-structured guardrails checklist for report rendering that assumes Claude's competence and stays lean. It is weakest on actionability and workflow clarity because it specifies what to check and preserve without executable methods or a validate-fix-retry feedback loop.

Suggestions

Add concrete execution detail to steps 3 and 5: name the deterministic templates or tooling used to render, and specify which structural/visual checks to run (e.g., link integrity, layout overflow) so the guidance is executable rather than descriptive.

Add a feedback loop after step 5: if structural or visual/layout checks fail, fix the template/data and re-run checks before writing, to satisfy the batch-operation validation requirement and lift workflow clarity above 3.

Optionally point to where canonical data and templates live (e.g., a path or manifest field) so step 3's "same canonical data and deterministic templates" is actionable rather than abstract.

Dimension	Reasoning	Score
Conciseness	The ~20-line body is lean and directive with no padding or explanation of concepts Claude already knows; every line (numbered steps and the constraints paragraph) earns its place.	5 / 5
Actionability	Steps enumerate concrete items to confirm and preserve (privacy class, evidence references, contradictions, owners, measurement windows), but "Run structural checks, then visual/layout checks" and "Render all formats from... deterministic templates" give no executable method, commands, or template names, leaving key details missing.	3 / 5
Workflow Clarity	A clear six-step sequence with an explicit validation checkpoint (step 5: structural then visual/layout checks), but this batch render operation lacks a feedback loop (what to do when checks fail), which caps workflow clarity at 3 per the batch-operation guideline.	3 / 5
Progressive Disclosure	Under 50 lines, single-purpose, with no bundle files and no need for external references; the well-organized numbered list plus separated constraints section satisfies the simple-skill progressive-disclosure exception.	5 / 5
	Total	16 / 20 Passed

Description

87%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, third-person description that clearly communicates both capability and trigger context with concrete, natural keywords. Minor specificity and synonym-coverage gaps keep it just below perfect on two dimensions.

Dimension	Reasoning	Score
Specificity	"Render Markdown, HTML, or PDF paid-advertising reports from a validated Claude Ads JSON run bundle" names several concrete output formats and a specific source bundle, but the single verb "render" leaves minor coverage gaps versus a fully comprehensive action list.	4 / 5
Completeness	It explicitly states both what ("Render Markdown, HTML, or PDF paid-advertising reports from a validated Claude Ads JSON run bundle") and when ("Use for ads report, client report, audit PDF, executive audience reporting...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	"Use for ads report, client report, audit PDF, executive audience reporting, or exporting prior audit and plan results" covers good natural keywords a user would say, though a few common synonyms (e.g., marketing/PPC report) are missing.	4 / 5
Distinctiveness Conflict Risk	The paid-advertising/Claude Ads report niche with distinct triggers (ads report, audit PDF, executive audience reporting) is clearly distinguishable from other skills with minimal conflict risk.	5 / 5
	Total	18 / 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-report/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.