CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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.

An exceptionally lean, guardrail-rich workflow with explicit validation ordering and no bundle sprawl. The main weakness is actionability: the body says what to verify and preserve but never how — no template paths, commands, or check specifics — leaving the execution details to be improvised.

Suggestions

Name the concrete rendering mechanism: where the deterministic templates live (e.g., templates/report.md.j2) and the command or procedure that turns the canonical JSON into each of Markdown, HTML, and PDF.

Add an error-recovery loop after step 5: what to do when structural or visual/layout checks fail (fix and re-run checks before writing), which would raise both actionability and workflow clarity.

Specify how to verify the prerequisites in step 2, e.g., which manifest fields to check for run completeness and evidence coverage, or a concrete command that validates the input bundle.

DimensionReasoningScore

Conciseness

The 22-line body is pure directive with zero padding: no concept explanations, no library recommendations, no filler — every line instructs ("Accept a validated versioned report bundle, never loose worker prose"; "Write atomically inside the run directory and update its manifest"). This matches anchor 5: lean, assumes Claude's competence, every token earning its place.

5 / 5

Actionability

The steps name concrete specifics ("run completeness, evidence coverage, privacy class", "findings, confidence, evidence references, contradictions, missing inputs, actions, owners, and measurement windows"), but no file paths, template locations, script names, commands, or examples of what "structural checks" and "visual/layout checks" entail. That matches anchor 3 (some concrete guidance but missing key details) rather than anchor 4, which requires concrete commands with only minor gaps.

3 / 5

Workflow Clarity

A clear six-step sequence (accept → confirm inputs → render → preserve data → run structural then visual checks → write atomically and update manifest) with an explicit validation step ("Run structural checks, then visual/layout checks for HTML and PDF"). It is not anchor 5 because there is no error-recovery feedback loop (what to do when a check fails) and no checklist; it exceeds anchor 3 because validation checkpoints are explicit, not implicit.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent) and the body references none, so there are no dangling or nested references to penalize. Per the rubric's simple-skill exception (under 50 lines, no external references needed), the lean, well-organized structure — heading, numbered workflow, separate guardrail paragraphs — earns anchor 5.

5 / 5

Total

17

/

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: third-person voice, explicit what-and-when structure, and multiple natural trigger phrases tied to a clear niche. Coverage of synonyms and file extensions could be slightly broader, but nothing rises to a material weakness.

DimensionReasoningScore

Specificity

"Render Markdown, HTML, or PDF paid-advertising reports" names the domain, output formats, and input artifact ("a validated Claude Ads JSON run bundle"), and "exporting prior audit and plan results" adds a second concrete action. It falls short of anchor 5 because it does not comprehensively enumerate capabilities (e.g., validation, branding, atomic writes) beyond rendering.

4 / 5

Completeness

The first sentence explicitly states what the skill does ("Render Markdown, HTML, or PDF paid-advertising reports from a validated Claude Ads JSON run bundle") and the second gives an explicit "Use for..." clause with multiple concrete trigger phrases. This matches anchor 5: both what and when are clearly and explicitly answered; it is not anchor 4 because the 'when' clause is already explicit and specific.

5 / 5

Trigger Term Quality

"Use for ads report, client report, audit PDF, executive audience reporting, or exporting prior audit and plan results" gives good natural-phrase coverage ("ads report", "audit PDF", "client report"). It misses common synonyms and file extensions (".pdf", "paid media report", "PDF report"), so it fits anchor 4 rather than anchor 5's comprehensive coverage.

4 / 5

Distinctiveness Conflict Risk

The niche (rendering paid-advertising reports from a validated Claude Ads run bundle) is well defined with distinct triggers like "ads report" and "executive audience reporting". Minor overlap risk remains with generic PDF/report/document skills via "client report" and "audit PDF", so anchor 4 rather than anchor 5.

4 / 5

Total

17

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

AgriciDaniel/claude-ads

Path

skills/ads-report/SKILL.md

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.