CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pptx-visual-assets

Use when selecting and placing approved supporting icons, images, SVGs, diagrams, or infographics in an editable PPTX deck.

Quality

82%

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

86%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-organized instruction-only skill body: every rule is actionable, the workflow is sequenced with pre- and post-placement checkpoints, and detailed constraints are correctly deferred to a real, clearly signaled reference file. The only gaps are unstated specifics (manifest format, classification-tag origin) and a missing re-check loop after the final placement check.

Suggestions

Give a concrete example of the source-manifest entry (fields and where the manifest lives) and of the `content` vs `layout_design` classification, since both are referenced without definition or example.

Add an explicit validation feedback loop after step 4, e.g., 'If an asset covers readable text, reposition or omit it and re-check before proceeding.'

DimensionReasoningScore

Conciseness

Every line instructs ("Use visual assets to support a slide's message, never to flatten or replace editable content"; "never wrap a raster image in SVG and call it editable") with zero padding and no explanation of concepts Claude already knows — every token earns its place.

5 / 5

Actionability

Guidance is concrete and specific ("a final inch bbox, deliberate z-index, and `content` or `layout_design` classification"; "Confirm the local asset path, source, usage rights, and concise alt text"), but minor gaps remain: 'the source manifest' and the classification tags get no example or stated location. As an instruction-only skill this is mostly executable guidance with minor gaps, matching anchor 4.

4 / 5

Workflow Clarity

Four clearly sequenced steps with a pre-placement rights checkpoint (step 2) and a post-placement check (step 4: "check that no asset covers readable text"), plus a failure path in Rules ("omit the asset and report the gap"). Not anchor 5 because there is no explicit fix-and-re-check loop after step 4's check fails; not a destructive/batch operation so no cap applies.

4 / 5

Progressive Disclosure

The body is a lean overview and the only reference, `references/asset-guidance.md`, exists on disk, is one level deep, clearly signaled with its scope ("licensing, placement, and SVG constraints"), and appropriately splits out detailed constraints — matching the well-signaled one-level-deep-references anchor.

5 / 5

Total

18

/

20

Passed

Description

70%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 well-scoped, trigger-first description with concrete asset terminology and an explicit 'Use when' clause. Its main limitations are a thin action vocabulary (select/place only) and missing common synonyms like 'PowerPoint' or '.pptx'.

Suggestions

Add one or two more concrete actions to the description (e.g., 'verifying usage rights and recording provenance in the source manifest') so specificity moves beyond select/place.

Include common synonyms and the file extension users naturally say, e.g., 'PowerPoint (.pptx) decks, clip art, pictures, or photos'.

Split the description into a standalone what-clause followed by an explicit 'Use when...' clause so both capabilities and triggers are independently concrete.

DimensionReasoningScore

Specificity

"selecting and placing approved supporting icons, images, SVGs, diagrams, or infographics" names the domain and two concrete actions (select, place) with an enumerated asset taxonomy, but lists no further actions (rights clearance, manifesting, formatting), matching the '1-2 concrete actions, not comprehensive' anchor.

3 / 5

Completeness

Both are present — what ("selecting and placing approved supporting...") and when ("Use when...") — but the what is embedded inside the when-clause rather than stated as a standalone capability sentence, making it slightly less explicit than the anchor-5 dual concrete structure.

4 / 5

Trigger Term Quality

Natural terms like "icons, images, SVGs, diagrams, infographics, editable PPTX deck" give good coverage of what users would say, but common variants such as "PowerPoint", "pictures", "photos", and the ".pptx" extension are missing, so it falls short of the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

The editable-PPTX visual-asset niche with distinct asset-type triggers is mostly distinct, with only minor overlap risk against a general pptx-authoring skill that also touches images and diagrams.

4 / 5

Total

15

/

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

wshobson/agents

Path

plugins/pptx-deck-creation/skills/pptx-visual-assets/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.