html-ppt-zhangzara-playful

A retail sales-floor training on consultative selling — the flow, the role-plays, and the daily habit that lifts conversion. Built as a decision-grade professional training deck for store associates, floor managers.

Quality

55%

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 ./design-templates/html-ppt-zhangzara-playful/SKILL.md

Quality

Content

60%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.

The body is concise and well-sequenced with a clear output contract, but it references bundle files (example.html, template.json, LICENSE, assets/) that are not present, undermining both actionability and progressive disclosure. Adding an explicit verify step would round out the workflow.

Suggestions

Bundle the referenced files (example.html, template.json, LICENSE, assets/deck-stage.js) so the workflow's 'Clone example.html' step is actually executable.

Add a final workflow step that verifies the deck renders correctly (e.g., open in a browser, confirm navigation and page-number labels are intact).

If example.html is intentionally fetched from upstream at runtime, state that explicitly and give the clone command rather than implying a local bundled file.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it never explains what HTML or slides are — and the 'Best for'/'Avoid for' prose is useful template-selection guidance rather than padding. Not a 5 because a few descriptive lines (the blockquote, 'At a glance') could be trimmed.	4 / 5
Actionability	The workflow gives concrete steps ('Clone example.html', 'Replace placeholder content', 'Preserve the design system') and an output-contract skeleton, but the primary referenced file example.html is not present in the bundle, so the guidance cannot actually be executed. Below 4 because a key executable target is missing.	3 / 5
Workflow Clarity	Six numbered steps form a clear, well-sequenced process with an explicit output contract; the only gap is the absence of a verify/render checkpoint. Not capped at 3 because the task is non-destructive, and not 5 because no explicit validation step is given.	4 / 5
Progressive Disclosure	The SKILL.md is well-sectioned and clearly signals one-level references (example.html, LICENSE, template.json, assets/deck-stage.js), but none of those bundle files exist in the skill directory, so the disclosure targets are broken. Scored against the actual (empty) bundle structure per the rubric guidance.	2 / 5
	Total	13 / 20 Passed

Description

50%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.

The description conveys the deck's topic and audience clearly but omits any explicit 'Use when' trigger guidance, capping completeness and trigger quality at mid-range. It also differentiates by topic rather than capability, leaving moderate overlap risk with sibling training-deck skills.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases (e.g., 'Use when creating a retail sales-floor training deck, a consultative-selling workshop, or onboarding slides for store associates').

Mention the actual capability — producing an HTML slide deck in the Playful template — so the description distinguishes this skill from sibling training decks.

Include common synonyms and cues users might say ('retail training', 'selling skills', 'HTML slides') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('retail sales-floor training on consultative selling') and a few concrete content elements ('the flow, the role-plays, and the daily habit that lifts conversion'), but does not enumerate the concrete actions the skill performs. Fits the 'names domain and 1-2 concrete actions, not comprehensive' anchor; not a 4 because no list of specific capabilities is given.	3 / 5
Completeness	Clearly states what the deck is ('A retail sales-floor training on consultative selling... Built as a decision-grade professional training deck'), but offers no explicit 'when to use' trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 3.	3 / 5
Trigger Term Quality	Contains relevant domain terms ('sales-floor training', 'consultative selling', 'training deck', 'store associates') but embeds them in prose with no 'Use when...' clause and no synonyms or file cues users would naturally say. Above 2 because several domain keywords are present; below 4 because common variations are missing.	3 / 5
Distinctiveness Conflict Risk	The retail consultative-selling topic is specific, but the description differentiates only by topic, not by capability, leaving overlap with sibling professional-training deck skills. Not a 4 because the actual capability (HTML deck generation in the Playful template) is not surfaced in the description.	3 / 5
	Total	12 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: nexu-io/open-design
Path: design-templates/html-ppt-zhangzara-playful/SKILL.md
Commit: f580271

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.