CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

html-ppt-zhangzara-vellum

A humanities lecture: how Renaissance linear perspective reshaped early cartography — sources, argument, and evidence. Built as a decision-grade academic research deck for faculty, graduate seminar.

49

Quality

62%

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

Fix and improve this skill with Tessl

tessl review fix ./design-templates/html-ppt-zhangzara-vellum/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 an exemplar of concise, well-structured template guidance — a clear identity statement, selection criteria, sequenced workflow, and an exact output contract. Its weakness is bundle integrity rather than writing quality: every file it instructs Claude to clone or consult is missing from the shipped skill, which undercuts both actionability and reference navigation.

Suggestions

Ship the referenced files (`example.html`, `template.json`, `LICENSE`, and any `assets/` runtime) alongside SKILL.md, or remove/inline the references so no path is dangling.

Add a final verification step to the workflow, e.g. re-check that page-number labels and slide count are consistent after duplicating or dropping slides.

Confirm the navigation-runtime rule applies: if no `assets/deck-stage.js` ships, state that inline keyboard handlers (if any) must be preserved instead of referencing a nonexistent file.

DimensionReasoningScore

Conciseness

The body is lean and directive throughout — "Deep navy canvas with warm-yellow italic Cormorant serifs", a 6-step workflow, an exact output-contract snippet, and license attribution. Nothing explains concepts Claude already knows, and every section (Best for / Avoid for, At a glance) earns its tokens by informing template selection. Matches 'Lean and efficient; assumes Claude's competence; every token earns its place'.

5 / 5

Actionability

Guidance is written concretely ("Clone `example.html`", "duplicate an existing slide of the most appropriate layout", exact `<artifact identifier="zhangzara-vellum"...>` block), but the primary working file `example.html` — along with `template.json`, `LICENSE`, and the referenced `assets/deck-stage.js` runtime — does not exist in the bundle, so step 1 cannot be executed as shipped. Matches 'Some concrete guidance but incomplete... missing key details'. Not a 4 because the missing working file breaks the core action; not a 2 because the written steps and output contract are specific.

3 / 5

Workflow Clarity

The workflow is a clearly sequenced 6-step list (clone → replace placeholders → preserve the design system → adjust length → design missing layouts → keep the nav runtime) with concrete detail in each step. Matches 'Clear sequence with most checkpoints present; minor validation gaps' — there is no final validation step (e.g. verify the emitted HTML renders or that page-number labels are consistent after duplicating/dropping slides). Not a 5 for that missing checkpoint; the destructive/batch cap does not apply since this is deck generation, not a destructive operation.

4 / 5

Progressive Disclosure

The body itself is well organized with one-level-deep, clearly signaled references ("[`LICENSE`](./LICENSE)", "See `template.json`"), but every referenced path — `example.html`, `template.json`, `LICENSE`, `assets/deck-stage.js` — is absent from the actual bundle (no references/, scripts/, or assets/ directories exist). Scored against the real bundle structure per the guideline: broken references mean navigation fails. Matches 'Some structure but could be better organized; references present but not clearly signaled'. Not a 4 or 5 because referenced files do not ship; not a 2 because the body's own structure and signaling are clean.

3 / 5

Total

15

/

20

Passed

Description

40%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 reads as a content brief for one specific deck rather than a capability statement for a reusable skill. It names a distinctive topic and audience but never states what the skill does or when to invoke it, and omits the natural slide/presentation vocabulary users would use.

Suggestions

State the skill's actual action in third person, e.g. "Builds self-contained HTML slide decks from the Vellum template..." instead of describing one deck's topic.

Add an explicit 'Use when...' clause covering natural triggers such as "Use when the user asks for HTML slides, an academic presentation, or a research deck".

Replace topic-specific nouns ("Renaissance linear perspective") with capability keywords (slides, presentation, research deck, HTML) so the description generalizes beyond a single subject.

DimensionReasoningScore

Specificity

The description names a concrete domain ("A humanities lecture", "decision-grade academic research deck for faculty, graduate seminar") but contains no concrete actions whatsoever — there is no verb stating what the skill does (e.g. create, build, generate). It is a topic statement, matching the anchor 'Names the domain but actions are minimal or generic'. Not a 1 because the domain itself is specific rather than abstract; not a 3 because even 1–2 concrete actions are absent.

2 / 5

Completeness

The 'what' is only vague: "Built as a decision-grade academic research deck" describes the artifact, never the skill's function, and there is no 'Use when...' clause or equivalent trigger guidance anywhere (per the guideline, a missing 'when' caps this dimension, and the vague 'what' puts it at the lower anchor). Matches 'Has a vague what and no when'. Not a 3 because the what is not clearly stated; not a 1 because the domain and audience are at least identified.

2 / 5

Trigger Term Quality

Some natural phrases a user would say are present ("humanities lecture", "academic research deck"), but common variations users actually use for slide work — "slides", "presentation", "HTML deck", "PowerPoint" — are missing from the description. Matches 'Some relevant keywords but missing common variations or synonyms'. Not a 4 because the keyword set is thin; not a 2 because more than two relevant natural terms are present.

3 / 5

Distinctiveness Conflict Risk

The very specific topic framing ("how Renaissance linear perspective reshaped early cartography — sources, argument, and evidence") gives it a clear niche with minimal conflict risk against unrelated skills. Matches 'Mostly distinct; minor overlap risk' — not a 5 because the skill's real function (an HTML slide template) is never surfaced, so generic research/presentation requests could route here incorrectly.

4 / 5

Total

11

/

20

Passed

Validation

81%

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

CriteriaDescriptionResult

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-vellum/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.