CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

html-ppt-xhs-pastel-card

A personal manifesto: a year of saying yes — the premise, the scenes, the turn, and the meaning that lands. Built as a decision-grade story deck for community, talk audience.

50

Quality

63%

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-xhs-pastel-card/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 well-structured entry-point card: it correctly delegates authoring rules to the master skill and concentrates on the one thing unique to this card — wiring the xhs-pastel-card template and its shared runtime into a project — with unusually specific guidance on the asset-path pitfall. Main weaknesses are the absence of any post-copy validation step and inconsistent upstream path bases that make the external references harder to follow.

Suggestions

Add a validation step after the copy/rewrite recipes, e.g. "Verify: open index.html in a browser and confirm T cycles themes and arrow keys navigate slides before delivering."

Fix the path inconsistency — pick one base for the upstream (either "../html-ppt/SKILL.md" or "design-templates/html-ppt/SKILL.md") and use it consistently in the intro, step 1, and step 3.

Tighten step 3 by stating the pitfall once (relative URLs 404 after copying) and listing the four asset paths a single time in the recipe, rather than repeating them across the warning, Recipe A, and the closing guard.

DimensionReasoningScore

Conciseness

The body is lean and operational — exact file paths, class names (".tpl-xhs-pastel-card"), and the theme mechanism with no concept explanations — but step 3 pads a concept Claude already knows ("those parent-relative URLs no longer resolve and base.css... will 404 — meaning the deck never activates and slide navigation is dead") and repeats the four asset filenames three times, fitting 'Efficient; minor instances of over-explanation that could be trimmed'. Not score 3 because the trimming needed is localized to one step, and not score 5 because that step's redundancy is real.

4 / 5

Actionability

Guidance is concrete and executable: copy "index.html and style.css", keep the ".tpl-xhs-pastel-card" body class, rewrite the four link/script tags to named project-local paths, swap themes via "<link id=\"theme-link\">", put notes in "<aside class=\"notes\">" — matching 'Mostly executable guidance; concrete code or commands with minor gaps'. The gap keeping it from 5 is a path inconsistency: the intro links "../html-ppt/SKILL.md" while steps 2–3 use "design-templates/html-ppt/..." for the same upstream, and none of these files ship in this skill's bundle, so a reader cannot tell exactly where the master files live.

4 / 5

Workflow Clarity

The six steps are clearly numbered and ordered, and the riskiest operation (asset URL rewriting) has its failure mode spelled out plus a guard ("do not ship the upstream ../../../assets/... URLs verbatim"), but there is no validation checkpoint anywhere — nothing like "after rewriting, open index.html and confirm the keyboard runtime and slide navigation work". That matches 'Steps listed but validation gaps; sequence present but checkpoints missing or implicit' rather than score 4, which requires most checkpoints to be present.

3 / 5

Progressive Disclosure

The body is a well-signaled overview pointing one level deep to the master skill ("Read the master skill first... All authoring rules live in [html-ppt/SKILL.md]") and the full-decks catalog, keeping only entry-card-specific operational detail inline — matching 'Good structure; most content is appropriately placed; references mostly clear; minor organization gaps'. Not score 5 because the referenced files are not part of this skill's bundle and the two conflicting base paths ("../html-ppt/" vs "design-templates/html-ppt/") leave navigation slightly ambiguous.

4 / 5

Total

15

/

20

Passed

Description

45%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 topic statement for one specific deck rather than a capability description for the skill. It identifies the subject and audience clearly but omits what the skill does (author HTML presentation decks in the xhs-pastel-card visual system) and when to invoke it, both of which the rubric expects explicitly.

Suggestions

Rewrite the description in third person with capability verbs, e.g. "Builds an HTML presentation deck in the xhs-pastel-card pastel visual system from a personal story or manifesto brief — plan, slides, speaker notes, and visual direction."

Append an explicit trigger clause: "Use when the user asks for a personal manifesto talk, life-story deck, photo essay presentation, or HTML slides in a soft pastel card style."

Include the differentiators (HTML output, pastel card template, speaker-ready structure) so this card cannot be confused with sibling story/deck template skills.

DimensionReasoningScore

Specificity

The description is a content brief ("A personal manifesto: a year of saying yes — the premise, the scenes, the turn, and the meaning that lands") with only one output-oriented phrase ("Built as a decision-grade story deck for community, talk audience"); it names the domain but names no concrete actions the skill performs (no create/build/design verbs), matching the anchor 'Names the domain but actions are minimal or generic' rather than score 1, which requires pure abstraction with no domain identified.

2 / 5

Completeness

A partial 'what' is present ("Built as a decision-grade story deck for community, talk audience") but there is no 'Use when...' clause or equivalent trigger guidance anywhere in the description, which caps completeness at 3 per the judging guidelines. It is above score 2 because the 'what' names a concrete deliverable and audience rather than being entirely vague.

3 / 5

Trigger Term Quality

"personal manifesto", "story deck", and "community, talk audience" are phrases a user would plausibly say, but common variations are missing ("talk", "presentation", "slides", "html deck" appear only in the triggers field, not the description), matching 'Some relevant keywords but missing common variations or synonyms'. Not score 4 because coverage is thin — most natural request phrasings for this skill are absent from the description itself.

3 / 5

Distinctiveness Conflict Risk

Phrases like "a year of saying yes" and "decision-grade story deck" carve out a niche, but the description never mentions the actual differentiators (HTML deck, pastel card template), so it overlaps with any sibling story/deck template skill in the same family — matching 'Somewhat specific but could still overlap with similar skills'. Not score 4 because without the template/format identifier the trigger surface is ambiguous across related deck skills.

3 / 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: 3 suspicious

Warning

referenced_paths_exist

Referenced path issues: 5 missing, 2 deeper-than-1-level

Warning

Total

13

/

16

Passed

Repository

nexu-io/open-design

Path

design-templates/html-ppt-xhs-pastel-card/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.