html-ppt

HTML PPT Studio — author professional static HTML presentations in many styles, layouts, and animations, all driven by templates. Use when the user asks for a presentation, PPT, slides, keynote, deck, slideshow, "幻灯片", "演讲稿", "做一份 PPT", "做一份 slides", a reveal-style HTML deck, a 小红书图文, or any kind of multi-slide pitch/report/sharing document that should look tasteful and be usable with keyboard navigation. Triggers include keywords like "presentation", "ppt", "slides", "deck", "keynote", "reveal", "slideshow", "幻灯片", "演讲稿", "分享稿", "小红书图文", "talk slides", "pitch deck", "tech sharing", "technical presentation".

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./SKILL.md

Quality

Content

50%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured and information-rich with a clear authoring workflow and good reference navigation, but it loses points across the board: inline duplication of presenter-mode detail and full theme/FX enumerations hurt conciseness, several copy-paste commands target non-existent template/example paths, and no validation feedback loops are specified.

Suggestions

Move the detailed presenter-mode internals (pixel-perfect iframe rendering, postMessage preview-goto, BroadcastChannel sync) into references/presenter-mode.md and keep only the 3 speaker-script rules plus a short pointer in the body, to remove duplication and tighten conciseness.

Replace the inline enumeration of all 36 theme filenames and all 20 FX names with a brief count plus a pointer to references/themes.md and references/animations.md, since those catalogs already exist.

Reconcile the templates/ and examples/ paths referenced throughout Quick start steps 3–6, the render examples, and the file-structure tree with the actual bundle (e.g. note that templates are generated by scripts/new-deck.sh), so copy-paste commands no longer point at missing files.

Dimension	Reasoning	Score
Conciseness	The body is mostly high-signal and avoids explaining concepts Claude already knows, but it over-enumerates all 36 theme filenames and all 20 FX names inline, and duplicates a ~20-line presenter-mode internals block (pixel-perfect iframes, postMessage, BroadcastChannel) that already lives in references/presenter-mode.md.	2 / 3
Actionability	Guidance is concrete and copy-paste-ready in form (install, new-deck.sh, data-anim/data-fx snippets, render.sh), but a large share of the actionable steps (Quick start 3–6 and render examples) point at templates/ and examples/ paths that are not present in the bundle, so the guidance is incomplete rather than fully executable.	2 / 3
Workflow Clarity	There is a clear sequence (clarify 3 things → scaffold → pick theme → pick layouts → add animations → render), but no explicit validation checkpoints or validate→fix→retry feedback loops are given for the batch render / authoring workflow.	2 / 3
Progressive Disclosure	A "Catalogs (load when needed)" section points cleanly to six real one-level-deep reference files, but the presenter-mode mechanics are duplicated inline despite the existing reference, and the body repeatedly references templates/ and examples/ paths that do not exist in the actual bundle.	2 / 3
	Total	8 / 12 Passed

Description

90%Weight 40%Scale 1-3

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 is strong: it states the skill's purpose concisely, provides rich natural-language triggers in English and Chinese, and explicitly pairs "what" with "when to use". The only weakness is that it names a single action ("author") with modifiers rather than enumerating several distinct operations.

Dimension	Reasoning	Score
Specificity	It names a concrete domain ("author professional static HTML presentations") and concrete dimensions ("many styles, layouts, and animations, all driven by templates"), but lists only the single action "author" rather than multiple distinct concrete actions like the anchor-3 example.	2 / 3
Completeness	It clearly answers both what ("author professional static HTML presentations...") and when ("Use when the user asks for a presentation, PPT, slides...") with explicit triggers.	3 / 3
Trigger Term Quality	It gives broad natural-term coverage in both English and Chinese ("presentation", "ppt", "slides", "deck", "keynote", "reveal", "slideshow", "幻灯片", "演讲稿", "做一份 PPT", "小红书图文") plus an explicit "Triggers include keywords like..." list.	3 / 3
Distinctiveness Conflict Risk	It carves a clear niche (static HTML slide decks with keyboard navigation, reveal-style, 小红书图文) with distinct presentation/deck triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 3 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: lewislulu/html-ppt-skill
Path: SKILL.md
Commit: f3a8435

Reviewed: 9 days 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.