huashu-slides

从内容到成品PPTX的端到端演示文稿制作，含AI插画生成和18种设计风格。当用户提到"做PPT"、"做幻灯片"、"演示文稿"、"Keynote"、"slides"时使用。

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./huashu-slides/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 skill is well-structured with a clear multi-step workflow, concrete executable commands, and genuine one-level-deep reference files. Its main weakness is conciseness: large style-preset catalogs and verbose prompt examples are inlined in SKILL.md when they would be more effective in the existing reference files.

Suggestions

Move the 12 full Design System Preset descriptions (colors/ratios/typography/composition per style) into references/proven-styles-gallery.md, keeping only the topic-recommendation table and tier labels in the body.

Trim the multi-paragraph GOOD-vs-BAD prompt example in Step 3-B to a compact template plus a single short contrast, relocating the long worked example to references/prompt-templates.md.

Add an explicit validate→fix→retry feedback loop after PPTX assembly (e.g., verify the PPTX opens and text renders correctly before declaring done) to strengthen workflow_clarity for this batch/destructive-ish output operation.

Dimension	Reasoning	Score
Conciseness	The body runs ~640 lines with large inlined style-preset catalogs (12 full preset descriptions with colors/ratios/typography) and lengthy GOOD-vs-BAD prompt examples that belong in reference files; this is noticeably verbose relative to the lean anchor.	2 / 5
Actionability	Provides concrete, executable guidance — real bash commands for image generation, a JavaScript html2pptx snippet, and Python create_slides.py usage — with only minor gaps (some paths assume external skills that may be absent).	4 / 5
Workflow Clarity	The 5-step process (Content → Design → Build → Assembly → Polish) is clearly sequenced with explicit numbered checkpoints and a default-mode fallback, though per-step validation feedback loops are implicit rather than spelled out as validate→fix→retry.	4 / 5
Progressive Disclosure	Good use of one-level-deep references (design-movements.md, proven-styles-gallery.md, proven-styles-snoopy.md, prompt-templates.md, design-principles.md, assets/style-samples/) that exist as real files, but substantial catalog content is still inlined in the body rather than fully offloaded.	4 / 5
	Total	14 / 20 Passed

Description

91%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 is strong: it states concrete capabilities, includes a rich set of natural trigger terms (including the bilingual Keynote/slides variants), and explicitly answers both 'what' and 'when'. Third-person voice is preserved throughout.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — '端到端演示文稿制作' and 'AI插画生成' — and enumerates '18种设计风格', covering the main capabilities with only minor gaps (no explicit mention of PPTX export).	4 / 5
Completeness	Clearly states what it does ('从内容到成品PPTX的端到端演示文稿制作，含AI插画生成和18种设计风格') and explicitly when to use it ('当用户提到...时使用') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including synonyms and the file-type term — '做PPT', '做幻灯片', '演示文稿', 'Keynote', 'slides' — phrases users would naturally say.	5 / 5
Distinctiveness Conflict Risk	The presentation/PPTX niche with AI illustration and 18 design styles is fairly distinct and has clear triggers; minor overlap risk with generic slide or image-generation skills keeps it just below 5.	4 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (642 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: alchaincyf/huashu-skills
Path: huashu-slides/SKILL.md
Commit: 49a55ba

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.