CtrlK
BlogDocsLog inGet started
Tessl Logo

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。

71

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

77%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.

A thorough, highly actionable presentation-building workflow with clear sequencing, checkpoints, and verified bundle references. Its main weaknesses are verbosity in places and a large inline preset catalog that would be better split into a reference file.

Suggestions

Move the 12 detailed design-system presets (Step 2, lines ~151–274) into a dedicated reference file, leaving only the topic-recommendation table and a one-line summary per preset in SKILL.md.

Trim the over-specified call-option GOOD/BAD example in Step 3-B to a short illustration of the mood-vs-layout principle; the current ~30-line block contradicts the skill's own 'short prompts' advice.

Cut conceptual exposition Claude already knows (e.g., 'A design system is NOT just colors', the Design Quick Reference truisms) to reduce token load.

DimensionReasoningScore

Conciseness

The body is dense with actionable specifics but ~630 lines with notable padding — the extended call-option GOOD/BAD example, "a design system is NOT just colors" exposition, and restated design wisdom Claude already knows — so it could be tightened.

2 / 3

Actionability

Provides fully executable bash and JS commands (generate_image.py, html2pptx.js, create_slides.py), concrete HTML rules, exact file paths, and copy-paste-ready style prompts.

3 / 3

Workflow Clarity

Clear Step 0–5 sequence with explicit Checkpoints 1–4 and validate→regenerate feedback loops (text accuracy, layout, style-consistency checks after generation).

3 / 3

Progressive Disclosure

References are well-signaled and one level deep (all referenced files verified present), but the 12+ full design-system presets are inlined in SKILL.md when they belong in a separate reference, matching the 'content that should be separate is inline' anchor.

2 / 3

Total

10

/

12

Passed

Description

100%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.

A concise, well-constructed description that states concrete capabilities, explicit trigger terms in both Chinese and English, and a clear use-when clause. It cleanly answers what the skill does and when to invoke it.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "端到端演示文稿制作", "AI插画生成", and "18种设计风格" — rather than vague language, matching the anchor for enumerating specific capabilities.

3 / 3

Completeness

Explicitly answers both what (end-to-end PPTX creation with AI illustration and 18 styles) and when ("当用户提到…时使用" trigger clause), satisfying the top anchor.

3 / 3

Trigger Term Quality

Includes natural bilingual terms users would actually say — "做PPT", "做幻灯片", "演示文稿", "Keynote", "slides" — giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear presentation-creation niche with distinct triggers and third-person voice, making overlap with other skills unlikely.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (637 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
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.