CtrlK
BlogDocsLog inGet started
Tessl Logo

pptgen-drawio

根据论文或汇报内容生成多页 Draw.io 格式 PPT,支持论文答辩与通用汇报两种模式,自动导出为 .pptx。当用户提到论文答辩 PPT、答辩幻灯片、通用 PPT、汇报 PPT、根据模板生成 PPT、drawio2pptx 时使用。

69

Quality

84%

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

76%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 highly actionable, well-sequenced workflow with strong validation feedback loops, but token efficiency is dragged down by retained deprecation commentary and progressive disclosure is undermined because the referenced reference/ style files are absent from the bundle.

Suggestions

Remove or relocate the inline '原先…已废弃/已改正' deprecation notes into a single short 'Deprecated patterns' section so the active instructions stay lean.

Add the missing reference/ directory with the five styleX-*.md / style-custom.md files the body instructs Claude to read, or remove the references if the styles are inlined.

Tighten the explanatory paragraphs behind Step 4.5 and the font-size rules to the essential rule plus the table, dropping the narrative justification.

DimensionReasoningScore

Conciseness

Mostly efficient and avoids teaching concepts Claude knows, but several '原先…已废弃/已改正' deprecation notes (lines 98, 130, 246) and repeated justification paragraphs pad the token budget without aiding execution.

3 / 5

Actionability

Fully executable: concrete install/ export commands for bash and PowerShell, exact file names, a minimal XML template, and specific pt/character-budget tables that cover the common cases copy-paste ready.

5 / 5

Workflow Clarity

Clear Step 0–6 sequence with explicit validation checkpoints (postprocess_pptx.py, render_check.py) and feedback loops ('有 OVERFLOW 就回 Step 2…改完重跑'), plus a 7-item pre-generation checklist for the batch/destructive export operation.

5 / 5

Progressive Disclosure

Good section structure and clear one-level-deep references to scripts/, but the repeatedly-referenced reference/ directory and all five styleX-*.md files do not exist in the bundle, so the signaled navigation leads to missing files.

3 / 5

Total

16

/

20

Passed

Description

92%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.

A strong description that explicitly covers both what it does and when to use it, with comprehensive, natural trigger terms including synonyms and the tool name. Written in third person as required.

DimensionReasoningScore

Specificity

Names the concrete action ('生成多页 Draw.io 格式 PPT') plus specifics (two modes, auto-export to .pptx), but is slightly less comprehensive than the multi-action 5-anchor.

4 / 5

Completeness

Explicitly answers what (生成多页 Draw.io PPT, two modes, export to .pptx) and when ('当用户提到…时使用' with concrete trigger phrases).

5 / 5

Trigger Term Quality

Covers natural synonyms users would say ('论文答辩 PPT','答辩幻灯片','通用 PPT','汇报 PPT','根据模板生成 PPT') plus the tool name 'drawio2pptx'.

5 / 5

Distinctiveness Conflict Risk

Clear niche (Draw.io-format PPT generation for defenses/reports) with distinctive triggers including the 'drawio2pptx' tool name; minimal conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
xstongxue/best-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.