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。

64

Quality

76%

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 ./skills/pptgen-drawio/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%

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

The content has a well-sequenced workflow with strong validation and feedback loops, plus concrete export commands. Its weaknesses are some verbosity/redundancy in the checklist and page-list, and that the heavily-referenced style files are absent from the bundle.

Suggestions

Add the missing reference/style1-classic-academic.md through style4-tech-modern.md (and style-custom.md) to the bundle, or inline the essential style rules so the signaled references resolve.

Provide one complete, executable content-page XML example in Step 2 rather than only the minimal empty mxfile skeleton.

Tighten the overlap between the "已知坑清单" checklist and "其他注意事项" to remove redundant guidance and reduce token weight.

DimensionReasoningScore

Conciseness

The body is mostly operational (mode table, steps, checklist, page sequence) but the 23-page default list and the 10-item "已知坑清单" overlap with "其他注意事项" and could be tightened; some redundancy keeps it from a 3.

2 / 3

Actionability

Concrete commands (pip install drawio2pptx -q, Set-Location, drawio2pptx ...) and checklist items are present, but the core generative step only shows a minimal empty-structure XML template rather than a complete executable content-page example.

2 / 3

Workflow Clarity

Steps 0→1→2→3→4 are clearly sequenced with explicit validation checkpoints (必过 checklist, 页数校验 requiring (N slides) == diagram count) and an export-failure troubleshooting feedback loop.

3 / 3

Progressive Disclosure

Style details are pointed to reference/styleX-*.md via a clearly signaled table, but those referenced files do not exist in the bundle (only scripts/analyze_pptx.py is present); navigation targets are missing, so it is not a clean one-level-deep structure.

2 / 3

Total

9

/

12

Passed

Description

90%

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: it covers what the skill does, when to use it, and natural trigger terms in a compact, third-person form. Specificity is the only mild weakness, as actions are described at a high level rather than enumerated concretely.

DimensionReasoningScore

Specificity

"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" name the domain and several actions, but each is a high-level capability rather than a list of multiple concrete specific actions; not comprehensive enough for a 3.

2 / 3

Completeness

It states what it does (generate multi-page Draw.io PPT, two modes, auto-export to .pptx) and an explicit when clause ("当用户提到...时使用").

3 / 3

Trigger Term Quality

"论文答辩 PPT、答辩幻灯片、通用 PPT、汇报 PPT、根据模板生成 PPT、drawio2pptx" give good coverage of natural terms a user would actually say, plus the tool name.

3 / 3

Distinctiveness Conflict Risk

The Draw.io→PPTX thesis-defense/reporting niche is clear, with distinct triggers including the tool name drawio2pptx, making conflict with other skills unlikely.

3 / 3

Total

11

/

12

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.