CtrlK
BlogDocsLog inGet started
Tessl Logo

nanobanana-ppt-visualizer

PPT 视觉增强工具,支持多种风格渲染、交互式播放器生成和视频合成。可与 ppt-generator Skill 协同工作,实现从内容规划到视觉呈现的完整流程。

49

Quality

55%

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/nanobanana-ppt-visualizer/nanobanana-ppt-visualizer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

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

The skill body is well-structured with a clear step sequence and a resource index, but it is held back by an abstract image-generation step, missing validation checkpoints, and a broken reference to the non-existent video_composer.py script. Tightening the diagram and fixing the reference would materially improve it.

Suggestions

Add scripts/video_composer.py to the bundle or remove its references from Step 5, the resource index, and Example 4 so all cited paths resolve.

Insert validation/verification checkpoints (e.g. confirm each slide PNG exists before generating the viewer; verify the FFmpeg output file after synthesis) to support the batch generation and video-composition steps.

Make the image-generation step more concrete by specifying the expected prompt format, output filename pattern, and directory, rather than 'use the agent's image generation capability'.

DimensionReasoningScore

Conciseness

The body is mostly efficient, but the large ASCII 协同工作流程 diagram enumerating ppt-generator's 7 roles and the inline JSON 数据格式兼容性 example add length beyond what Claude needs, fitting the 'mostly efficient but includes some unnecessary explanation' anchor.

2 / 3

Actionability

Concrete commands appear (e.g. 'python scripts/generate_viewer.py --input ./ppt_data.json --style gradient-glass'), but the core image-generation step is abstract ('使用智能体的图像生成能力创建图片') without executable detail, matching 'some concrete guidance but incomplete'.

2 / 3

Workflow Clarity

Steps 1–5 are clearly sequenced across collaborative and standalone modes, but there are no validation or verification checkpoints for the generation/video-synthesis outputs, so per the batch-operation guideline workflow clarity is capped at 2.

2 / 3

Progressive Disclosure

The 资源索引 provides a well-signaled, one-level-deep reference list, but the body references scripts/video_composer.py (Step 5, resource index, Example 4) which does not exist in the bundle, a broken navigation path that prevents a score of 3.

2 / 3

Total

8

/

12

Passed

Description

60%

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 specific about capabilities but weak on triggering: it states concrete actions yet lacks an explicit 'Use when...' clause and natural trigger-term coverage. This makes it less discoverable and somewhat overlapping with ppt-generator. Adding a Use-when clause with common terms (PPT, 幻灯片, 演示文稿) would raise completeness and trigger quality.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user needs to add visuals, slide images, an interactive player, or synthesized video to a PPT/演示文稿/幻灯片.'

Include natural trigger-term variations (幻灯片, 演示文稿, slides, 播放器) so users' phrasing matches the description.

Sharpen the distinction from ppt-generator by stating this skill handles visual rendering/player/video only, not content planning.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — '多种风格渲染、交互式播放器生成和视频合成' (style rendering, interactive player generation, video synthesis) — matching the anchor for listing multiple specific concrete actions.

3 / 3

Completeness

It clearly states what the skill does but provides no explicit 'Use when...' trigger clause; the only 'when' is implied via the ppt-generator collaboration, so per the guidelines completeness is capped at 2.

2 / 3

Trigger Term Quality

It contains the natural keyword 'PPT', but omits common variations a user might say such as 幻灯片, 演示文稿, or slides, fitting the 'some relevant keywords but missing common variations' anchor.

2 / 3

Distinctiveness Conflict Risk

The 'PPT 视觉增强工具' niche is somewhat specific and distinguishes it from ppt-generator's content role, but the lack of explicit triggers and close pairing with ppt-generator leaves real overlap risk, matching the 'somewhat specific but could still overlap' anchor.

2 / 3

Total

9

/

12

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 1 missing

Warning

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

13

/

16

Passed

Repository
anbeime/skill
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.