CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pitch-deck

当执行 BD/IR 任务需要对外演示材料时创建精美的 HTML 演示文稿——路演 PPT、合作提案、客户 Demo、产品介绍。零依赖单文件输出,可直接通过邮件/微信发送或浏览器演示。

Quality

73%

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 ./crews/main/skills/pitch-deck/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 body is a well-sequenced, highly actionable workflow whose script commands match the real bundle files. Its main defects are the missing STYLE_PRESETS.md file that the workflow depends on for presets and the mandatory CSS base, and duplicated long-image/dependency content between the workflow step and the dedicated conversion section.

Suggestions

Add the missing STYLE_PRESETS.md (preset catalog, viewport-safe CSS base, density limits) to the bundle — the body instructs "务必读取" but the file does not exist, breaking the style-selection and build steps.

Deduplicate the long-image delivery instructions and the "依赖" notes between 第七步:交付 and the "HTML → 长图转换" section.

Add an explicit validation loop for the hard viewport rule: render/screenshot each slide, detect overflow, and split any slide that does not fit before delivery.

DimensionReasoningScore

Conciseness

Mostly tight, task-specific guidance (density tables, anti-patterns, hard viewport rules), but the long-image delivery instructions and dependency notes appear twice (第七步 vs the "HTML → 长图转换" section, and the "依赖:Pillow 由 xiaobei 统一安装" note repeated in both conversion sections), and four worked CLI examples pad the conversion sections. This is noticeably duplicated rather than the minor trimming of anchor 4.

3 / 5

Actionability

Commands are copy-paste ready with exact flags that match the real bundled scripts (--save-slides, --screenshots-dir, --images-dir all verified present), plus concrete CSS rules ("height: 100vh; height: 100dvh; overflow: hidden") and per-deck structure templates. The gap beyond anchor 5: the preset catalog and required "视口安全 CSS 基础" block are delegated to STYLE_PRESETS.md, which does not exist in the bundle.

4 / 5

Workflow Clarity

A clear 7-step sequence with mode disambiguation, a hard acceptance criterion ("视为硬性验收标准") for viewport fit, an overflow remedy rule ("内容放不下时,拆分成多张幻灯片"), error fallback for missing python-pptx, and a delivery checklist. Validation is checklist-based rather than the explicit validate→fix→retry loops of anchor 5 (e.g. no instructed step to actually verify each slide fits the viewport).

4 / 5

Progressive Disclosure

Good section structure with one-level-deep script references that all exist and are accurately documented. The one significant organization gap: STYLE_PRESETS.md is repeatedly flagged as required reading ("务必读取 STYLE_PRESETS.md", "详见 STYLE_PRESETS.md") but is missing from the bundle (no references/ directory), so a core navigation target is a dangling reference.

4 / 5

Total

15

/

20

Passed

Description

70%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 clearly states what the skill produces and when to use it, using natural Chinese business trigger terms. Its main weaknesses are that only the creation workflow is described (the conversion half of the skill is missing) and the trigger condition leans on the jargon abbreviation "BD/IR" rather than phrases a user would naturally say.

Suggestions

Add the conversion capabilities (PPT/PPTX→HTML, HTML→长图, HTML→PPTX) to the description so coverage matches what the skill body actually does.

Expand the trigger beyond "BD/IR 任务" with natural variations users would say, e.g. "pitch deck、融资路演、幻灯片、.pptx 转换".

DimensionReasoningScore

Specificity

The description names the domain (BD/IR presentation materials) and one core concrete action ("创建精美的 HTML 演示文稿") plus output properties ("零依赖单文件输出"), but the skill's conversion capabilities (PPT/PPTX→HTML, HTML→长图/PPTX) are entirely absent, so coverage is not comprehensive. It sits above anchor 3's example thanks to enumerated deliverable types, but below anchor 4 because only one distinct action is stated.

3 / 5

Completeness

Both parts are explicitly answered: what ("创建...HTML 演示文稿...零依赖单文件输出") and when ("当执行 BD/IR 任务需要对外演示材料时") followed by concrete deck types. The when-clause is a single abstract condition hinging on the jargon abbreviation "BD/IR" rather than the concrete user-mention trigger phrases of anchor 5.

4 / 5

Trigger Term Quality

Natural Chinese business phrases users would say are present: "路演 PPT", "合作提案", "客户 Demo", "产品介绍", "演示文稿". A few natural terms are missing, e.g. the English "pitch deck", "融资演示", "幻灯片", and ".pptx" as a file-format trigger, so it does not reach anchor 5's comprehensive synonym/extension coverage.

4 / 5

Distinctiveness Conflict Risk

The HTML-presentation niche for BD/IR with triggers like 路演/合作提案 is mostly distinct from document- or data-oriented skills. There is minor overlap risk with a generic presentation/.pptx skill, keeping it below anchor 5.

4 / 5

Total

15

/

20

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.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

TeamWiseFlow/xiaobei

Path

crews/main/skills/pitch-deck/SKILL.md

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.