CtrlK
BlogDocsLog inGet started
Tessl Logo

ppt-forge

PPT 制作全链路:内容分析 → 分页规划 → 低保真 MD → imagegen 精美图。 架构猫写低保真 MD(ASCII art 结构图 + 视觉指引),imagegen 猫逐页出精美图。 Use when: 做 PPT、做演示文稿、做 slide、帮朋友做 PPT、画架构图、画技术蓝图。 Not for: 纯代码开发(用 worktree/tdd)、纯文档写作(直接写)。 Output: 低保真 MD + AI 原生精美图(raster PNG)。

67

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

71%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-organized, mostly lean overview with a clear routed workflow and concrete handoff protocol. Its main weakness is dependence on external shared-reference files that are not bundled with the skill, hurting both actionability and self-containment.

Suggestions

Bundle the referenced specs (ppt-lofi-authoring.md, ppt-style-huawei.md) under references/ within the skill, or inline the essential authoring rules so the skill is self-contained.

Add an explicit validation checkpoint after imagegen output (e.g., verify each page image matches the corresponding lofi MD section and naming convention) before delivery.

Tighten placeholder content — fill or remove the '待补' style-preset rows and replace informal asides like '出来贼丑' with concise technical rationale.

DimensionReasoningScore

Conciseness

Mostly lean and table-driven assuming Claude's competence, but informal asides ('出来贼丑', '贼丑') and placeholder rows ('待补' for Apple/阿里 styles) are minor trim opportunities; not fully the 'every token earns its place' anchor.

4 / 5

Actionability

Concrete guidance throughout — 开局参数 table, numbered 写作流程, a 低保真 MD file template, and a handoff protocol with specific naming ('p{N}-{简短描述}.png') and output location ('assets/') — but the core authoring spec is deferred to an external file not present in the bundle, leaving a minor gap.

4 / 5

Workflow Clarity

The 场景路由 table sequences steps 1-5 plus an R retry loop with explicit checkpoints (operator confirms 分页 before writing, 审稿通过 before imagegen), but there is no checkpoint validating that generated images actually match the lofi MD content.

4 / 5

Progressive Disclosure

References are clearly signaled and one level deep (ppt-lofi-authoring.md, ppt-style-huawei.md), but they point outside the skill bundle to a shared-refs directory that does not exist in the review environment, and no bundle files (references/scripts/assets) ship with the skill, so it is not self-contained.

3 / 5

Total

15

/

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, well-structured description: it states a concrete multi-stage pipeline, gives explicit natural-language triggers, and draws clear boundaries with a 'Not for' clause. The only minor gap is slight redundancy and a few missing synonyms in the trigger list.

DimensionReasoningScore

Specificity

Lists multiple concrete pipeline stages — '内容分析 → 分页规划 → 低保真 MD → imagegen 精美图' plus 'ASCII art 结构图 + 视觉指引' — giving comprehensive coverage of what the skill does, matching the multi-action anchor.

5 / 5

Completeness

Explicitly answers both what (full pipeline) and when (concrete 'Use when' triggers), and adds 'Not for' boundaries and 'Output' — clearly the top anchor.

5 / 5

Trigger Term Quality

'Use when: 做 PPT、做演示文稿、做 slide、帮朋友做 PPT、画架构图、画技术蓝图' covers natural synonyms (PPT/演示文稿/slide), but '做 PPT' and '帮朋友做 PPT' are redundant and file-extension/alternative terms like 幻灯片 or .pptx are absent.

4 / 5

Distinctiveness Conflict Risk

A clear PPT-via-imagegen niche with explicit 'Not for' exclusions (纯代码开发, 纯文档写作) minimizes conflict with adjacent skills.

5 / 5

Total

19

/

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.

Validation14 / 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: 5 suspicious

Warning

Total

14

/

16

Passed

Repository
zts212653/clowder-ai
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.