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）。

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%Weight 40%Scale 1-3

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 tight, well-sequenced orchestration workflow with strong feedback loops and checkpoints. Its weaknesses are deferred detail that points at missing reference files and incomplete (TBD) style presets, which undercut actionability and progressive disclosure.

Suggestions

Create or ship the referenced bundle files (ppt-lofi-authoring.md, ppt-style-huawei.md) under refs/ so the lofi-authoring and style-preset details the body points to actually resolve.

Fill in the 待补 (TBD) entries for the Apple and 阿里 style presets, or remove them from the table until they are ready, so the style Preset section is actionable.

Inline a minimal executable slice of the lofi-MD authoring spec (one full worked page with ASCII art + visual guidance) in SKILL.md so the skill remains usable even when the ref file is absent.

Dimension	Reasoning	Score
Conciseness	The body is dense and table-driven with no padding or explanation of concepts Claude already knows (no "what is a PPT" filler); nearly every line carries instruction, so every token earns its place.	3 / 3
Actionability	It gives concrete templates, file-structure examples, and naming conventions ("p{N}-{简短描述}.png"), but the core authoring spec is deferred to ../refs/ppt-lofi-authoring.md which does not exist, and two style presets are marked 待补 (TBD), leaving key guidance incomplete.	2 / 3
Workflow Clarity	A clear 6-stage routing table sequences the process with an explicit feedback loop ("R: 回到 1 或 2") and validation checkpoints ("先给operator看分页表，确认再动手写", "审稿通过" before imagegen), covering error recovery for the batch image-generation step.	3 / 3
Progressive Disclosure	The body signals one-level-deep references (../refs/ppt-lofi-authoring.md, ../refs/ppt-style-huawei.md), but those files do not exist in the bundle, so the disclosed references are broken rather than navigable.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 states a concrete multi-step pipeline, gives explicit natural-language triggers, and draws clear boundaries with a Not-for clause. It is concise and uses third-person voice throughout.

Dimension	Reasoning	Score
Specificity	Names the full concrete pipeline ("内容分析 → 分页规划 → 低保真 MD → imagegen 精美图") and the role split plus a concrete output ("低保真 MD + AI 原生精美图"), listing multiple specific actions rather than vague language.	3 / 3
Completeness	It explicitly answers both what (the full authoring→imaging pipeline) and when (explicit "Use when" triggers), and adds a "Not for" boundary, so both clauses are present and explicit.	3 / 3
Trigger Term Quality	The "Use when" clause covers natural terms users would actually say — "做 PPT、做演示文稿、做 slide、帮朋友做 PPT、画架构图、画技术蓝图" — with good coverage and natural variation.	3 / 3
Distinctiveness Conflict Risk	It carves a clear PPT/slide niche with distinct triggers and an explicit "Not for" exclusion (pure code dev, pure doc writing), making collision with adjacent skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 5 suspicious	Warning

	Total	15 / 16 Passed

Repository: zts212653/clowder-ai
Path: cat-cafe-skills/ppt-forge/SKILL.md
Commit: 80782c5

Reviewed: 11 days ago

Table of Contents

Discovery Implementation Validation

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.