pptx

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.

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%

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

A well-structured, highly actionable body with strong validation feedback loops and concrete reference data, weakened mainly by broken navigation links to editing.md and pptxgenjs.md (files absent from the bundle) and some motivational design prose that could be trimmed.

Suggestions

Add the missing editing.md and pptxgenjs.md files (or remove the links and inline the essential steps) so the two primary navigation paths resolve.

Trim motivational rationale like "白底加纯文本要点无法打动任何人" to tighten the design section while keeping the concrete palette, font, and spacing tables.

Consider moving the large inline design-guidance block (palettes, fonts, avoid-list) into a separate design.md referenced from the overview to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient — the concrete color-palette table, font-pairing table, pt-size specs, and bash commands earn their place — but motivational design rationale such as "白底加纯文本要点无法打动任何人" and "配色应该让人觉得是专门为这个主题设计的" is explanatory prose that could be tightened, so it sits at score 2 rather than the lean score 3.	2 / 3
Actionability	Provides fully executable, copy-paste-ready guidance throughout — `python -m markitdown presentation.pptx`, `python scripts/thumbnail.py`, `python scripts/office/unpack.py`, `soffice.py`/`pdftoppm` conversions, the placeholder grep, and a complete subagent visual-check prompt — matching the score-3 anchor.	3 / 3
Workflow Clarity	The edit workflow is sequenced ("解包 → 操作幻灯片 → 编辑内容 → 清理 → 打包") and the "验证循环" section gives an explicit generate→convert→check→fix→re-validate feedback loop with "在完成至少一个修复-验证循环之前，不要宣布成功", matching the score-3 anchor for fragile document operations.	3 / 3
Progressive Disclosure	References are clearly signaled one level deep ("阅读 [editing.md](editing.md)" / "[pptxgenjs.md](pptxgenjs.md)"), but those two primary detail files do not exist in the bundle and the large design-guidance section is inline, so the structure is well-intended but the broken links and inline bulk keep it at score 2 rather than the clean split of score 3.	2 / 3
	Total	10 / 12 Passed

Description

100%

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, comprehensive description that names concrete capabilities, supplies explicit natural-language triggers, and clearly states when to use the skill. The only nit is the soft second-person phrasing in the closing trigger clause, but it follows the accepted 'Use when...' pattern rather than explicit 'I/You' subject voice.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "创建幻灯片、演示文稿或路演材料；读取、解析或提取...文本；编辑、修改或更新...；合并或拆分幻灯片文件；处理模板、布局、演讲者备注或批注" — covering creation, extraction, editing, merging/splitting, and templates comprehensively, matching the score-3 anchor of multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both "what" (the "包括" action list) and "when" ("当用户提到...时触发" plus "如果需要打开、创建或操作 .pptx 文件，就使用此技能"), satisfying the score-3 requirement of an explicit 'Use when' trigger clause.	3 / 3
Trigger Term Quality	Covers natural user terms — "演示文稿"、"幻灯片"、"PPT" plus the ".pptx 文件名" reference — giving good coverage of the phrasings a user would actually say, matching the score-3 anchor rather than the partial coverage of score 2.	3 / 3
Distinctiveness Conflict Risk	Scoped tightly to .pptx files with file-extension-anchored triggers, creating a clear niche unlikely to conflict with other skills; not the generic overlap of score 2.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 4 missing	Warning
referenced_paths_exist	Referenced path issues: 2 deeper-than-1-level	Warning

	Total	13 / 16 Passed

Repository: agentscope-ai/QwenPaw
Path: src/qwenpaw/agents/skills/pptx-en/SKILL.md
Commit: 734c8b9

Reviewed: 3 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.