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.

1.54x

Quality

89%

Does it follow best practices?

Impact

82%

1.54x

Average score across 14 eval scenarios

Securityby

Passed

No findings from the security scan

The canonical home for this skill is pptx in anthropics/skills

Quality

Content

78%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 highly actionable and pairs strong command coverage with an excellent QA verification loop, but it suffers from two missing referenced files (editing.md, pptxgenjs.md) that break navigation for the editing and create-from-scratch paths, plus some over-explained design prose that could be trimmed.

Suggestions

Add the missing editing.md and pptxgenjs.md files to the bundle (or remove the dead links and inline the essential steps), so the editing and create-from-scratch workflows are actually navigable.

Trim the conceptual prose in Design Ideas (e.g., "Don't create boring slides…", "Dominance over equality") and lead with the concrete palette/font/size tables, which are the genuinely useful reference data.

Expand the compressed editing workflow ("Unpack → manipulate slides → edit content → clean → pack") into explicit numbered steps with the underlying script commands, matching the clarity of the QA verification loop.

Dimension	Reasoning	Score
Conciseness	The operational sections (Quick Reference, Reading, QA, Converting, Dependencies) are lean and command-driven, but the Design Ideas section opens with preachy conceptual advice ("Don't create boring slides. Plain bullets on a white background won't impress anyone", "Dominance over equality") that over-explains design ideas Claude largely already knows; the concrete palette/font/size tables, however, earn their place.	4 / 5
Actionability	Provides copy-paste-ready commands for the common cases (markitdown extraction, thumbnail.py, office/unpack.py, soffice PDF conversion, pdftoppm rendering), a ready-to-use subagent visual-QA prompt, and a grep pattern for leftover placeholders — fully executable guidance.	5 / 5
Workflow Clarity	The QA section is exemplary: an explicit verification loop (generate → convert → inspect → list issues → fix → re-verify → repeat) with a "do not declare success until one fix-and-verify cycle" checkpoint, but the editing workflow sequence ("Unpack → manipulate slides → edit content → clean → pack") is compressed and high-level.	4 / 5
Progressive Disclosure	Navigation is signaled well (one-level-deep bold callouts to editing.md and pptxgenjs.md from the Quick Reference table), but those two referenced files do not exist anywhere in the bundle, so the two main editing/creation workflows lead to dead links — navigation is effectively broken for those paths.	3 / 5
	Total	16 / 20 Passed

Description

100%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.

This is an exemplary skill description: it is specific, trigger-rich, complete on both what and when, and clearly scoped to .pptx files with minimal conflict risk. The phrasing follows the standard imperative "Use this skill..." convention seen in the reference good examples rather than the penalized second-person "You can use this" form.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the full pptx lifecycle — creating slide decks/pitch decks/presentations, reading/parsing/extracting text, editing/modifying/updating, combining/splitting slide files, and working with templates/layouts/speaker notes/comments — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (the enumerated create/read/edit/combine/split/template operations) and when ("Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename"), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers natural user terms including synonyms and the file extension: "deck," "slides," "presentation," "pitch decks," and ".pptx filename," matching the comprehensive-anchor pattern.	5 / 5
Distinctiveness Conflict Risk	Tightly anchored to .pptx files ("If a .pptx file needs to be opened, created, or touched, use this skill"), giving it a clear niche with minimal overlap risk against docx/xlsx skills.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 4 missing	Warning
referenced_paths_exist	Referenced path issues: 3 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: ZHangZHengEric/Sage
Path: app/skills/pptx/SKILL.md
Commit: df00b92

Reviewed: 4 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.