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

The canonical home for this skill is gyan/pptx

Quality

Content

77%

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 with strong QA/verification workflows, but it carries a large inline design-guidance section that trades against token efficiency and relies on two referenced markdown files (editing.md, pptxgenjs.md) that are missing from the bundle. Fixing the broken references and offloading the design material would lift both weak dimensions.

Suggestions

Create the missing editing.md and pptxgenjs.md bundle files referenced by 'Read [editing.md](editing.md)' and 'Read [pptxgenjs.md](pptxgenjs.md)', or remove the links — they currently point to nonexistent files.

Move the Design Ideas section (color palettes, typography, spacing, and the 'Avoid' list) into a separate reference file such as design.md and link to it from SKILL.md, keeping only the core read/edit/create workflow inline.

Trim general design coaching Claude already knows ('Don't create boring slides', 'Plain bullets on a white background won't impress anyone') to tighten the token budget.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands, but the large inline Design Ideas section (10 color palettes, font-pairing tables, spacing rules, and coaching like 'Don't create boring slides') spends tokens on general design principles Claude already knows and could live in a reference file.	2 / 3
Actionability	Provides copy-paste-ready, executable commands throughout — 'python -m markitdown presentation.pptx', 'python scripts/thumbnail.py', 'python scripts/office/unpack.py', the soffice/pdftoppm conversion pair, and a grep one-liner for leftover placeholders.	3 / 3
Workflow Clarity	The QA section gives an explicit verification loop with checkpoints — 'Generate slides → Convert to images → Inspect → List issues → Fix → Re-verify affected slides → Repeat until no new issues' and 'Do not declare success until you've completed at least one fix-and-verify cycle' — exactly the feedback-loop pattern the top anchor rewards.	3 / 3
Progressive Disclosure	Structure is clear (Quick Reference table, well-signaled one-level links to editing.md and pptxgenjs.md), but those referenced files do not exist in the bundle and the bulky Design Ideas content that should be split out is inline, matching the mid anchor rather than the top.	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.

The description is specific, trigger-rich, and clearly scoped to .pptx work, explicitly answering both what the skill does and when to use it. It uses the canonical third-person/imperative trigger voice with no vague fluff. This is a strong, low-conflict trigger description.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — 'creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text... editing, modifying, or updating... combining or splitting slide files; working with templates, layouts, speaker notes, or comments' — matching the top anchor.	3 / 3
Completeness	Explicitly answers both what (the enumerated 'This includes' actions) and when ('Trigger whenever the user mentions...' and 'If a .pptx file needs to be opened, created, or touched, use this skill'), satisfying the top anchor; the explicit 'Use when'-style trigger guidance keeps completeness at 3 rather than capped at 2.	3 / 3
Trigger Term Quality	Covers natural user terms users would actually say — 'deck,' 'slides,' 'presentation,' and '.pptx filename' — with good variation, matching the top anchor.	3 / 3
Distinctiveness Conflict Risk	Scoped tightly to .pptx with distinct triggers ('deck,' 'slides,' 'presentation,' '.pptx filename'), making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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: K-Dense-AI/scientific-agent-skills
Path: skills/pptx/SKILL.md
Commit: 757b63b

Reviewed: about 9 hours 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.