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

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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, validated workflows, but is weighed down by a heavy design-guidance section and dead references to editing.md/pptxgenjs.md that are absent from the bundle.

Suggestions

Either ship editing.md and pptxgenjs.md alongside SKILL.md or inline their essential content, since the body routes core tasks to files that don't exist in the bundle.

Trim the Design Ideas section (e.g., reduce the palette table and typography tables to a few examples) to lower token cost while preserving the core 'don't make boring slides' guidance.

Add an explicit validation checkpoint to the Editing Workflow steps (e.g., run scripts/office/validate.py after editing) to match the QA section's already-strong verification loop.

Dimension	Reasoning	Score
Conciseness	Commands and workflows are lean, but the Design Ideas section is voluminous (a 10-row palette table, typography tables, an extended Avoid list); while much of it is useful concrete guidance, it could be tightened and risks overloading the context window, fitting the 'mostly efficient but could be tightened' anchor.	2 / 3
Actionability	It provides concrete, copy-paste-ready commands ('python -m markitdown presentation.pptx', 'python scripts/thumbnail.py', 'pdftoppm -jpeg -r 150 output.pdf slide', 'pip install "markitdown[pptx]"') plus a Quick Reference routing table, matching the fully-executable anchor.	3 / 3
Workflow Clarity	The editing workflow is sequenced ('Analyze template -> Unpack -> manipulate slides -> edit content -> clean -> pack') and QA is an explicit fix-and-verify loop with a checkpoint ('Do not declare success until you've completed at least one fix-and-verify cycle'), matching the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	The Quick Reference table signals one-level-deep pointers to [editing.md] and [pptxgenjs.md], but those files do not exist in the bundle (only SKILL.md and scripts/ are present), so the navigation is broken; this fits the 'references present but not clearly signaled/valid' band rather than the clean one-level-deep anchor.	2 / 3
	Total	10 / 12 Passed

Description

90%

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, detailed description with explicit what/when triggers and good natural-language coverage, scored down only for the second-person voice penalty.

Dimension	Reasoning	Score
Specificity	The description lists many concrete actions ('creating slide decks, pitch decks... reading, parsing, or extracting text... editing, modifying, or updating... combining or splitting slide files; working with templates, layouts, speaker notes, or comments'), which would normally score 3, but the rubric penalizes second-person voice ('Use this skill...', 'use this skill') by reducing specificity by 1.	2 / 3
Completeness	It clearly answers both 'what' (the enumerated capability list) and 'when' with explicit triggers ('Trigger whenever the user mentions...', 'Use this skill any time...', 'If a .pptx file needs to be opened, created, or touched, use this skill').	3 / 3
Trigger Term Quality	Natural user-facing terms are well covered: 'deck,' 'slides,' 'presentation,' and '.pptx filename,' matching the anchor for good coverage of terms users would actually say.	3 / 3
Distinctiveness Conflict Risk	The scope is narrowly scoped to .pptx files with distinct, file-type-specific triggers, making it unlikely to fire for the wrong skill.	3 / 3
	Total	11 / 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: eigent-ai/eigent
Path: resources/example-skills/pptx/SKILL.md
Commit: 9d0a169

Reviewed: about 11 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.