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

Low

Low-risk findings worth noting

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.

A highly actionable body with strong QA workflow and validation loops, held back by an oversized inline design-reference section and two broken file references (editing.md, pptxgenjs.md) plus a dead scripts/office symlink. Tightening the inline reference tables and restoring the missing referenced files would raise both conciseness and progressive disclosure.

Suggestions

Restore or create the referenced files editing.md and pptxgenjs.md (and fix the scripts/office symlink to a real _shared/office directory) so the well-signaled one-level references actually resolve.

Move the 10-row color palette table and 8-row font-pairing table into a separate references file (e.g. design.md) and keep SKILL.md as a lean overview, tightening the inline 'Avoid'/'Don't' lists where items overlap.

Add a one-line note in the Editing Workflow that unpack/pack rely on scripts/office, and confirm those scripts are present, so the brief 'Unpack → … → pack' step is traceable to working tooling.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of concepts Claude already knows, but the 10-row color palette table, 8-row font-pairing table, and layered 'Avoid'/'Don't' lists are generous inline reference material that could be tightened or moved to a reference file. It is not a 3 because not every token earns its place, and not a 1 because it never pads with general explanations.	2 / 3
Actionability	Provides fully executable commands ('python -m markitdown presentation.pptx', 'soffice --headless --convert-to pdf output.pptx', 'pdftoppm -jpeg -r 150 output.pdf slide') plus concrete pt sizes, hex codes, margins, and a copy-paste QA subagent prompt — copy-paste ready, matching the score-3 anchor.	3 / 3
Workflow Clarity	The QA Verification Loop is a clear sequence with explicit validation checkpoints — 'List issues found', 'Re-verify affected slides', 'Do not declare success until you've completed at least one fix-and-verify cycle', plus the grep placeholder check before success — so it is not capped at 2 despite involving batch/destructive-style operations.	3 / 3
Progressive Disclosure	References are well-signaled and one level deep ('Read [editing.md](editing.md)', 'Read [pptxgenjs.md](pptxgenjs.md)'), but those referenced files do not exist in the bundle and 'scripts/office' is a broken symlink, so the navigation points nowhere; per the guideline to score against the actual bundle structure, broken referenced paths cap this at 2 rather than 3.	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, specific description with explicit trigger guidance and comprehensive concrete actions tightly scoped to .pptx work. It cleanly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Lists multiple specific 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 score-3 anchor; the imperative 'Use this skill…' mirrors the rubric's own good examples ('Use when…') rather than the penalized 'You can use this'/'I can help', so no voice penalty applies.	3 / 3
Completeness	Explicitly answers both what (create/read/edit/combine/templates/notes/comments) and when ('Trigger whenever the user mentions deck, slides, presentation, or references a .pptx filename'), with an explicit 'Use when'-style trigger clause, so it is not capped at 2.	3 / 3
Trigger Term Quality	'Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename' gives good coverage of natural terms a user would actually say, matching the score-3 anchor; it is not merely technical jargon.	3 / 3
Distinctiveness Conflict Risk	Scoped narrowly to .pptx files with distinct triggers ('deck,' 'slides,' 'presentation,' '.pptx filename'), giving it a clear niche 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: 1 missing, 1 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: nextlevelbuilder/goclaw
Path: skills/pptx/SKILL.md
Commit: 31f9734

Reviewed: 10 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.