pptx

Use this skill any time a .pptx or .potx 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 or .potx 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 (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.

Quality

96%

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

92%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, well-sequenced skill body with strong validation feedback loops and minimal filler. Its main weakness is progressive disclosure: nearly all documentation lives inline in one large SKILL.md with no reference files to offload the design/QA detail.

Suggestions

Move the Design Ideas section (color palettes, typography, spacing, avoid list) into a references/ file such as references/design.md, leaving a short pointer plus the most critical rules (e.g. no accent stripes, safe-font QA list) inline in SKILL.md.

Extract the detailed QA and Converting-to-Images procedures into references/qa.md, keeping only a compact QA checklist with the key commands in SKILL.md so the overview stays scannable.

If splitting files, ensure each reference is one level deep with clearly signaled links (e.g. "See [design.md](references/design.md) for palettes and typography") so navigation stays direct.

Dimension	Reasoning	Score
Conciseness	Dense and operational throughout — footguns, exact commands, and validate.py usage with almost no concept explanation Claude already knows (the single "A .pptx is a ZIP archive of XML files" line is justified context); the sizable Design Ideas section is the one area that could be trimmed but stays concrete and skill-specific rather than padded.	3 / 3
Actionability	Copy-paste-ready throughout: a scripts table with exact invocations, an executable bash block for the unzip→edit→zip→validate flow, concrete pptxgenjs options, and exact PDF/image conversion commands — fully executable, not pseudocode.	3 / 3
Workflow Clarity	Multi-step flows are explicitly sequenced with validation checkpoints — "Do all structural work... before editing any slide's content," validate.py after writeFile/packing, markitdown+grep content QA with "fix them before declaring success," and visual QA with "rerun all four commands" feedback loops for these destructive XML operations.	3 / 3
Progressive Disclosure	The bundle scripts are well-listed and referenced one level deep (thumbnail.py, add_slide.py, clean.py, validate.py, soffice.py all exist), but SKILL.md itself is a ~236-line monolithic manual — Design Ideas, typography, and detailed QA guidance that could live in separate reference files are all inline rather than split out, fitting the "content that should be separate is inline" anchor rather than the "content appropriately split" one.	2 / 3
	Total	11 / 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 that clearly states both capabilities and explicit trigger conditions with natural user vocabulary. Its only minor gap is omitting "PowerPoint" as a trigger term, which many users say.

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 (.potx), layouts, speaker notes, or comments" — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly answers both what (the enumerated actions) and when — "Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx or .potx filename" and "If a .pptx or .potx file needs to be opened, created, or touched, use this skill," satisfying the explicit-trigger anchor.	3 / 3
Trigger Term Quality	Covers natural terms users say — "deck," "slides," "presentation," and explicit ".pptx" / ".potx" filename references — giving good coverage; the one notable omission is the word "PowerPoint" itself, but the listed terms still meet the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	Scoped tightly to .pptx/.potx files with format-specific triggers, giving it a clear niche unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 9 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: K-Dense-AI/claude-scientific-writer
Path: .claude/skills/document-skills/pptx/SKILL.md
Commit: 43aaecd

Reviewed: 18 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.