pptx

Read, create, or edit PowerPoint .pptx decks — build slides from an outline, extract slide text/speaker notes, edit shapes/tables/charts, replace images, or export to PDF/images. Use whenever a .pptx (or .ppt) file is an input or output, or the user mentions a deck, slides, or a presentation.

Quality

98%

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

Quality

Content

96%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.

A strong, information-dense skill body: every code block is executable, workflows carry explicit validation and re-check loops, and there is no padding or re-teaching of known concepts. The only structural note is that the ~250-line monolith (particularly the Advanced OOXML section) could be split into a reference file rather than inlined in SKILL.md.

Suggestions

Move the 'Advanced: raw OOXML' section (package map, content-type/relationship invariants, zip-surgery example) into a references/ file and link to it one level deep, keeping SKILL.md as a lean overview.

Consider extracting the LibreOffice export and .ppt conversion snippets into a reference file as well, since they are optional paths rather than core workflow.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational throughout — one-line mental model, EMU unit note, no tutorials on what PowerPoint or python-pptx is, and every section carries instructions Claude doesn't already know (e.g. "never hand-write bullet glyphs", "zip members can't be overwritten in place"). Nothing can be trimmed without losing operational value, so it fits the 'lean and efficient' anchor.	5 / 5
Actionability	All snippets are executable and copy-paste ready: the slide/text/notes dump loop, outline build, run-level templated-text edit, image part blob swap via `r:embed`, table/chart creation, soffice availability-checked export, and the zip-rebuild surgery example. Concrete API calls and pitfalls cover the common cases, matching the top anchor.	5 / 5
Workflow Clarity	Sequences are explicit with validation checkpoints and feedback loops: "Verify before done" (reopen output, assert slide count/key text, check for leftover placeholder text), "Re-run conversion after every edit — the PDF won't reflect a changed .pptx", and "assume there are overlap/overflow/contrast bugs and fix them before declaring done". It also includes honest-fallback handling (say visual inspection was unavailable rather than claiming it).	5 / 5
Progressive Disclosure	Sections are well-organized with clear headers and the raw-OOXML material is explicitly signaled as a last resort, so navigation is easy. However, the body is ~250 lines with no bundle files at all — the Advanced OOXML package-map and invariants material is the kind of deep reference content that could live in a separate reference file, so it fits 'good structure with minor organization gaps' rather than the fully split top anchor.	4 / 5
	Total	19 / 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.

An exemplary description: concrete enumerated capabilities, both file extensions, natural trigger synonyms, and an explicit 'Use whenever' clause covering input, output, and user-mention cases. It is concise (three lines) while remaining fully specific and clearly distinct from related office-document skills.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "build slides from an outline, extract slide text/speaker notes, edit shapes/tables/charts, replace images, or export to PDF/images" — with comprehensive coverage of the skill's operations. It matches the top anchor (multiple specific concrete actions) and has no coverage gaps that would warrant a 4.	5 / 5
Completeness	It explicitly answers what ("Read, create, or edit PowerPoint .pptx decks" with enumerated operations) and when ("Use whenever a .pptx (or .ppt) file is an input or output, or the user mentions a deck, slides, or a presentation") with concrete trigger phrases. Both halves are explicit, matching the top anchor.	5 / 5
Trigger Term Quality	It includes natural terms and synonyms users would say — "PowerPoint", "deck", "slides", "presentation" — plus both file extensions ".pptx" and ".ppt". This matches the anchor for comprehensive coverage including synonyms and file extensions.	5 / 5
Distinctiveness Conflict Risk	The PowerPoint/presentation niche is clear and the triggers (deck, slides, .pptx, .ppt) are distinct from adjacent document/PDF skills, giving minimal conflict risk. It does not use generic language that would overlap other skills, so it fits the top anchor rather than the 'minor overlap risk' anchor at 4.	5 / 5
	Total	20 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: HKUDS/DeepTutor
Path: deeptutor/skills/builtin/pptx/SKILL.md
Commit: ef2d9e5

Reviewed: 5 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.