pptx-official

Use this skill whenever a Microsoft PowerPoint (.pptx) file is being produced, opened, transformed, or read. That includes: authoring slide decks, pitch decks, executive readouts, training material, or any presentation deliverable; extracting text or structure from an existing .pptx; filling a .pptx template with values; converting a deck to PDF or images; splitting or merging decks; inspecting slides, layouts, masters, tables, images, charts, speaker notes, or comments. Trigger on words like 'deck', 'slides', 'presentation', 'pitch deck', 'keynote' (when a .pptx is expected as output), or any filename ending in .pptx. Do NOT trigger when the primary deliverable is a Word document, spreadsheet, PDF report, HTML site, or Google Slides API call, even if presentation-shaped content appears along the way.

Quality

92%

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

85%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 highly actionable, well-sequenced body with strong validation feedback loops and copy-paste code. The main weakness is progressive disclosure: the skill repeatedly points to create.md/edit.md/read.md for detailed recipes, but those files are absent from the bundle, leaving the navigation partially broken and forcing detail into the overview.

Suggestions

Add the missing create.md, edit.md, and read.md files to the bundle (or to a references/ dir) so the decision matrix and 'Where each detail lives' links resolve, moving the inlined recipes out of the SKILL.md overview.

Once detail files exist, trim the overview (e.g. the live-preview setup and image-sourcing L1-L4 exposition) so SKILL.md stays a lean index pointing one level deep.

Keep the existing QA checklist and explode/edit/assemble validation flow as the model — those are the strongest parts and should stay inline.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient — decision matrix, tables, and copy-paste code earn their tokens — but the live-preview and image-sourcing sections run long with guidance that could be trimmed without losing clarity, leaving minor over-explanation.	4 / 5
Actionability	Provides fully executable, copy-paste-ready commands (`uv run scripts/...`) and complete code (e.g. the `download_image` function with headers, the QA grep) covering the common cases directly.	5 / 5
Workflow Clarity	Multi-step flows are clearly sequenced (read → plan → edit/create → validate → visual QA; explode → edit XML → assemble) with explicit validation checkpoints (`diagnose.py`, the QA checklist) and a feedback loop ('If any of these fail, fix and re-run') covering destructive/batch operations like prune.	5 / 5
Progressive Disclosure	Structure and signaling are clear (decision matrix, 'Where each detail lives'), but the three referenced detail files — create.md, edit.md, read.md — do not exist anywhere in the bundle (only scripts/ is present), so the one-level-deep references point at missing content and much detail is inlined in a ~560-line overview.	3 / 5
	Total	17 / 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.

A strong, specific description that crisply states what the skill does and exactly when to invoke it, with explicit negative triggers to avoid misfires. No meaningful gaps; the only minor nit is the imperative 'Use this skill whenever' voice, which matches the rubric's own good examples and warrants no penalty.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the full lifecycle — authoring decks, extracting text/structure, filling templates, converting to PDF/images, splitting/merging, and inspecting slides/layouts/masters/tables/images/charts/notes/comments — giving comprehensive coverage rather than vague verbs.	5 / 5
Completeness	Clearly answers 'what' (the enumerated capabilities) and 'when' (an explicit 'Trigger on...' clause and a 'Do NOT trigger when...' boundary), both stated concretely.	5 / 5
Trigger Term Quality	Explicitly enumerates natural user terms ('deck', 'slides', 'presentation', 'pitch deck', 'keynote') plus the .pptx file extension, covering synonyms and extension-based triggers a user would actually say.	5 / 5
Distinctiveness Conflict Risk	The .pptx niche is tightly scoped and the 'Do NOT trigger' exclusion of Word docs, spreadsheets, PDF reports, HTML, and Google Slides minimizes overlap with adjacent skills.	5 / 5
	Total	20 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (560 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 8 missing	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	13 / 16 Passed

Repository: XiaomiMiMo/MiMo-Code
Path: packages/opencode/src/skill/builtin/.bundle/pptx-official/SKILL.md
Commit: ec3f989

Reviewed: ~20 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.