This is a strong, well-crafted skill description that thoroughly covers capabilities, trigger conditions, and edge cases (e.g., extracting content from .pptx for use elsewhere). It uses third person voice appropriately and provides comprehensive natural language triggers. The only minor note is that it uses second person 'Use this skill' framing at the start, but this is directed at Claude as the agent selecting skills, which is acceptable and consistent with the good examples in the rubric.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: creating slide decks/pitch decks/presentations, reading/parsing/extracting text, editing/modifying/updating, combining/splitting slide files, working with templates/layouts/speaker notes/comments.	3 / 3
Completeness	Clearly answers both 'what' (creating, reading, parsing, editing, combining presentations) and 'when' with explicit triggers ('Trigger whenever the user mentions deck, slides, presentation, or references a .pptx filename'). The entire description is essentially a detailed 'Use when...' clause.	3 / 3
Trigger Term Quality	Excellent coverage of natural terms users would say: 'deck,' 'slides,' 'presentation,' '.pptx,' 'pitch decks,' 'speaker notes,' 'templates,' and even covers the scenario of referencing a .pptx filename. These are all terms users would naturally use.	3 / 3
Distinctiveness Conflict Risk	Very clearly scoped to .pptx files specifically, with distinct triggers like 'deck,' 'slides,' 'presentation,' and '.pptx.' Unlikely to conflict with other skills since it's anchored to a specific file format and domain.	3 / 3
	Total	12 / 12 Passed

Implementation

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-structured, highly actionable skill with excellent workflow clarity, particularly in its QA verification loop with explicit feedback cycles and subagent delegation. The main weakness is the lengthy inline Design Ideas section, which inflates the token cost and would be better served as a separate referenced file. The quick reference table and progressive disclosure to editing.md and pptxgenjs.md are effective patterns.

Suggestions

Move the Design Ideas section (color palettes, typography, spacing, common mistakes) to a separate file like design-guide.md and reference it with a one-line summary, reducing the main skill by ~80 lines.

Trim the Design Ideas intro text — phrases like 'Plain bullets on a white background won't impress anyone' and 'The palette should feel designed for THIS topic' explain taste rather than provide actionable instructions Claude needs.

Dimension	Reasoning	Score
Conciseness	The quick reference table and reading/editing sections are lean and efficient. However, the Design Ideas section is quite lengthy with extensive color palettes, typography tables, and layout advice that could be moved to a separate reference file. The QA section is thorough but somewhat verbose with explanations Claude could infer.	2 / 3
Actionability	The skill provides fully executable commands throughout (markitdown, thumbnail.py, unpack.py, soffice.py, pdftoppm), concrete QA prompts for subagents, specific grep patterns for placeholder detection, and precise design specifications (font sizes, margins, color hex codes). Everything is copy-paste ready.	3 / 3
Workflow Clarity	The QA verification loop is exemplary with explicit validation checkpoints, feedback loops (generate → inspect → fix → re-verify), and the strong directive 'Do not declare success until you've completed at least one fix-and-verify cycle.' The editing workflow references a detailed guide while providing a clear high-level sequence. The subagent delegation for visual QA is a well-defined checkpoint.	3 / 3
Progressive Disclosure	The quick reference table effectively routes to editing.md and pptxgenjs.md for detailed workflows. However, the Design Ideas section (~80 lines of color palettes, typography, spacing, and anti-patterns) is inlined when it could be split into a separate design-guide.md reference. The skill would benefit from moving this content out and linking to it.	2 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Reviewed

2 days ago

Table of Contents

Discovery Implementation Validation