baoyu-slide-deck

Generates professional slide deck images from content. Creates outlines with style instructions, then generates individual slide images. Use when user asks to "create slides", "make a presentation", "generate deck", "slide deck", or "PPT".

Quality

81%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

70%

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

This is a highly actionable and well-structured skill with excellent workflow clarity and progressive disclosure. Its primary weakness is extreme verbosity — the image backend resolution logic alone spans ~30 lines with multiple sub-cases, and the confirmation policy, batch generation policy, and preference management sections add significant token overhead that could be condensed substantially without losing clarity. The skill would benefit greatly from aggressive trimming of explanatory prose and consolidation of policy sections.

Suggestions

Condense the 'Image Generation Tools' section from ~30 lines to ~10 by moving the detailed resolution logic (codex-imagegen invocation, fallback chains) into a reference file and keeping only the priority summary inline.

Move the 'Batch Generation Policy', 'Confirmation Policy', and 'Changing Preferences' sections into reference files, leaving only 1-2 sentence summaries in the main SKILL.md.

Remove explanations of obvious concepts like what a slug is ('2-4 words, kebab-case, extracted from topic') and what backup means — Claude knows these.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~400+ lines. It over-explains backend resolution logic, batch generation policies, confirmation policies, and preference management in exhaustive detail. Much of this (e.g., how to resolve which image backend to use across 4 priority levels with sub-bullets) could be drastically condensed. It also explains concepts Claude can infer (e.g., what a slug is, what kebab-case means, what a backup is).	1 / 3
Actionability	The skill provides highly concrete, executable guidance: specific CLI commands for merging, exact file paths, precise YAML frontmatter examples, detailed option flags, and copy-paste-ready workflow checklists. Every step has specific actions rather than vague descriptions.	3 / 3
Workflow Clarity	The 9-step workflow is clearly sequenced with explicit checkpoints (Step 2 is a hard gate, Step 4/6 are conditional reviews), validation steps (verify prompt files exist before generation, check existing output before confirmation), error recovery (retry failed items once), and a checklist format. Feedback loops are present for outline and prompt review cycles.	3 / 3
Progressive Disclosure	The skill has excellent progressive disclosure with a clear overview in SKILL.md and well-signaled one-level-deep references to 15+ supporting files (styles, dimensions, confirmation copy, analysis framework, etc.). The references table at the bottom provides clean navigation. Content is appropriately split — verbatim confirmation copy and per-preset specs live in reference files rather than inline.	3 / 3
	Total	10 / 12 Passed

Description

92%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong description that clearly communicates what the skill does and when to use it, with good natural trigger terms. The main weakness is potential overlap with other presentation-related skills, as terms like 'PPT' and 'make a presentation' could apply to traditional PowerPoint creation tools. The distinction that this skill generates slide *images* rather than editable files could be made more explicit to reduce conflict risk.

Suggestions

Clarify the distinction from traditional presentation tools by emphasizing that this generates slide images (not editable .pptx files), e.g., 'Generates slide deck as images (not editable PowerPoint files)' to reduce conflict with .pptx-based skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: generates slide deck images, creates outlines with style instructions, generates individual slide images. These are specific, actionable capabilities.	3 / 3
Completeness	Clearly answers both 'what' (generates professional slide deck images, creates outlines with style instructions, generates individual slide images) and 'when' (explicit 'Use when' clause with specific trigger phrases).	3 / 3
Trigger Term Quality	Includes excellent natural trigger terms users would actually say: 'create slides', 'make a presentation', 'generate deck', 'slide deck', 'PPT'. Good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Could potentially overlap with a presentation editing/creation skill that works with .pptx files. The description focuses on image-based slides which is somewhat distinct, but 'make a presentation' and 'PPT' could conflict with a traditional PowerPoint skill.	2 / 3
	Total	11 / 12 Passed

Validation

72%

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 — 8 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	8 / 11 Passed

Repository: jimliu/baoyu-skills
Commit: ce84174

Reviewed: 4 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.