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".
65
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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. It includes specific actions and natural trigger terms. The only minor weakness is potential overlap with other presentation-related skills, where the distinction of generating images (rather than editable presentation files) could be made more explicit.
| 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 | While it specifies slide deck *images* which is somewhat distinctive, it could overlap with a presentation editing skill (like the .pptx example in the rubric). The distinction between generating slide images vs. creating/editing .pptx files could be clearer. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
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 comprehensive, well-structured skill with excellent workflow clarity, strong actionability, and good progressive disclosure to supporting reference files. Its primary weakness is significant verbosity — the backend resolution logic, confirmation policy, preference management, and tool selection rules are over-specified for Claude's capabilities, consuming far more tokens than necessary. The content could likely be cut by 40-50% without losing any actionable information.
Suggestions
Dramatically condense the 'Image Generation Tools' section — the 4-step priority cascade with sub-bullets and edge cases could be a simple ordered list of 4 lines plus one constraint line about no SVG/HTML fallback.
Compress the 'Confirmation Policy', 'User Input Tools', and 'Changing Preferences' sections — Claude doesn't need detailed explanations of when to batch questions or how AskUserQuestion works; a brief rule statement suffices.
Remove explanatory rationale sentences (e.g., 'The file is the reproducibility record and lets you switch backends without regenerating prompts') — Claude can infer purpose from the instruction itself.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines. It over-explains tool resolution logic, backend selection cascades, confirmation policies, and preference management in exhaustive detail. Much of this (e.g., how to resolve bun vs npx, XDG config paths, detailed backend priority rules) could be dramatically condensed. The image generation tools section alone is a wall of text covering edge cases Claude could handle with briefer guidance. | 1 / 3 |
Actionability | The skill provides highly concrete, actionable guidance: specific file paths, exact CLI commands for merging, precise YAML frontmatter examples, detailed step-by-step workflows with numbered substeps, exact option flags, and clear file naming conventions. The checklist format and table-driven specifications make it copy-paste ready. | 3 / 3 |
Workflow Clarity | The 9-step workflow is clearly sequenced with a checklist, explicit hard gates (Step 2 confirmation is marked as REQUIRED), conditional branching (skip flags, outline-only/prompts-only stops), validation checkpoints (Step 1.3 checks existing output, Step 4/6 review gates), error recovery (auto-retry on image failure), and a backup rule for destructive overwrites. Feedback loops are well-defined. | 3 / 3 |
Progressive Disclosure | The skill maintains a clear overview structure with well-signaled one-level-deep references to 15+ supporting files (styles, dimensions, confirmation copy, analysis framework, etc.) organized in a references table. Inline content covers what's needed for the overview while deferring detailed specs to dedicated files. Navigation is straightforward. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
72%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
bd5745f
- Reviewed
Table of Contents
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.