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".
88
77%
Does it follow best practices?
Impact
98%
1.25xAverage score across 6 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/baoyu-slide-deck/SKILL.mdQuality
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 skill description that clearly communicates what the skill does and when to use it. It includes specific actions and natural trigger terms. The main weakness is potential overlap with other presentation-related skills, as the distinction between image-based slide generation and traditional presentation creation could be clearer.
Suggestions
Clarify the distinction from traditional .pptx presentation skills by emphasizing the image-generation approach more explicitly, e.g., 'Generates slide images using AI image generation rather than creating editable .pptx files.'
| 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 rather than generating images. The image-based approach is somewhat distinctive but the trigger terms like 'make a presentation' and 'PPT' could conflict with a traditional presentation tool skill. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill excels in actionability and workflow clarity, providing an extremely detailed and well-sequenced multi-step process with proper validation checkpoints, conditional branching, and error recovery. However, it suffers significantly from verbosity — inlining extensive style tables, confirmation dialog schemas, and dimension details that belong in reference files. The progressive disclosure structure exists (references table at bottom) but is undermined by duplicating much of that content inline.
Suggestions
Move the style presets table, auto style selection mapping, and dimension options to reference files (e.g., references/dimensions/presets.md) and replace with brief summaries and links — this alone would cut ~100 lines.
Move the detailed AskUserQuestion schemas for Steps 2, 4, and 6 into a reference file (e.g., references/confirmation-dialogs.md) and keep only a brief description of what each confirmation round covers in the main workflow.
Consolidate the inline content signal → preset mapping table into the existing references/dimensions/presets.md file, keeping only a one-line note like 'Auto-select style based on content signals (see references/dimensions/presets.md)'.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~500+ lines. It includes exhaustive tables for style presets, auto-selection mappings, full AskUserQuestion schemas for every confirmation round, and detailed dimension options that could easily live in reference files. Much of this content (style preset tables, dimension options, content signal mappings) belongs in the referenced files rather than inline. | 1 / 3 |
Actionability | The skill provides highly concrete, executable guidance throughout: specific bash commands, exact file paths, precise AskUserQuestion schemas with labels and descriptions, clear file naming conventions, and copy-paste ready command examples. Every step has specific instructions rather than vague directions. | 3 / 3 |
Workflow Clarity | The workflow is exceptionally well-structured with a numbered checklist, clear step sequencing, explicit conditional logic (skip/proceed flags), validation checkpoints (Step 2 confirmation marked as REQUIRED, Step 1.3 existing content check marked as REQUIRED), backup rules before destructive operations, and feedback loops (edit → regenerate cycles in Steps 4 and 6). | 3 / 3 |
Progressive Disclosure | The skill has a clear references table pointing to external files, which is good. However, it inlines massive amounts of content that should live in those reference files — the full style presets table, auto style selection table, all AskUserQuestion schemas, and custom dimension options. The SKILL.md should be an overview pointing to these details, not containing them all inline. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
63%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 7 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (715 lines); consider splitting into references/ and linking | Warning |
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 | 7 / 11 Passed | |
- Repository
- jimliu/baoyu-skills
- Commit
9eb032a
- 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.