AC slidev-maker
Use this skill when creating, editing, or exporting Slidev presentations — the Markdown + Vue web-based slide framework for developers. Covers installation and CLI commands, slide syntax and frontmatter, layouts, click animations and transitions, code highlighting (Shiki/Monaco/Magic Move), built-in components, diagrams (Mermaid/PlantUML), images/video/fonts, UnoCSS styling, LaTeX, themes, presenter mode, and exporting to PDF/PPTX/PNG. Prevents common mistakes like incorrect asset paths, deprecated features (Prism), and non-existent layouts.
Covers installation and CLI commands, slide syntax and frontmatter, layouts, click animations and transitions, code highlighting (Shiki/Monaco/Magic Move)…
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 17. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 41): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 16 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 668 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 547: enough signal without eating the budget
- +4Structure: 4 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (15 of 15)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.