AB guizang-html-to-pptx
Convert a guizang-ppt-skill magazine HTML deck into a real editable PowerPoint PPTX. Use this skill whenever the user asks to export, convert, or rebuild a guizang/magazine-web-ppt HTML deck, index.html, web PPT, slides, or presentation as .pptx, especially when they say "editable PPTX", "not screenshots", "不要截图", or need PowerPoint-native text, shapes, and images. If the user explicitly selects or mentions this skill with little or no extra instruction, default to exporting the current guizang HTML PPT as a real editable PPTX, not screenshots, with fonts matching the HTML. This is an export-only companion skill for guizang-ppt-skill, originally from https://github.com/op7418/guizang-ppt-skill; it should not replace the original HTML deck generation skill.
As a process B 74/100 · Nearly there — weak spots: result and completion, progress reporting
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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 74/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (python, node) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 52 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2176 tokens
- 100Running it twice. Mutating operations check current state
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 766: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 52 items
- +4Has examples (10 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.