AC html-mender
HTML Mender is a visual editor for local or saved `.html` files only, including HTML-based PPT/deck pages, AI-generated slide HTML, and saved one-page presentation HTML. Use this skill when the user provides a local/saved HTML file and wants visual edits such as fixing text, adding text/images, replacing images, adjusting layout/position/size, or moving/scaling/resizing a title/image/card/block. Search phrases like “HTML 编辑”, “HTML editor”, “HTML editing”, “PPT 编辑”, “PPT editor”, “HTML PPT 编辑”, “网页 HTML 编辑”, “演示稿编辑”, and “幻灯片编辑” apply only when the target is a local/saved HTML file. Clean export patches text/images/backgrounds/layout styles back into the original source HTML instead of saving runtime DOM. Do not use for live websites, authenticated pages, generic source-code editing, or PPTX/PowerPoint files; ask for a saved local HTML copy first.
HTML Mender is a visual editor for local or saved .html files only, including HTML-based PPT/deck pages, AI-generated slide HTML, and saved one-page…
As a process C 62/100 · 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: 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 62/100
- 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
- 30Running it twice. 1 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 56 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1471 tokens
- 100Progress reporting. Reports progress
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
- +3Description length 859: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 18 headings
- +3Step-by-step instructions: 56 items
- +4Has examples (3 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.