CD marp-slide-expert
Convert or create Marp slide decks from Markdown sources. Use when working with .marp.md / .md files meant for marp CLI rendering, designing page-level slide layouts (cover, divider, text, tables, multi-column / split layouts), drawing infographics and relation diagrams as inline SVG (staircase, arrow chain, 2x2 matrix, value tree, sankey, funnel, swimlanes, bento grid, icon-rail, card-row, wave-timeline, argument map, pie / radar / balance-wheel charts), splitting long content into slides (15-line per-slide cap), writing speaker notes as invisible HTML comments, preparing image assets, or troubleshooting marp syntax errors and content overflow. Applies to marp / marpit slide format.
Convert or create Marp slide decks from Markdown sources.
As a process D 36/100 · Unfinished process — References files that are not bundled: ..., <path>, <a>
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 43. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ... - warning
missing-refreference to a missing file: <path> - warning
missing-refreference to a missing file: <a> - warning
missing-refreference to a missing file: <b>
Process rating: all ten parameters 36/100
- 0Tools and files. 4 referenced file(s) missing: ..., <path>, <a>
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 70Execution cost. Instruction body is 4709 tokens
- 85Steps. 53 steps, 2 vague phrases
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (6 tags): a typed call is more reliable
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
- -5TODO / placeholder text left in the skill
- -31 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 692: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 53 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.