CD slide-dsl
The complete slide DSL manual — the canvas and its background, the ten element types field by field with units, defaults and legal values, where each type keeps its words, which field the renderer actually paints when two disagree, exactly what happens to the HTML you put in `content`, and the structure schema that is now the ONLY thing a write is checked against. Nothing filters your markup and nothing normalises your values, so this manual is the whole of what makes a page render correctly. Load it before patching a field you have not patched before, when a patch comes back rejected, when a patch lands but nothing moves on screen, or when you need to know where a colour, a font, a table cell or a code line really lives. This is a field reference and not a procedure — `page-clone` and `pro-editing` decide which pages to touch, `slide-craft` decides what a good page looks like, and this one says what the JSON means.
The complete slide DSL manual — the canvas and its background, the ten element types field by field with units, defaults and legal values, where each type…
As a process D 47/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, execution cost
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 16336 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "title" - note
edit-residuethe text marks something as outdated (lines 593, 594, 595): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 47/100
- 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
- 10Execution cost. Instruction body is 16336 tokens: crowds the task out of the window
- 30Running it twice. 34 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 101 steps
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (12 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)
- +3Description length 929: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 36 headings
- +3Step-by-step instructions: 101 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.