Use when turning presales requirements, meeting notes, or solution materials into editable business capability blueprints, swimlane flows, and application architecture diagrams. Use when generating blueprint JSON, static HTML viewers, or exporting to SVG, draw.io, Excalidraw, or Mermaid formats. When no standard export template applies, default to free-flow output.
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: 73. 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 68/100
0Progress reporting. Says nothing while it works
30Running it twice. 2 mutating operations with no state check
40Consistency. Frontmatter name (kai-business-blueprint) differs from the folder (business-blueprint)
50When it triggers. No condition that starts the skill
60Tools and files. Uses tools (bash, python, node) that frontmatter does not declare
60Result and completion. Output format stated, no completion criterion
70Inputs and preconditions. Inputs and preconditions are listed
100Steps. 55 steps
100Failures and branches. 4 branches, has a failure section
100Execution cost. Instruction body is 3038 tokens
medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
low 12 top-level sections: this looks like several domains in one skill
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)
+1No license
+2Single-language instructions
+3Description length 367: enough signal without eating the budget
+4Structure: 22 headings
+3Step-by-step instructions: 55 items
+3Output format is stated explicitly
+4Has examples (7 code blocks)
+4Reference files are cited in the instructions (3 of 15)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.
External checks
ClawHub: suspicious
The skill is mostly a local business-blueprint and diagram generator, but it has under-disclosed local persistence of invocation details and mismatched sensitive capability metadata that deserve review before installation.
LLM: suspicious (medium) · VirusTotal: · 29 May 2026