BC term-interrogation
Walks a finished document line by line, finds every word and phrase standing in for a concept, and breaks each one down until a reader with no background can follow it. Targets the assumed-knowledge phrase, the kind that sounds ordinary while hiding everything that matters ("moat", "flywheel", "product-market fit", "at scale"), not merely the rare word. Explains each term where it is used, then re-reads its own explanation and unpacks any new term that explanation introduced, repeating until every word bottoms out in ordinary language. Produces a term ledger recording what was flagged, how it was handled, where each explanation came from, and how many passes it took. Use after drafting any report, explainer or analysis for a non-expert audience, or when asked to explain something from first principles, assume the reader knows nothing, cross-question the jargon, define every term, or make a document readable by a beginner.
Walks a finished document line by line, finds every word and phrase standing in for a concept, and breaks each one down until a reader with no background can…
As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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: 1. 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 55/100
- 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
- 30Running it twice. 5 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Execution cost. Instruction body is 4259 tokens
- 100Steps. 24 steps
- 100Failures and branches. 1 branches, has a failure section
- 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
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)
- +3Description length 935: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +4Structure: 12 headings
- +3Step-by-step instructions: 24 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.