BD numbers-in-narrative
Writes quantities into prose so they land without overstating what the source supports. Applies a per-paragraph number-landing checklist (three numbers per paragraph, one per sentence, direction before magnitude, a comparison on the same screen), a unit-and-denominator lock that catches denominator drift, quantitative fidelity refusals (precision ceiling, rounding drift, percent vs percentage point, model output vs measurement), an uncertainty routing table, a declared likelihood-and-confidence ladder, and a chart-beat contract for exhibits that carry a claim. Use when drafting or editing prose that carries figures, statistics, benchmarks, forecasts or estimates, when a passage reads as a stat wall, when deciding how much precision or hedging a number can bear, or when the user mentions numbers in prose, rounding, denominator, per capita, percentage points, error bars, confidence, uncertainty, chart title, caption, or stat wall.
Writes quantities into prose so they land without overstating what the source supports.
As a process D 47/100 · Unfinished process — References files that are not bundled: ../narrative-evidence-ledger/resources/frame-lock.md
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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../narrative-evidence-ledger/resources/frame-lock.md
Process rating: all ten parameters 47/100
- 0Tools and files. 1 referenced file(s) missing: ../narrative-evidence-ledger/resources/frame-lock.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4670 tokens
- 100Steps. 51 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- 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
- +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 942: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 10 headings
- +3Step-by-step instructions: 51 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.