BD narrative-arc-mapping
Maps researched evidence onto Truby's twenty-two structural steps without fabricating the steps the evidence cannot fill. Runs the designing-principle discrimination test, step-fit triage (PRESENT / ABSENT / NOT APPLICABLE), per-slot warrant cards, the empty-slot decision table, the moral-argument spine, and the revelation-intensity audit, then stops at a tagged scene weave. Use when architecting a long-form nonfiction piece from a research corpus, structuring a post-mortem, market history, biography, or science writeup, or when user mentions Truby, 22 steps, designing principle, moral argument, revelation sequence, scene weave, or step-fit triage.
Maps researched evidence onto Truby's twenty-two structural steps without fabricating the steps the evidence cannot fill.
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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: 5. 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 46/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 4525 tokens
- 100Steps. 52 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
- high The skill tells the model to perform an irreversible action with no human approval
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
- +1No license
- +2Single-language instructions
- +3Description length 656: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 52 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.