CD narrative-form-triage
Decides which narrative form a body of researched material can actually support, before any structure is imposed. Runs a six-question form-triage gate producing STORY NARRATIVE, EXPLANATORY NARRATIVE, MULTI-NODE GATHERING, or DO NOT NARRATE; runs the ABT (And/But/Therefore) spine diagnostic; selects a spine from a thirteen-structure table covering Truby arc, layer cake, pyramid/SCQA, OCAR, PR/FAQ, sparkline, Raskin five-slot, martini glass, drill-down, inverted pyramid and braided/mosaic; and writes an immutable spine contract with a boredom budget. Use before outlining or drafting any long-form nonfiction, report, post-mortem, market history, research writeup or case study, or when user mentions find the narrative, what's the story here, narrative arc, story structure, how should I structure this, does this have a story, or storytelling with data.
Decides which narrative form a body of researched material can actually support, before any structure is imposed.
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5113 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 49/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 8 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (node) that frontmatter does not declare
- 70Execution cost. Instruction body is 5113 tokens
- 100Steps. 58 steps
- 100Consistency. Name and required fields are in place
- 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 860: 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: 58 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.