BC narrative-evidence-ledger
Builds the evidence ledger that narrative work is allowed to be built on, before any structure is chosen. Locks the frame (unit, denominator, window, population boundary), atomizes material into findings with evidence classes A-F and re-findable pointers, triages every causal claim L1 MECHANISM to L5 CONJECTURE with permitted and banned verb sets, runs one-way promotion from finding to claim to beat, and keeps a DEAD column of everything a veto killed. Use before outlining or drafting any evidence-based narrative, when auditing whether a draft's claims are actually sourced, when a piece needs a provenance layer for handoff, or when user mentions evidence ledger, claim ledger, provenance, sourcing, causal grading, denominator lock, cherry-picking, or circular citation.
Builds the evidence ledger that narrative work is allowed to be built on, before any structure is chosen.
As a process C 51/100 · Has gaps — 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: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5094 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 51/100
- 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
- 30Running it twice. 10 mutating operations with no state check
- 70Execution cost. Instruction body is 5094 tokens
- 100Tools and files. No external tools needed
- 100Steps. 49 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 778: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 49 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.