AB narrative-fallacy
Activate when: user is reading a business case study or founder biography and drawing lessons; a post-mortem produced a neat single root cause; someone says 'the story is too clean' or 'that explanation is too convenient'; a pundit explains a market or political event confidently after it happened; user is building a strategy based on what worked at another company. Do NOT activate when: the causal structure is genuinely well-understood (physics, well-tested medical interventions) and the narrative reflects that; the user needs a narrative for communication purposes and already knows it is a compression. More: deciqai.com/c/narrative-fallacy
Activate when: user is reading a business case study or founder biography and drawing lessons; a post-mortem produced a neat single root cause; someone says…
As a process B 65/100 · Nearly there — weak spots: inputs and preconditions, failures and branches, progress reporting
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 65/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 25 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2067 tokens
- 100Running it twice. No mutating operations
- low 10 top-level sections: this looks like several domains in one skill
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
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 649: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 25 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 95.