BC narrative-fallacy-guard
Stops a true set of facts from being assembled into a false story. Runs the retrospective slot audit, the outcome-blind rewrite (flip test, separation test), the inevitability audit with its overshoot check, the survivorship graveyard pass, the counterfactual admissibility gate, and the expensive proportion and omission audits. Every check labels and discloses; none deletes. Use when drafting or reviewing history, post-mortems, biography, market or protocol narratives, research writeups, or any account written after the outcome was known, or when user mentions hindsight bias, narrative fallacy, survivorship bias, inevitability, halo effect, outcome bias, just-so story, teleology, or Whig history.
Stops a true set of facts from being assembled into a false story.
As a process C 56/100 · Has gaps — 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: 4. 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 56/100
- 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. 12 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70Execution cost. Instruction body is 4966 tokens
- 100Tools and files. No external tools needed
- 100Steps. 54 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 705: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 54 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.