Z1 evidence stress test
Skill thepraggyverse/zeroone-foundry/skills/z1-evidence-stress-test
80 source-grounded operating skills for zero-to-one strategy, technology, teams, distribution, and progress.
npx -y skills add thepraggyverse/zeroone-foundry --skill z1-evidence-stress-testAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 22 days oldThe repository was created 22 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Separate fact, inference, framing, incentives, and competing explanations for contentious claims. Use when the user asks about evidence stress test, separate fact from framing. Prompts like "Analyze why nuclear innovation stalled without forcing one cause." also trigger. Do not use for finding a contrarian thesis (use `z1-contrarian-question`) when claims are not contentious.
SKILL.md
2.2 KB, as published. Nobody here has run it
Evidence Stress Test
Separate fact, inference, framing, incentives, and competing explanations for contentious claims.
- State decision, object, time horizon, and constraints; separate facts from assumptions.
- Apply every relevant source-grounded check below; mark non-applicable checks explicitly.
- Seek a counterexample, failure mode, and competing explanation.
- Return the output table and one concrete next action; label claims as source doctrine, plugin synthesis, inference, current evidence, or speculation.
Source-grounded checks
- overdetermined causation — Generate multiple sufficient causes, weigh evidence, and avoid a single-cause story.
- alternate hypothesis stress test — Construct competing explanations, list predictions, and label confidence rather than escalating speculation.
- source trust decoder — Read a biased source by separating facts, framing, omissions, incentives, and independent corroboration.
- belief evidence separation — Separate a plausible story, a supported inference, and confirmed evidence.
- formalization kills agency — Test whether bureaucratic formalization made a once-agentic institution legible but ineffective.
Output
decision, evidence, source-backed checks, counterargument, risk, recommendation, next action. Confidence: high | medium | low.
Refs: references/source-note.md, references/examples.md.
Stop (fail-closed): do not invent quotations, imply affiliation with source authors/publishers, or expand beyond this skill's checks. Treat the framework as a lens, not law.
Use z1-source-fidelity when attribution labels matter; use z1-quote-safety before exact wording; use z1-router only when the target skill is unclear.