agentsclimarketplace

Causal audit

Skill cdeust/zetetic-team-subagents/skills/causal-audit

11 problem-shaped skills backed by 97 sourced reasoning patterns — Curie to Toulmin, as Claude Code agents. Every claim cites its source; a pre-commit gate blocks unsourced constants. Install the gates alone in 30s (zetetic-gates). The only agent system where "I don't know" is a feature.

Install
npx -y skills add cdeust/zetetic-team-subagents --skill causal-audit

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 7 stars7 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

Correlation walked in; make it prove causation. Use when someone claims "X causes Y" from observational data, asks "did the change actually cause the improvement?", "is this confounded?", "what would have happened if we hadn't shipped it?", plans an A/B test, or investigates why an incident/outbreak spread the way it did.

SKILL.md

2.7 KB, as published. Nobody here has run it

Causal Audit

Problem shape: a causal claim is being made, tested, or acted on, and the evidence is correlational, confounded, unreplicated, or resisted by the organization even when clean. The move: make the causal structure explicit, then intervene or design the comparison that could refute it.

Relevant geniuses

AgentUse when
pearl"X causes Y" claimed from correlation; counterfactual questions; controlled-for variables may be colliders — draw the DAG first
fisheran experiment is being designed: randomize, block, replicate, factorial over one-at-a-time; "run it and see" needs a design document
peircesurprising observation needs candidate explanations; several hypotheses and a limited budget — test cheapest-to-refute first
semmelweismatched groups with wildly different outcomes; the evidence is clear but the institution resists it
snowsomething is spreading (bug, outage class, behavior) — outbreak investigation, case definitions, Hill's criteria
millonly a handful of cases exist — methods of agreement/difference, necessary vs sufficient conditions
feinsteindiagnosis under uncertainty: differential ranked by likelihood ratios, treatment thresholds before acting

Invocation

  1. Pick the best-fit agent above. If two or more fit, run tools/genius-invoker.sh route "<problem>" and take the top ranked match.
  2. Load it: tools/genius-invoker.sh invoke <agent> "<problem>", then read agents/genius/<agent>.md in full.
  3. Apply the agent's <workflow> step by step and answer in its <output-format>. State explicitly which rung of the ladder (association / intervention / counterfactual) the final claim sits on.
  4. Typical chain: pearl classifies the claim → fisher designs the intervention → semmelweis plans the communication. Run via tools/genius-invoker.sh compose pearl fisher -- "<problem>".
  5. If no shape above matches, use a standard team agent instead.

Refuse when

  • The requester wants a causal conclusion from data that can only support association — name the missing intervention instead.
  • No falsifiable version of the claim can be stated.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.