# Causal Audit

> >

- **Type:** Skill
- **Install:** `agentstack add skill-cdeust-zetetic-team-subagents-causal-audit`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [cdeust](https://agentstack.voostack.com/s/cdeust)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [cdeust](https://github.com/cdeust)
- **Source:** https://github.com/cdeust/zetetic-team-subagents/tree/main/skills/causal-audit
- **Website:** https://ai-architect.tools

## Install

```sh
agentstack add skill-cdeust-zetetic-team-subagents-causal-audit
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# 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

| Agent | Use when |
|---|---|
| [pearl](../../agents/genius/pearl.md) | "X causes Y" claimed from correlation; counterfactual questions; controlled-for variables may be colliders — draw the DAG first |
| [fisher](../../agents/genius/fisher.md) | an experiment is being designed: randomize, block, replicate, factorial over one-at-a-time; "run it and see" needs a design document |
| [peirce](../../agents/genius/peirce.md) | surprising observation needs candidate explanations; several hypotheses and a limited budget — test cheapest-to-refute first |
| [semmelweis](../../agents/genius/semmelweis.md) | matched groups with wildly different outcomes; the evidence is clear but the institution resists it |
| [snow](../../agents/genius/snow.md) | something is spreading (bug, outage class, behavior) — outbreak investigation, case definitions, Hill's criteria |
| [mill](../../agents/genius/mill.md) | only a handful of cases exist — methods of agreement/difference, necessary vs sufficient conditions |
| [feinstein](../../agents/genius/feinstein.md) | diagnosis 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 ""` and take the top ranked match.
2. Load it: `tools/genius-invoker.sh invoke  ""`, then read
   `agents/genius/.md` in full.
3. Apply the agent's `` step by step and answer in its
   ``. 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 -- ""`.
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.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [cdeust](https://github.com/cdeust)
- **Source:** [cdeust/zetetic-team-subagents](https://github.com/cdeust/zetetic-team-subagents)
- **License:** MIT
- **Homepage:** https://ai-architect.tools

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-cdeust-zetetic-team-subagents-causal-audit
- Seller: https://agentstack.voostack.com/s/cdeust
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.