causal-detective

Challenge causal claims through structured threat assessment, counterfactual reasoning, and CausalPy falsification checks. Use when validating whether a causal effect is real or when the user asks "is this effect real?" or "can I trust this result?"

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

80%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise and well-structured with concrete check names and a clear output pattern, but it offers no executable code examples and its three reference links point to files that are missing from the bundle.

Suggestions

Add the missing referenced files (reference/counterfactual_analysis.md, reference/threat_catalog.md, reference/falsification_tests.md) or remove the References section, since the links currently resolve to nothing.

Include at least one small executable CausalPy snippet (e.g. how to instantiate and run a check) so the guidance is copy-paste ready rather than check-name-only.

Add an explicit verify/retry checkpoint in the workflow (e.g. 'after running the mapped checks, re-score each threat and iterate if new confounders surface') to strengthen the feedback loop.

Dimension	Reasoning	Score
Conciseness	Lean and well-organized with no over-explanation of concepts Claude already knows; every section (workflow, core questions, check table, output pattern) earns its place.	5 / 5
Actionability	Names concrete CausalPy checks (e.g. cp.checks.PreTreatmentPlaceboCheck, LeaveOneOut) and a concrete output pattern, but provides no executable code snippets, so guidance is specific-by-reference rather than copy-paste ready.	4 / 5
Workflow Clarity	A clear 6-step sequence with step 5 acting as an interpretive checkpoint (separating ruled-out from unresolved threats), though it lacks an explicit validate-fix-retry feedback loop.	4 / 5
Progressive Disclosure	Structure is reasonable and references are signaled one level deep, but the three referenced files (reference/counterfactual_analysis.md, threat_catalog.md, falsification_tests.md) do not exist in the bundle, so the links are broken.	3 / 5
	Total	16 / 20 Passed

Description

88%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong: it states concrete capabilities, gives an explicit 'Use when' clause with natural quoted trigger phrases, and occupies a distinct niche. Minor room to add a few more trigger synonyms, but it cleanly answers what and when.

Dimension	Reasoning	Score
Specificity	Names the domain and multiple concrete actions ('structured threat assessment, counterfactual reasoning, and CausalPy falsification checks'), giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (challenge causal claims via threat assessment, counterfactual reasoning, CausalPy checks) and 'when' ('Use when validating whether a causal effect is real...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural trigger phrases users would say ('is this effect real?', 'can I trust this result?'), but lacks synonyms and common variations beyond the two quoted questions, so it sits just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (causal-effect validation) with distinct triggers unlikely to fire for unrelated skills, minimizing conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: pymc-labs/CausalPy
Path: causalpy/skills/causal-detective/SKILL.md
Commit: f94d7af

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.