running-placebo-analysis

Performs placebo-in-time sensitivity analysis with hierarchical null model and optional Bayesian assurance. Use when checking model robustness, verifying lack of pre-intervention effects, or estimating study power.

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./causalpy/skills/running-placebo-analysis/SKILL.md

Quality

Content

65%Weight 40%Scale 1-3

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 but stops short of being directly actionable: it lacks executable code and relies on a reference file that is missing from the bundle, and the workflow has no explicit validation checkpoints.

Suggestions

Add a minimal executable code snippet (import, PlaceboInTime construction, .run call) so the skill is actionable without loading the reference.

Add an explicit validation/inspection checkpoint in the Evaluate step, e.g. specific thresholds or checks for p_effect_outside_null, instead of the vague 'Inspect the null distribution'.

Fix or create the referenced reference/placebo_in_time.md file so the progressive-disclosure link resolves; the referenced path is currently absent from the bundle.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no padding or explanation of concepts Claude already knows; every section earns its place.	3 / 3
Actionability	Gives named steps and API names (PlaceboInTime, n_folds, .run(experiment)) but provides no executable code, imports, or copy-paste-ready examples, leaning on a reference file for the concrete details.	2 / 3
Workflow Clarity	A clear four-step sequence (Fit, Configure, Run, Evaluate) is present, but checkpoints are implicit and the Evaluate step is vague ('Inspect the null distribution') with no validation feedback loop.	2 / 3
Progressive Disclosure	Sections are well organized and the reference is clearly signaled one level deep, but the referenced path reference/placebo_in_time.md does not exist in the bundle, so the disclosure is incomplete.	2 / 3
	Total	9 / 12 Passed

Description

85%Weight 40%Scale 1-3

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

A strong, well-structured description that covers what and when with concrete capabilities and explicit triggers. Trigger terms are slightly specialized, which keeps it from being maximally natural for a broad audience.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities: 'placebo-in-time sensitivity analysis', 'hierarchical null model', and 'optional Bayesian assurance', matching the anchor for several specific concrete actions.	3 / 3
Completeness	Explicitly states what it does and includes an explicit 'Use when...' clause naming multiple trigger scenarios, satisfying both the what and when.	3 / 3
Trigger Term Quality	Triggers like 'checking model robustness', 'verifying lack of pre-intervention effects', and 'estimating study power' are reasonably natural but lean on specialized jargon (placebo-in-time, Bayesian assurance) and miss common lay variations.	2 / 3
Distinctiveness Conflict Risk	Targets a clear niche (placebo-in-time robustness for causal models) with distinct trigger phrasing, making triggering for unrelated skills unlikely.	3 / 3
	Total	11 / 12 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: 1 missing	Warning

	Total	15 / 16 Passed

Repository: pymc-labs/CausalPy
Path: causalpy/skills/running-placebo-analysis/SKILL.md
Commit: 7e23946

Reviewed: 13 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.