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

73%

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

70%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 commendably concise and well-structured, but it lacks executable code and relies on a reference file (reference/placebo_in_time.md) that is not present in the bundle, undermining both actionability and progressive disclosure.

Suggestions

Add a minimal executable code example showing PlaceboInTime construction and .run() invocation so the skill is copy-paste ready.

Create the referenced reference/placebo_in_time.md file (or correct the path) so the reference resolves and progressive disclosure works.

Insert an explicit validation checkpoint in the workflow (e.g., inspect trace convergence or verify p_effect_outside_null is sane) before declaring analysis complete.

Dimension	Reasoning	Score
Conciseness	Lean and efficient; assumes Claude's competence and avoids explaining basic concepts, with every line (Workflow, Key Concepts, References) earning its place.	5 / 5
Actionability	Names concrete API elements (PlaceboInTime, n_folds, experiment_factory, .run(experiment), theta_new, p_effect_outside_null) but provides no executable code examples or copy-paste-ready snippets, leaving the user to assemble calls.	3 / 5
Workflow Clarity	The four-step sequence (Fit, Configure, Run, Evaluate) is clearly ordered, but for a model-fitting/analysis batch operation there are no explicit validation checkpoints or feedback loops (e.g., checking convergence, sanity-checking the null distribution), capping the score at 3.	3 / 5
Progressive Disclosure	The body references [Placebo-in-time Implementation](reference/placebo_in_time.md) but that referenced file does not exist in the bundle, so the one-level-deep reference is broken rather than well-signaled, and most detail remains inlined with no actual destination.	2 / 5
	Total	13 / 20 Passed

Description

76%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 clear, third-person, and explicitly covers both the 'what' and 'when' with concrete, distinctive capabilities. Its main weakness is trigger-term naturalness — the phrasing is technical and may not match how a typical user would phrase the request.

Suggestions

Add more natural-language trigger synonyms (e.g., 'Use when stress-testing a causal model' or 'when checking if an effect is real') alongside the technical terms.

Consider mentioning the broader causal-inference context (e.g., interrupted time series, synthetic control) so users describing those tasks route to this skill.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('placebo-in-time sensitivity analysis', 'hierarchical null model', 'optional Bayesian assurance') with only minor gaps in coverage; not fully comprehensive enough for a 5.	4 / 5
Completeness	Explicitly states both what it does ('Performs placebo-in-time sensitivity analysis...') and when to use it ('Use when checking model robustness, verifying lack of pre-intervention effects, or estimating study power').	5 / 5
Trigger Term Quality	Trigger phrases ('checking model robustness', 'verifying lack of pre-intervention effects', 'estimating study power') are relevant but specialized; they miss common natural synonyms a non-specialist user might say and use technical jargon.	3 / 5
Distinctiveness Conflict Risk	Clear niche in causal-inference sensitivity analysis with distinct triggers; minimal overlap risk with other skills given the specialized statistical vocabulary.	5 / 5
	Total	17 / 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: 1 missing	Warning

	Total	15 / 16 Passed

Repository: pymc-labs/CausalPy
Path: causalpy/skills/running-placebo-analysis/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.