pymc

Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.

Quality

87%

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

92%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 highly actionable, well-structured, and uses progressive disclosure effectively with real one-level-deep references and validation-gated workflows. The only notable weakness is minor redundancy between inline sections and the Quick Reference, which slightly reduces token efficiency.

Suggestions

Trim or de-duplicate the Quick Reference section, which repeats Sampling and Diagnostics snippets already shown in full above, to recover token budget.

Fix the non-executable snippet 'pm.Poisson(\'y\', mu=lambda)' (lambda is a reserved keyword) by renaming the parameter, e.g. 'mu=lam'.

Consider collapsing the 'When to Use This Skill' bullet list into the workflow reference pointer to reduce padding without losing trigger context.

Dimension	Reasoning	Score
Conciseness	Mostly efficient reference-style content with concrete tables and code, but minor redundancy — the Quick Reference section repeats Sampling/Diagnostics snippets already shown, and the 'When to Use' bullet list pads slightly; not 5 because of these trimmable instances, not 3 because it largely assumes Claude's competence.	4 / 5
Actionability	Provides fully executable, copy-paste-ready guidance — concrete pm.sample() calls, distribution constructors, and script imports (e.g. 'from scripts.model_diagnostics import create_diagnostic_report') covering the common cases; matches the fully-executable anchor.	5 / 5
Workflow Clarity	The 8-step Standard Bayesian Workflow is clearly sequenced with explicit validation checkpoints ('Prior predictive check … before fitting', 'Divergences invalidate the fit; fix … rather than raising target_accept') and symptom→solution feedback loops in Common Issues; matches the explicit-validation anchor.	5 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled one-level-deep references to real bundle files (standard_workflow.md, model_patterns.md, distributions.md, sampling_inference.md, plus scripts and assets), each described in a Resources section; all referenced paths exist and navigation is easy.	5 / 5
	Total	19 / 20 Passed

Description

82%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 specific, trigger-rich, and clearly distinct, but lacks an explicit 'Use when…' clause, leaving the 'when to use' guidance only weakly implied and capping completeness at 3. Adding a concrete trigger clause would lift the weakest dimension.

Suggestions

Add an explicit 'Use when...' clause naming concrete user triggers, e.g. 'Use when building or fitting Bayesian models, running MCMC/VI, diagnosing convergence, or comparing models with LOO/WAIC.'

Include common synonyms users say, such as 'Bayesian inference', 'priors', or 'posterior distributions', to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the modeling lifecycle — 'Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks' — matching the comprehensive-coverage anchor; not 4 because coverage is broad rather than having minor gaps.	5 / 5
Completeness	The 'what' is explicit and strong, but the 'when' is only weakly implied via the 'for probabilistic programming and inference' purpose clause with no explicit 'Use when…' trigger; per the judging guidelines a missing explicit trigger caps completeness at 3, and it is not 4 because no concrete trigger guidance is present.	3 / 5
Trigger Term Quality	Natural terms a user would say are well covered — 'Bayesian modeling', 'PyMC', 'MCMC (NUTS)', 'variational inference', 'LOO/WAIC', 'posterior checks', 'probabilistic programming'; clearly above the 'a few natural terms missing' anchor at 4.	5 / 5
Distinctiveness Conflict Risk	'Bayesian modeling with PyMC' is a clear niche with distinct triggers and minimal conflict risk with other skills; matches the clear-niche anchor.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/pymc/SKILL.md
Commit: 49c6e97

Reviewed: 1 day 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.