pymc-bayesian-modeling

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

Quality

79%

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 ./bundled/skills/pymc/SKILL.md

Quality

Content

85%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.

A well-structured, highly actionable PyMC skill with a clear validated workflow and clean progressive disclosure into real bundle files. Main improvement is reducing repeated code/advice blocks to tighten token efficiency.

Suggestions

De-duplicate the pm.sample(draws=2000, tune=1000, chains=4, target_accept=0.9) block and the standardize-predictors / weakly-informative-prior guidance, which reappear across the workflow, Sampling, and Best Practices sections.

Inline-link references/workflows.md from a relevant section (it is currently only inventoried in Resources) so the cookbook is discoverable at the point of need.

Replace the 'X = ... # Predictors' placeholders in the core workflow with a minimal concrete example or a clearly labeled data-loading snippet to push actionability to fully copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Largely lean and code-forward with no concept padding, but the pm.sample(draws=2000, tune=1000, chains=4, target_accept=0.9) block and the standardize/weakly-informative-prior advice repeat across the workflow, Sampling, and Best Practices sections.	4 / 5
Actionability	Extensive copy-paste-ready code spanning the full workflow plus model patterns and comparison utilities, with script imports mapping to real files; held just below 5 by 'X = ... # Predictors' placeholders and a few illustrative signatures (pm.AR, pm.LKJCorr).	4 / 5
Workflow Clarity	An 8-step Standard Bayesian Workflow is clearly numbered with explicit validation checkpoints (prior PPC, R-hat/ESS/divergence checks, posterior PPC) and remediation feedback loops for divergences and low ESS.	5 / 5
Progressive Disclosure	SKILL.md is an overview with detailed material split into real, one-level-deep bundle files (references/, scripts/, assets/), consistently signaled via 'See: references/...', 'Use template: assets/...', and a Resources inventory; all referenced paths verified to exist.	5 / 5
	Total	18 / 20 Passed

Description

73%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.

A specific, well-scoped description with strong trigger terms and low conflict risk, but it lacks an explicit 'Use when...' clause so the 'when' is only weakly implied. Adding a concrete trigger phrase would lift completeness.

Suggestions

Add an explicit trigger clause, e.g. 'Use when building or diagnosing Bayesian models in PyMC, running MCMC/VI, or comparing models with LOO/WAIC.'

Include a couple of user-natural phrasings like 'Bayesian inference' or 'MCMC sampling' as synonyms alongside the technical terms.

Optionally name a file extension or artifact cue (e.g. '.nc' InferenceData outputs) to sharpen trigger matching.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks' — giving comprehensive coverage of the PyMC surface with no real gaps.	5 / 5
Completeness	The 'what' is clear and detailed, but there is no explicit 'Use when...' trigger clause; the trailing 'for probabilistic programming and inference' only weakly implies 'when', which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Covers the natural domain vocabulary — 'PyMC', 'Bayesian modeling', 'hierarchical models', 'MCMC (NUTS)', 'variational inference', 'LOO/WAIC', 'posterior checks' — plus the key synonym 'probabilistic programming'.	5 / 5
Distinctiveness Conflict Risk	'PyMC' + 'probabilistic programming' + 'Bayesian hierarchical models' carve a clear niche with minimal overlap risk, and the body reinforces this with an explicit routing boundary.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (574 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning

	Total	14 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/pymc/SKILL.md
Commit: d5ae560

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.