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

78%

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 ./backend/cli/skills/coding/pymc/SKILL.md

Quality

Content

81%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 highly actionable, well-structured skill with an excellent validated workflow and clean bundle navigation, held back slightly by redundant inline sections that duplicate both earlier steps and existing reference files.

Suggestions

Remove or trim the Quick Reference section, since its code blocks duplicate the Standard Bayesian Workflow and Common Model Patterns.

Collapse the Best Practices section into the per-step 'Key practices' callouts already in the workflow to avoid restating the same guidance twice.

Replace the inline Distribution Selection Guide and Sampling/Inference sections with a brief pointer to references/distributions.md and references/sampling_inference.md to eliminate overlap with those reference files.

Dimension	Reasoning	Score
Conciseness	Mostly efficient actionable code, but the Quick Reference, Best Practices, and Common Model Patterns sections restate code and guidance already covered in the Standard Bayesian Workflow, adding noticeable padding.	3 / 5
Actionability	Fully executable, copy-paste-ready code throughout, with real referenced scripts (check_diagnostics, compare_models) and templates covering the common model types.	5 / 5
Workflow Clarity	A clearly sequenced 8-step workflow with explicit validation checkpoints (prior predictive, diagnostics, posterior predictive) and feedback loops for error recovery (divergences/low ESS/high R-hat remediation).	5 / 5
Progressive Disclosure	References are well-signaled and one level deep with a clear Resources map, but the inline Distribution Selection Guide and Sampling/Inference sections overlap content already in references/distributions.md and sampling_inference.md.	4 / 5
	Total	17 / 20 Passed

Description

75%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-targeted description with strong capability listing and low conflict risk, weakened only by the absence of an explicit 'Use when...' trigger clause.

Suggestions

Add an explicit trigger clause, e.g. 'Use when building Bayesian models, running MCMC/variational inference, or comparing models with LOO/WAIC.'

Include common synonyms users might say such as 'Bayesian inference', 'posterior estimation', or 'probabilistic model fitting' to broaden trigger coverage.

Optionally mention ArviZ, since diagnostics and comparison rely on it and users may phrase requests around it.

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 Bayesian modeling workflow.	5 / 5
Completeness	The 'what' is clear, but 'when' is only weakly implied by 'for probabilistic programming and inference' — there is no explicit 'Use when...' trigger clause, which caps completeness at 3.	3 / 5
Trigger Term Quality	Strong natural domain keywords (PyMC, Bayesian, MCMC, NUTS, LOO/WAIC, probabilistic programming), but a few common synonyms such as 'Bayesian inference' or 'posterior estimation' are missing.	4 / 5
Distinctiveness Conflict Risk	'Bayesian modeling with PyMC' carves a clear niche with distinct triggers and minimal overlap risk against other skills.	5 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (576 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/coding/pymc/SKILL.md
Commit: 3a6c3a9

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.