pymc-bayesian-modeling

Compatibility alias for the descriptive PyMC skill name. Delegate to the canonical local `pymc` payload while preserving route and README compatibility.

Quality

80%

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-bayesian-modeling/SKILL.md

Quality

Content

77%

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-sequenced skill with strong workflow clarity and real, correctly-referenced bundle files, held back by verbosity and inline duplication of reference material. Trimming the duplicated Distribution Selection Guide and Quick Reference and deferring to the bundle files would lift both conciseness and progressive_disclosure.

Suggestions

Remove the inline 'Distribution Selection Guide' and 'Quick Reference' sections that duplicate references/distributions.md and earlier workflow code; replace with one-line pointers to the bundle files.

Consolidate the repeated pm.sample(draws=2000, tune=1000, chains=4, target_accept=0.9) example so it appears once and is referenced rather than restated.

Keep the 8-step workflow and diagnostics feedback loops intact, as they are the strongest part of the content.

Dimension	Reasoning	Score
Conciseness	The ~565-line body is padded with repetition (the same sampling call appears in the workflow, Sampling section, and Quick Reference) and inline material that duplicates the bundled reference files (the Distribution Selection Guide mirrors references/distributions.md), so it is mostly useful but could be tightened rather than being lean and efficient.	2 / 3
Actionability	Provides fully executable, copy-paste-ready Python with specific parameter values and concrete calls to bundled scripts (check_diagnostics, compare_models), matching the score-3 anchor rather than incomplete or pseudocode guidance.	3 / 3
Workflow Clarity	An explicit 8-step Bayesian workflow includes validation checkpoints with concrete thresholds (R-hat < 1.01, ESS > 400) and feedback loops for error recovery (divergences -> raise target_accept / non-centered parameterization), satisfying the score-3 anchor.	3 / 3
Progressive Disclosure	References/scripts/templates are well signaled, real, and one level deep, but significant content that belongs in the reference files is duplicated inline (Distribution Selection Guide, Quick Reference), pulling organization down to 'content that should be separate is inline' rather than cleanly split.	2 / 3
	Total	10 / 12 Passed

Description

82%

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 a clear niche, weakened only by the absence of an explicit 'Use when...' clause. Adding explicit trigger guidance would raise completeness from 2 to 3.

Suggestions

Append an explicit 'Use when...' clause, e.g. 'Use when building Bayesian models in PyMC, running MCMC/VI, doing posterior or prior predictive checks, or comparing models with LOO/WAIC.'

Keep the current concrete action list; it is the strongest part of the description and should not be shortened.

Ensure the phrasing stays in third person to avoid any specificity penalty.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions/techniques (hierarchical models, MCMC/NUTS, variational inference, LOO/WAIC comparison, posterior checks), matching the score-3 anchor for multiple specific concrete actions rather than the partial coverage of score 2.	3 / 3
Completeness	Clearly states what the skill does but lacks an explicit 'Use when...' trigger clause; the trailing 'for probabilistic programming and inference' only implies when, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Covers the natural vocabulary a user would say (Bayesian modeling, PyMC, MCMC, probabilistic programming, inference, posterior checks), giving good coverage of natural terms rather than only some relevant keywords.	3 / 3
Distinctiveness Conflict Risk	The PyMC Bayesian/probabilistic-programming niche has distinct triggers unlikely to fire for unrelated skills, rather than only being somewhat specific with overlap.	3 / 3
	Total	11 / 12 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-bayesian-modeling/SKILL.md
Commit: f627ab5

Reviewed: about 23 hours 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.