bayesian-inference

Bayesian parameter estimation with MCMC (emcee) and probabilistic programming (PyMC). Posterior distributions, corner plots, model evidence, convergence diagnostics. Use when you need full posterior distributions, not just point estimates.

Quality

96%

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%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, concise, well-sequenced skill body whose only weakness is structure: everything lives inline in one long SKILL.md with no progressive disclosure into reference files. Splitting the advanced workflows out would lift the weakest dimension.

Suggestions

Split the advanced workflows (Convergence Diagnostics, Posterior Predictive Check, Model Comparison) into reference files such as references/diagnostics.md and references/model-comparison.md, linking them from SKILL.md to reduce the monolithic ~190-line body.

Add a brief Quick Start section near the top that points to the core emcee workflow, so the essential path is front-loaded before the five detailed workflows.

Move the emcee Tips and Troubleshooting table into a references/troubleshooting.md, keeping SKILL.md as a concise overview with clearly signaled one-level-deep references.

Dimension	Reasoning	Score
Conciseness	The body is lean and code-dense with only task-specific prose; it does not explain what MCMC, posteriors, or the libraries are, assuming Claude's statistical competence.	3 / 3
Actionability	All five workflows are complete, executable, copy-paste-ready Python (emcee sampling, corner plots, R-hat diagnostics, posterior predictive, model comparison) rather than pseudocode.	3 / 3
Workflow Clarity	Workflows are numbered and sequenced, convergence steps carry explicit validation thresholds ('Should be > 50', 'Should be < 1.01'), and the Troubleshooting table provides symptom-to-fix feedback loops.	3 / 3
Progressive Disclosure	Sections are well-organized, but the ~190-line body is a monolithic single file with no external references; the under-50-line simple-skill exception does not apply, so it sits at the 'structured but content that could be separate is inline' anchor rather than 3.	2 / 3
	Total	11 / 12 Passed

Description

100%

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 strong, third-person description that concisely states concrete capabilities and an explicit use-trigger with a helpful contrast against point-estimate fitting. It satisfies every dimension without verbosity or over-claiming.

Dimension	Reasoning	Score
Specificity	Names multiple concrete deliverables — 'Posterior distributions, corner plots, model evidence, convergence diagnostics' — alongside the core estimation action, matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly answers what ('Bayesian parameter estimation with MCMC...') and when ('Use when you need full posterior distributions, not just point estimates'), satisfying the explicit-trigger anchor.	3 / 3
Trigger Term Quality	Terms a Bayesian-inference user would naturally say (posterior distributions, MCMC, convergence diagnostics) plus the contrast trigger 'not just point estimates' give good natural coverage; not merely technical jargon.	3 / 3
Distinctiveness Conflict Risk	The Bayesian/MCMC posterior niche is clear and the 'not just point estimates' phrasing distinguishes it from basic fitting skills, making wrong-skill triggering unlikely.	3 / 3
	Total	12 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/physics/bayesian-inference/SKILL.md
Commit: 52845c3

Reviewed: about 10 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.