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

85%

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

78%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 body built around five executable workflows with real convergence diagnostics and troubleshooting. Its main weakness is progressive disclosure: everything lives inline with no reference files to keep the overview lean.

Suggestions

Move the longer worked workflows (e.g. convergence diagnostics, model comparison) into reference files under ./references/ and link to them from a concise overview, so SKILL.md stays a lean entry point.

Integrate the convergence check as an explicit gate inside the main MCMC workflow (run -> check R-hat/tau -> rerun if not converged) rather than as a standalone section.

Trim the duplicated 'When to Use' bullets that restate the description, keeping the body focused on how to execute.

Dimension	Reasoning	Score
Conciseness	Mostly lean and code-forward, assuming Claude's competence without explaining basic Bayesian concepts; a few inline comments and the duplicated 'When to Use' framing could be trimmed slightly.	4 / 5
Actionability	Five complete, copy-paste-ready Python workflows (sampling, corner plot, diagnostics, posterior predictive, model comparison) cover the common cases with real, executable code.	5 / 5
Workflow Clarity	Workflows are clearly numbered and sequenced with explicit validation thresholds (R-hat < 1.01, chain/tau > 50) and a troubleshooting feedback table, but the diagnostics are presented as a separate step rather than an integrated gate inside the main sampling workflow.	4 / 5
Progressive Disclosure	Well-organized with clear section headers, but all content (~190 lines) is inlined in SKILL.md with no bundle files and no one-level-deep references to split out the longer workflow details.	3 / 5
	Total	16 / 20 Passed

Description

92%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 strong, specific description that names concrete capabilities and provides an explicit use-trigger, with good distinctiveness from sibling fitting skills. Keyword coverage is solid though a few natural synonyms could be added.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'parameter estimation', 'posterior distributions', 'corner plots', 'model evidence', 'convergence diagnostics' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (estimation, posteriors, corner plots, evidence, diagnostics) and 'when' via the concrete trigger 'Use when you need full posterior distributions, not just point estimates'.	5 / 5
Trigger Term Quality	Strong natural keywords ('posterior distributions', 'point estimates', 'Bayesian', 'MCMC') plus library names (emcee, PyMC); a few common synonyms or phrasings a user might say are absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche (Bayesian/MCMC posteriors) with distinct triggers and an explicit contrast to least-squares/curve_fit, minimizing overlap with neighboring physics skills.	5 / 5
	Total	19 / 20 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: 5f2a37b

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.