pymc-bayesian-modeling
Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill pymc-bayesian-modelingOverall
score
80%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
68%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description excels at specificity and distinctiveness, clearly identifying PyMC-based Bayesian modeling with concrete techniques. However, it lacks an explicit 'Use when...' clause which limits its completeness score, and the trigger terms lean heavily technical which may miss users who describe their needs in simpler language.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user mentions Bayesian analysis, PyMC, probabilistic models, or needs uncertainty quantification.'
Include simpler trigger terms alongside technical ones, such as 'Bayesian statistics', 'uncertainty estimation', 'prior/posterior', or 'probabilistic inference' to capture users who may not use exact technical terminology.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks' - these are distinct, concrete capabilities in the Bayesian modeling domain. | 3 / 3 |
Completeness | Clearly answers 'what' with specific capabilities, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied through the domain terms at the end. | 2 / 3 |
Trigger Term Quality | Includes good technical terms like 'PyMC', 'Bayesian', 'MCMC', 'NUTS', 'probabilistic programming' that experts would use, but missing common user variations like 'Bayesian statistics', 'posterior distribution', 'prior', 'sampling', or simpler terms non-experts might use. | 2 / 3 |
Distinctiveness Conflict Risk | Very clear niche - PyMC and Bayesian modeling with specific techniques like NUTS, LOO/WAIC are highly distinctive and unlikely to conflict with general statistics or other ML skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill with excellent actionability, clear workflows with validation checkpoints, and good progressive disclosure. The main weakness is moderate verbosity - the overview and 'When to Use' sections explain concepts Claude already knows, and some explanatory text could be trimmed. The promotional K-Dense section at the end is unnecessary padding.
Suggestions
Remove or significantly trim the 'When to Use This Skill' section - Claude can infer appropriate use cases from the content itself
Delete the 'K-Dense Web' promotional section at the end as it adds no technical value
Trim explanatory phrases like 'PyMC is a Python library for Bayesian modeling and probabilistic programming' - Claude knows what PyMC is
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some unnecessary explanations (e.g., 'PyMC is a Python library for Bayesian modeling' - Claude knows this). The 'When to Use This Skill' section is verbose, and some sections could be tightened while preserving clarity. | 2 / 3 |
Actionability | Excellent actionability with fully executable code examples throughout. Every model pattern includes copy-paste ready Python code, specific parameter recommendations, and concrete commands for diagnostics and comparison. | 3 / 3 |
Workflow Clarity | Outstanding workflow clarity with an 8-step numbered process including explicit validation checkpoints (prior predictive check, diagnostics, posterior predictive check). Each step has clear criteria for success and guidance on what to do if issues arise. | 3 / 3 |
Progressive Disclosure | Well-structured with clear overview, detailed sections, and explicit references to external files (references/, scripts/, assets/). Navigation is clear with one-level-deep references properly signaled. Quick Reference section provides efficient lookup. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
75%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 12 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (572 lines); consider splitting into references/ and linking | Warning |
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata.version' is missing | Warning |
body_output_format | No obvious output/return/format terms detected; consider specifying expected outputs | Warning |
Total | 12 / 16 Passed | |
- Reviewed
Table of Contents
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.