pymc
Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.
83
80%
Does it follow best practices?
Impact
88%
1.49xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/pymc/SKILL.mdQuality
Discovery
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.
This is a strong description with excellent specificity and domain-appropriate trigger terms that clearly carve out a distinct niche in Bayesian probabilistic programming with PyMC. Its main weakness is the lack of an explicit 'Use when...' clause, which would help Claude know precisely when to select this skill. The technical terminology is appropriate for the target audience and unlikely to cause conflicts with other skills.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Bayesian analysis, probabilistic modeling, PyMC, MCMC sampling, or statistical inference with uncertainty quantification.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Build hierarchical models', 'MCMC (NUTS)', 'variational inference', 'LOO/WAIC comparison', 'posterior checks'. These are concrete, well-defined capabilities in the Bayesian modeling domain. | 3 / 3 |
Completeness | The 'what' is well-covered with specific capabilities, but there is no explicit 'Use when...' clause or equivalent trigger guidance. The description only implies when it should be used through the listed capabilities. Per rubric guidelines, missing 'Use when...' caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Bayesian', 'PyMC', 'hierarchical models', 'MCMC', 'NUTS', 'variational inference', 'LOO', 'WAIC', 'posterior checks', 'probabilistic programming', 'inference'. These cover the key terms a user working in this domain would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Bayesian modeling specifically with PyMC. The combination of domain-specific terms (NUTS, LOO/WAIC, hierarchical models, variational inference) makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive, well-structured Bayesian modeling skill with excellent actionability and workflow clarity. The 8-step workflow with validation checkpoints and the troubleshooting section are particular strengths. The main weakness is length — at ~400 lines, it includes content (distribution guide, all model patterns, detailed troubleshooting) that could be offloaded to the referenced files, and the opening sections contain some unnecessary framing for Claude.
Suggestions
Move the Distribution Selection Guide and Common Model Patterns sections into reference files (e.g., references/distributions.md and references/workflows.md) to reduce the main skill's token footprint while keeping the quick reference section.
Remove or significantly trim the 'When to Use This Skill' section — Claude can infer when Bayesian modeling is appropriate from the skill's content and description.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~400 lines) and includes some unnecessary explanation (e.g., 'PyMC is a Python library for Bayesian modeling' in the overview, the 'When to Use This Skill' section listing obvious use cases). However, most content is actionable code and structured guidance rather than padding. The distribution selection guide and common model patterns are useful references but contribute to length. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste ready code examples throughout — model building, sampling, diagnostics, predictions, and multiple model patterns (linear, logistic, hierarchical, Poisson, time series). Key parameters are explained with concrete values and adjustment guidance. | 3 / 3 |
Workflow Clarity | The 8-step standard Bayesian workflow is clearly sequenced with explicit validation checkpoints: prior predictive check (step 3), diagnostics with specific thresholds (step 5, R-hat < 1.01, ESS > 400), posterior predictive check (step 6). Feedback loops are present — 'If issues arise' sections with concrete remediation steps, and the troubleshooting section provides symptom → solution mappings. | 3 / 3 |
Progressive Disclosure | The skill references external files (references/, scripts/, assets/) with clear descriptions in the Resources section, and inline references like 'See references/distributions.md'. However, no bundle files were provided to verify these exist, and the main SKILL.md itself is very long — the distribution selection guide, common model patterns, and common issues sections could reasonably be split into reference files to keep the main skill leaner. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (571 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 9 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
cbcae7b
- 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.