code-best-practice

PyMC-Marketing coding conventions, preferred implementations, and style guidelines.

Quality

57%

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 ./.claude/skills/code-best-practice/SKILL.md

Quality

Content

61%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.

The body is a well-structured, actionable best-practices guide with concrete code examples and a clear PR checklist. It loses points for some basic-concept padding and for workflows whose validation steps are implied rather than explicit.

Suggestions

Trim explanations of concepts Claude already knows (e.g. why vectorization is faster, what automatic differentiation is) and drop the redundant intro sentence that restates the description.

Add explicit validation checkpoints to the PR workflow, e.g. 'Only commit when make lint, mypy, and make test all pass; fix and re-run if any fail.'

Replace '...' placeholder snippets with complete, copy-pasteable examples or mark them as fragments explicitly.

Dimension	Reasoning	Score
Conciseness	Mostly efficient project-specific guidance, but includes unnecessary explanation of basics Claude already knows (e.g. 'Python loops are slow; vectorized operations in C/Fortran backends are orders of magnitude faster', 'Essential for gradient-based optimization') and an intro line that restates the description.	3 / 5
Actionability	Provides concrete, mostly executable code for type hints, NumPy docstrings, pm.Data, Prior, pytensor, and pytest parametrization, plus specific commands (make lint, pre-commit run mypy); minor gaps where examples use '...' placeholders.	4 / 5
Workflow Clarity	The PR 'Workflow Checklist' and the numbered model lifecycle (init -> build_model -> _extract_predictive_variables) give a clear sequence, but validation checkpoints are only implicit (no 'only proceed when lint/tests pass' feedback loop).	3 / 5
Progressive Disclosure	No bundle files exist; the single SKILL.md is well-organized into five clearly headed sections with appropriately placed content, so the simple-skill exception applies despite exceeding 50 lines.	4 / 5
	Total	14 / 20 Passed

Description

53%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.

The description clearly identifies the domain and content scope but is missing explicit trigger ('Use when...') guidance, which limits its completeness and trigger-term quality. It is reasonably distinct thanks to the project-specific scoping.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when contributing to pymc-marketing, writing or reviewing PRs, or when the user asks about coding conventions, best practices, or style for the project.'

Include more natural trigger terms and synonyms a contributor would actually say, such as 'best practices', 'linting', 'type hints', or 'how to contribute'.

Replace abstract topic labels with a few concrete actions (e.g. 'Apply Ruff/MyPy linting rules, write NumPy-style docstrings, define priors with pymc_extras.Prior').

Dimension	Reasoning	Score
Specificity	Names the domain ('PyMC-Marketing') and three content categories ('coding conventions, preferred implementations, and style guidelines'), but these are abstract topic labels rather than concrete actions like 'Extract text from PDFs'.	3 / 5
Completeness	Has a clear 'what' (conventions, preferred implementations, style guidelines) but no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Includes some relevant phrases a contributor might say ('coding conventions', 'style guidelines', 'PyMC-Marketing') but misses common variations and synonyms like 'best practices', 'linting', or 'how to contribute'.	3 / 5
Distinctiveness Conflict Risk	Scoping to the specific 'PyMC-Marketing' project gives it a clear niche with minimal conflict risk, though the generic 'coding conventions/style guidelines' phrasing could lightly overlap with other coding-style skills.	4 / 5
	Total	13 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: pymc-labs/pymc-marketing
Path: .claude/skills/code-best-practice/SKILL.md
Commit: 66d575d

Reviewed: 4 days 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.