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

65%

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

The body is highly actionable with concrete, executable code examples and a clear PR workflow, but explains some concepts Claude already knows and lacks an explicit validation/feedback loop. As a monolithic single-file guide it is well-sectioned but does not split detail into referenced files for progressive disclosure.

Suggestions

Trim explanations of concepts Claude already knows (e.g., why vectorization is faster, PyTensor backend/auto-diff primers) to tighten conciseness.

Add an explicit validation/feedback loop to the PR checklist (e.g., 'If lint or test fails, fix and re-run before proceeding') to lift workflow clarity.

Move detailed templates (full NumPy-style docstring example, extended code blocks) into a reference file and link from the overview to enable progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete conventions and code, but it explains concepts Claude already knows ('Python loops are slow; vectorized operations in C/Fortran backends are orders of magnitude faster', PyTensor backend/auto-differentiation primers), so it is not fully lean.	2 / 3
Actionability	It provides concrete, executable guidance throughout — typed function signatures, pm.Data/Prior usage, pytensor.tensor examples, a parametrized pytest test, and exact commands like 'make lint' and 'pre-commit run mypy --all-files'.	3 / 3
Workflow Clarity	The PR checklist ('Lint → Type Check → Test → Docs') and class lifecycle are sequenced, but there is no explicit validate→fix→retry feedback loop for these batch/PR operations, which caps workflow clarity at 2.	2 / 3
Progressive Disclosure	The body is well-organized into numbered sections, but as a ~165-line monolithic single-file guide with no referenced files (references/scripts/assets absent), detail like the full docstring template could be split out for clearer navigation.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 PyMC-Marketing niche and its topical scope, but relies on noun phrases and lacks an explicit 'Use when' trigger clause, capping completeness and trigger guidance at the mid level. It is specific to its domain yet missing the concrete actions and natural trigger variations that would distinguish it further.

Suggestions

Add an explicit 'Use when...' trigger clause naming when to invoke (e.g., 'Use when contributing code to pymc-marketing or reviewing PRs for style compliance') to satisfy the 'when' half of completeness.

Lead with concrete verbs/actions (e.g., 'Enforces Ruff/MyPy conventions, defines PyMC model patterns, reviews code for vectorization') instead of noun phrases to lift specificity.

Include natural trigger variations users actually say ('linting', 'best practices', 'PR review', 'pymc-marketing') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	It names a concrete domain and topical scope ('PyMC-Marketing coding conventions, preferred implementations, and style guidelines') but uses noun phrases rather than concrete actions, so it is not comprehensive enough for a 3.	2 / 3
Completeness	It answers 'what' (conventions, implementations, style) but has no explicit 'Use when...' trigger clause, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	'PyMC-Marketing' and 'coding conventions'/'style guidelines' are relevant natural terms, but common variations a user might say (e.g., 'linting', 'best practices', 'PR review') are missing.	2 / 3
Distinctiveness Conflict Risk	The 'PyMC-Marketing' niche is clearly stated, but without explicit triggers it could still overlap with generic coding-conventions or style skills.	2 / 3
	Total	8 / 12 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: e6e2574

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.