aif-best-practices

Code quality guidelines and best practices for writing clean, maintainable code. Covers naming, structure, error handling, testing, and code review standards. Use when writing code, reviewing, refactoring, or asking "how should I name this", "best practice for", "clean code".

Quality

92%

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

85%

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

A well-structured, actionable reference skill with concrete executable examples and clear checklists; its main weakness is moderate verbosity from duplicated rules and the skill-context framing that could be condensed.

Suggestions

Consolidate the per-domain prose 'Rules' lists with the side-by-side tables to remove duplication and trim tokens.

Tighten the skill-context framing block — it restates the override principle several times; compress to the essential 'skill-context rules override defaults and apply to all outputs' instruction.

Move the static coverage-priorities and module-organization reference material into a separate references file to keep SKILL.md as a leaner overview.

Dimension	Reasoning	Score
Conciseness	Code examples are appropriately lean and skip explanations of basic concepts, but the body repeats rules across prose lists and side-by-side tables, and the skill-context framing block adds bulk that could be tightened.	2 / 3
Actionability	Provides fully executable, copy-paste-ready examples (calculateDiscount in TypeScript/PHP, custom error classes, AAA test blocks) plus concrete side-by-side good/bad comparisons and specific rules.	3 / 3
Workflow Clarity	An advisory reference skill with no destructive multi-step operation; it supplies a clear review checklist and an explicit enforcement feedback loop ('After generating any output artifact, verify... If any rule is violated — fix the output').	3 / 3
Progressive Disclosure	No bundle files exist, so all content is inline in one well-organized file with clear section navigation (Quick Reference, per-domain headings, summary table) and only a single one-level skill-context reference.	3 / 3
	Total	11 / 12 Passed

Description

100%

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, concise description that names concrete capabilities, supplies natural user trigger phrases, and explicitly covers both what the skill does and when to use it in third person.

Dimension	Reasoning	Score
Specificity	Explicitly enumerates concrete capability domains — 'Covers naming, structure, error handling, testing, and code review standards' — listing multiple specific actions rather than vague language.	3 / 3
Completeness	Clearly answers both 'what' (code quality guidelines covering named domains) and 'when' with an explicit 'Use when writing code, reviewing, refactoring, or asking...' clause.	3 / 3
Trigger Term Quality	Natural user utterances are quoted directly — "how should I name this", "best practice for", "clean code" — alongside 'writing code, reviewing, refactoring', giving good coverage of phrases a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Triggers are tightly scoped to code-quality concerns and anchored by distinctive quoted phrases, making it unlikely to fire for the wrong skill; written in third person.	3 / 3
	Total	12 / 12 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: lee-to/ai-factory
Path: skills/aif-best-practices/SKILL.md
Commit: 4b943ec

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.