Technical decision criteria, anti-pattern detection, debugging techniques, and quality check workflow. Use when making technical decisions, detecting code smells, or performing quality assurance.
55
61%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/ai-development-guide/SKILL.mdQuality
Discovery
59%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 has good structural completeness with an explicit 'Use when...' clause, but suffers from being too broad and category-level rather than specific. The terms used are more like chapter headings than concrete capabilities, and the scope is so wide that it would likely conflict with many other skills in a multi-skill environment.
Suggestions
Narrow the scope or list specific concrete actions (e.g., 'Detects N+1 queries, evaluates coupling metrics, checks for SOLID violations') instead of broad category labels like 'anti-pattern detection'.
Add more natural trigger terms users would say, such as 'code review', 'tech debt', 'refactor', 'best practices', 'performance bottleneck'.
Define a clearer niche to reduce conflict risk — consider whether this is primarily about code review, architecture decisions, or debugging, and focus the description accordingly.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names several domain areas ('technical decision criteria', 'anti-pattern detection', 'debugging techniques', 'quality check workflow') but these are category labels rather than concrete actions. It doesn't list specific things it does like 'identifies N+1 queries' or 'evaluates architecture tradeoffs'. | 2 / 3 |
Completeness | Explicitly answers both 'what' (technical decision criteria, anti-pattern detection, debugging techniques, quality check workflow) and 'when' ('Use when making technical decisions, detecting code smells, or performing quality assurance'). The 'Use when...' clause is present and provides explicit triggers. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'code smells', 'quality assurance', 'debugging', and 'technical decisions' that users might naturally say. However, it misses common variations like 'code review', 'refactor', 'best practices', 'performance issues', 'tech debt', or 'linting'. | 2 / 3 |
Distinctiveness Conflict Risk | The scope is extremely broad — 'technical decisions', 'debugging', and 'quality assurance' could overlap with virtually any coding, review, or development skill. It lacks a clear niche and would likely conflict with many other skills in a large skill library. | 1 / 3 |
Total | 8 / 12 Passed |
Implementation
62%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 technical decision-making guide with strong workflow clarity and well-structured checklists, but it suffers from being overly monolithic and occasionally verbose. The content covers many distinct domains (anti-patterns, debugging, quality assurance, implementation completeness) that would benefit from progressive disclosure across multiple files. Actionability is moderate — the guidance is structured and specific in intent but relies on pseudocode and abstract patterns rather than executable examples.
Suggestions
Split the monolithic document into focused sub-files (e.g., ANTI_PATTERNS.md, QUALITY_CHECKS.md, DEBUGGING.md, IMPACT_ANALYSIS.md) with a concise overview in SKILL.md linking to each.
Remove explanations of concepts Claude already knows (e.g., what SRP/DRY are, basic debugging steps like 'read error message accurately') and focus only on project-specific decision criteria and thresholds.
Where possible, provide language-specific executable examples rather than pseudocode patterns — or at minimum provide examples in one representative language to anchor the abstract guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but contains some content Claude already knows well (e.g., explaining what DRY/SRP principles are, basic debugging techniques like reading error messages, the concept of 5 Whys). Some sections like 'Common Failure Patterns' include explanations of symptoms/causes that are somewhat verbose. However, the structured tables and concise pattern formats help offset this. | 2 / 3 |
Actionability | The skill provides structured checklists, decision tables, and workflow steps which are useful, but lacks concrete executable code examples — the code blocks are pseudocode patterns rather than copy-paste ready implementations. The Impact Analysis template and error handling patterns give specific structure but remain abstract rather than tied to specific tools or commands. | 2 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit validation checkpoints. The Quality Check Workflow has clear phases with a final quality gate, the Impact Analysis has a mandatory 3-stage process with a 'do not implement until documented' checkpoint, and the error handling section includes review triggers and verification steps before implementing fallbacks. | 3 / 3 |
Progressive Disclosure | The content is a monolithic document at ~300 lines covering many distinct topics (anti-patterns, error handling, debugging, quality checks, implementation completeness) that could benefit from being split into separate referenced files. While internal section organization is decent with clear headers, there are no references to external files and the document tries to cover too much in one place. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
adf2e4d
Table of Contents
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.