tdg-personal/coding-standards
Baseline cross-project coding conventions for naming, readability, immutability, and code-quality review. Use detailed frontend or backend skills for framework-specific patterns.
55
55%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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 establishes a reasonable scope as a baseline coding conventions skill and helpfully distinguishes itself from framework-specific skills. However, it lacks an explicit 'Use when...' trigger clause, lists categories rather than concrete actions, and misses common natural language terms users would employ when seeking coding convention guidance.
Suggestions
Add an explicit 'Use when...' clause with trigger terms like 'code style', 'naming conventions', 'clean code', 'best practices', 'code review standards'.
Replace abstract categories with concrete actions, e.g., 'Enforces consistent naming conventions, flags mutable state, checks function length and readability, and provides code-quality review feedback'.
Include more natural user-facing keywords such as 'coding standards', 'style guide', 'linting rules', 'variable naming', 'code smell' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (coding conventions) and lists some areas (naming, readability, immutability, code-quality review), but these are categories rather than concrete actions. It doesn't describe specific actions like 'enforce camelCase naming' or 'flag mutable variables'. | 2 / 3 |
Completeness | The 'what' is partially addressed (baseline coding conventions for naming, readability, etc.), but there is no explicit 'Use when...' clause. The second sentence provides a negative boundary ('Use detailed frontend or backend skills for framework-specific patterns') rather than positive trigger guidance for when to use this skill. | 2 / 3 |
Trigger Term Quality | Includes some relevant terms like 'naming', 'readability', 'immutability', and 'code-quality review', but misses many natural user phrases like 'code style', 'coding standards', 'best practices', 'clean code', 'code review', 'linting', or 'conventions'. | 2 / 3 |
Distinctiveness Conflict Risk | The description positions itself as a 'baseline cross-project' skill and explicitly defers to frontend/backend-specific skills, which helps with differentiation. However, 'coding conventions' and 'code-quality review' are broad enough to potentially overlap with many code-related skills. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides excellent concrete code examples with clear PASS/FAIL patterns, making it highly actionable. However, it severely violates its own stated scope boundaries by including extensive React, API design, testing, and performance content that it explicitly says belongs in other skills. The result is a bloated, monolithic file that explains many concepts Claude already knows, wasting significant token budget.
Suggestions
Remove the React Best Practices, API Design Standards, Performance Best Practices, and Testing Standards sections entirely—these are explicitly out of scope per the skill's own boundaries and should live in frontend-patterns, backend-patterns, and api-design skills.
Trim the Code Quality Principles section to just the headings or a single-line summary each—Claude already knows KISS, DRY, YAGNI, and readability principles.
Add a brief code review workflow with explicit steps (e.g., 1. Check naming conventions, 2. Verify immutability patterns, 3. Run linter, 4. Confirm no code smells) to improve workflow clarity.
Move the detailed TypeScript/JavaScript examples for naming, immutability, and error handling into a referenced file (e.g., EXAMPLES.md) and keep only the most critical patterns inline.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose (~350+ lines) and explains many concepts Claude already knows well: KISS, DRY, YAGNI, REST conventions, AAA testing pattern, basic React patterns, lazy loading, memoization, etc. The scope boundaries say to defer React and API design to other skills, yet the file includes extensive React, API, and testing sections anyway. Most tokens are spent on universally known programming principles. | 1 / 3 |
Actionability | The skill provides fully executable TypeScript/React code examples throughout, with clear PASS/FAIL patterns that are copy-paste ready. Every principle is illustrated with concrete, runnable code rather than abstract descriptions. | 3 / 3 |
Workflow Clarity | The skill is organized into clear sections with good structure, but it lacks any multi-step workflow with validation checkpoints. For a code review/standards skill, there's no defined process for how to apply these standards (e.g., a review checklist sequence or linting workflow with verification steps). | 2 / 3 |
Progressive Disclosure | The file is a monolithic wall of content (~350+ lines) that includes extensive React, API, testing, and performance sections inline despite explicitly stating these belong in other skills. The references to frontend-patterns, backend-patterns, and api-design at the top are good, but the content contradicts the scope boundaries by duplicating what those skills should cover. | 1 / 3 |
Total | 7 / 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 (550 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
Reviewed
Table of Contents