coding-standards
Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.
62
21%
Does it follow best practices?
Impact
89%
1.21xAverage score across 6 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./docs/zh-TW/skills/coding-standards/SKILL.mdQuality
Discovery
14%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is too vague and broad to be effective for skill selection. It names a technology domain but fails to specify concrete actions, lacks a 'Use when...' clause, and uses generic terms like 'best practices' and 'patterns' that would cause conflicts with many other coding-related skills. It reads more like a category label than a skill description.
Suggestions
Add a 'Use when...' clause specifying explicit triggers, e.g., 'Use when the user asks about code style, naming conventions, project structure, or coding patterns for TypeScript/React/Node.js projects.'
Replace vague terms like 'best practices and patterns' with concrete actions, e.g., 'Enforces naming conventions, recommends file/folder structure, applies error handling patterns, and guides component composition.'
Narrow the scope to reduce conflict risk — specify what makes this skill distinct from other TypeScript/React skills, e.g., focusing on style enforcement vs. debugging vs. architecture.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'coding standards, best practices, and patterns' without listing any concrete actions. It doesn't specify what the skill actually does (e.g., 'enforces naming conventions', 'applies linting rules', 'structures project directories'). | 1 / 3 |
Completeness | The description partially addresses 'what' (coding standards/best practices) but in very vague terms, and completely lacks a 'when' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | It includes relevant technology keywords (TypeScript, JavaScript, React, Node.js) that users might mention, but lacks natural trigger phrases users would say like 'code review', 'refactor', 'style guide', 'lint', or 'code quality'. The terms 'coding standards' and 'best practices' are somewhat generic. | 2 / 3 |
Distinctiveness Conflict Risk | This description is extremely broad and would conflict with virtually any TypeScript, JavaScript, React, or Node.js coding skill. 'Universal coding standards' and 'best practices' could overlap with linting skills, code review skills, project scaffolding skills, and many others. | 1 / 3 |
Total | 5 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a comprehensive but extremely verbose catalog of universal coding best practices that Claude already knows thoroughly. It teaches nothing project-specific or novel — KISS, DRY, YAGNI, naming conventions, early returns, and React patterns are all part of Claude's baseline knowledge. The massive token cost provides almost zero incremental value while consuming significant context window space.
Suggestions
Remove all generic programming principles Claude already knows (KISS, DRY, YAGNI, naming conventions, early returns, magic numbers, etc.) and keep only project-specific conventions or deviations from standard practices.
Split into a concise SKILL.md overview (<30 lines) with links to separate files for React patterns, API standards, and testing standards if project-specific details are needed.
Add project-specific context: which linter config to use, specific library versions, project-specific architectural decisions, or custom patterns unique to this codebase that Claude wouldn't know by default.
If the skill must exist, reduce it to a brief list of the few conventions that differ from standard best practices (e.g., 'always use immutable patterns even where mutation is simpler' or specific response format requirements).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This is extremely verbose (~350+ lines) and almost entirely explains concepts Claude already knows well: KISS, DRY, YAGNI, naming conventions, early returns, magic numbers, AAA testing pattern, etc. Nearly every section restates basic programming principles that add no new information for Claude. | 1 / 3 |
Actionability | The code examples are concrete and executable TypeScript/React snippets, which is good. However, the guidance is generic best-practices rather than project-specific actionable instructions — Claude already knows all of these patterns and the skill doesn't tell Claude what to do differently from its defaults. | 2 / 3 |
Workflow Clarity | There is no multi-step workflow or process described. The content is organized as a reference catalog of patterns (good vs bad examples) but lacks any sequenced process, validation checkpoints, or decision trees for when to apply which pattern. For a standards document this is acceptable but not exemplary. | 2 / 3 |
Progressive Disclosure | All content is inlined in a single monolithic file with no references to external files for detailed sections. The API design, testing, React, and TypeScript sections could each be separate files linked from a concise overview. The current structure is a wall of text with no navigation strategy. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (521 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- ysyecust/everything-claude-code
- Commit
79cc4e3
- Reviewed
Table of Contents
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.