coding-standards

适用于 TypeScript、JavaScript、React 和 Node.js 开发的通用编码标准、最佳实践与模式。

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 ./.agents/skills/coding-standards/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 extensive executable good/bad code examples across TypeScript, React, and API design. Its weaknesses are verbosity from teaching well-known principles and a monolithic single-file structure with no progressive disclosure or external references.

Suggestions

Cut or condense the concept explanations for KISS/DRY/YAGNI and basic smells (magic numbers, deep nesting, long functions) that Claude already knows, keeping only project-specific conventions.

Split large reference areas (React best practices, API design standards, testing standards) into separate referenced files and add a concise overview with one-level-deep links in SKILL.md.

If the skill is meant to guide a process (e.g., conducting a code review), add an explicit sequenced workflow with validation checkpoints; otherwise keep it as a reference but state that clearly.

Dimension	Reasoning	Score
Conciseness	The body is rich with concrete ✅优/❌劣 code examples that earn their place, but it also explains basic concepts Claude already knows (KISS, DRY, YAGNI, 'code is read more than written', magic numbers, deep nesting), which the rubric penalizes; it could be tightened by trimming the principle prose.	2 / 3
Actionability	It provides numerous concrete, executable TypeScript/React examples (typed components, custom hooks, zod validation, REST conventions, JSDoc) in copy-paste-ready form with paired good/bad samples, matching the score-3 anchor.	3 / 3
Workflow Clarity	This is a reference catalog rather than a sequenced multi-step process; sections are well organized but there is no workflow sequence with validation checkpoints, so it sits at the score-2 anchor (sequence present/organized but no checkpoints).	2 / 3
Progressive Disclosure	All content lives inline in a single ~525-line SKILL.md with no bundle files or references; sections are well structured, but material that could be split (React practices, API design, testing) is inline, matching the score-2 anchor rather than the under-50-lines exception.	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 is in correct third-person voice and names a clear tech stack, but it stays at an abstract category level and omits any explicit 'when to use' trigger guidance. It is adequate but not sharply differentiated or action-specific.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers (e.g., code review, setting up linting/formatting rules, refactoring for consistency, onboarding contributors).

Replace the generic '最佳实践和模式' with concrete actions the skill enforces (e.g., naming, immutability, error handling, type safety conventions).

Add natural trigger variations users would say ('coding conventions', 'code style', 'linting rules') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('TypeScript、JavaScript、React 和 Node.js') and broad action categories ('通用编码标准、最佳实践和模式'), but 'best practices and patterns' is abstract rather than a list of concrete actions, matching the score-2 anchor.	2 / 3
Completeness	It clearly states what the skill provides (coding standards/best practices/patterns for the listed technologies) but provides no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	It includes relevant natural keywords users would say ('编码标准', '最佳实践', 'TypeScript', 'React', 'Node.js'), but it misses common variations like 'code review', 'linting', or 'naming conventions' that a user requesting this skill would often say.	2 / 3
Distinctiveness Conflict Risk	Listing the specific tech stack (TS/JS/React/Node) gives it some specificity, but '通用编码标准' (general coding standards) is broad and could overlap with other linting, review, or framework-specific skills.	2 / 3
	Total	8 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (531 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: xu-xiang/everything-claude-code-zh
Path: .agents/skills/coding-standards/SKILL.md
Commit: dfbf946

Reviewed: about 2 hours 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.