coding-standards

Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.

Quality

49%

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 ./docs/zh-TW/skills/coding-standards/SKILL.md

Quality

Content

57%Weight 40%Scale 1-5

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

The body is a well-sectioned catalog of concrete, executable PASS/FAIL examples that clearly communicate each standard. Its weaknesses are the absence of any bundle structure (everything inlined in one 500+ line file), sections re-teaching concepts Claude already knows, and the lack of any workflow or decision guidance for applying the standards. Splitting topic areas into reference files and trimming the principle primers would lift both conciseness and progressive disclosure.

Suggestions

Move the larger topic areas (React best practices, API design, testing, performance) into references/*.md files and keep SKILL.md as a concise index with one or two key examples per topic.

Cut or compress the KISS/DRY/YAGNI/readability sections to one-line reminders — these are concepts Claude already knows and add tokens without new information.

Add brief decision guidance (e.g. which standards to check when reviewing vs. writing new code) so the catalog functions as a workflow rather than pure reference material.

Dimension	Reasoning	Score
Conciseness	The body is mostly dense PASS/FAIL code examples, but the KISS/DRY/YAGNI/readability sections restate programming concepts Claude already knows (e.g. "程式碼被閱讀的次數遠多於被撰寫的次數", "避免過度工程"), and several examples illustrate the trivially obvious (count++, user.name). Anchor 3 (mostly efficient but includes some unnecessary explanation) fits; not 4 because these concept-primers occupy a non-trivial share of a 500+ line body.	3 / 5
Actionability	Nearly every section gives concrete, executable PASS/FAIL TypeScript/React snippets with specific patterns (spread-operator immutability, Promise.all, functional state updates, zod schemas). It is not 5 because some snippets are non-executable placeholders ("// 實作" bodies in getMarket/searchMarkets) and the zod POST handler is incomplete (no return on the success path).	4 / 5
Workflow Clarity	This is a reference catalog, not a multi-step process: sections are well-organized by topic but there is no sequencing, no decision guidance on which standards apply in which situation, and no validation checkpoints. It earns 3 rather than lower because the material is coherent and each standard is self-contained; it cannot score higher since the skill exceeds the simple-skill size exception and offers no explicit workflow.	3 / 5
Progressive Disclosure	There are no bundle files (references/, scripts/, assets/ are absent) and the entire ~515-line body lives in SKILL.md, with self-contained topic blocks (React, API design, file organization, testing, performance) that belong in separate reference files. Anchor 3 (some structure via ## sections, but content that should be separate is inline) fits; not 4 because no split or navigation exists at all.	3 / 5
	Total	13 / 20 Passed

Description

41%Weight 40%Scale 1-5

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 correctly identifies its target stacks but describes no concrete actions and provides no trigger guidance for when the skill should activate. Its broad 'universal' framing also creates conflict risk with more specific coding skills. Adding a 'Use when...' clause with concrete actions would address the two biggest gaps.

Suggestions

Add a trigger clause, e.g. 'Use when writing or reviewing TypeScript, JavaScript, React, or Node.js code, or when the user mentions code standards, clean code, or best practices.'

State 2-3 concrete capabilities instead of the generic 'standards, best practices, and patterns' (e.g. 'Enforces naming, immutability, error-handling, and typing conventions; flags code smells such as deep nesting and magic numbers').

Narrow the 'universal' framing or add distinctive keywords (lint, code review, refactor) to reduce overlap with other coding skills.

Dimension	Reasoning	Score
Specificity	The description names the domain ("TypeScript, JavaScript, React, and Node.js") but the actions are purely generic — "Universal coding standards, best practices, and patterns" names no concrete capability. It matches anchor 2 (domain named, actions minimal or generic) rather than 3 because no concrete action is ever stated.	2 / 5
Completeness	The "what" is moderately clear (provides standards/best practices/patterns for those stacks), but there is no "when" clause or equivalent trigger guidance anywhere, which caps completeness at 3 per the judging guidelines. It is not 4 because 'when' is entirely absent rather than merely under-specified.	3 / 5
Trigger Term Quality	"coding standards", "best practices", and the stack names "TypeScript", "React", "Node.js" are natural terms users would say, but common variations like "code review", "clean code", "lint", or "refactor" are missing. Anchor 3 (some relevant keywords, missing common variations/synonyms) fits better than 4, whose keyword coverage is broader.	3 / 5
Distinctiveness Conflict Risk	"Universal coding standards" for all of TypeScript, JavaScript, React, and Node.js is very broad and would overlap with code-review, refactoring, testing, and framework-specific skills. Anchor 2 (very broad, high overlap risk with many similar skills) fits; not 3 because no niche or distinct trigger narrows the scope.	2 / 5
	Total	10 / 20 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
skill_md_line_count	SKILL.md is long (521 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: docs/zh-TW/skills/coding-standards/SKILL.md
Commit: c70874f

Reviewed: 1 day 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.