A tight, high-signal conventions reference: concrete paths, named types, and real commands with essentially zero padding. Its main gap is the absence of any executable code examples, and its monolithic single-file structure is fine but not exceptional at this length.

Dimension	Reasoning	Score
Conciseness	Every section is lean bullet-style rules with no padding or explanation of concepts Claude already knows; the one justification present ("external SSO/OIDC/SCIM identity sources whose UIDs are typically stable strings") is project-specific knowledge that earns its tokens.	5 / 5
Actionability	Gives exact file paths, class names, and runnable commands (e.g., `make test-backend-app`, `web/src/shared/lib/utils.ts`, `LocalizedDomainException`), but includes no executable code snippets showing common usage patterns, keeping it just short of copy-paste-ready coverage.	4 / 5
Workflow Clarity	This is a single-purpose reference skill with no multi-step process; the action (apply these conventions when writing or reviewing code) is unambiguous, sections are clearly organized, and no destructive or batch operations require validation checkpoints.	5 / 5
Progressive Disclosure	Well-organized sections with clear headers and a layer table, all content appropriately inline for a cross-cutting quick reference; however, at ~130 lines with no external references, it sits above the rubric's under-50-line bound for section-only structure to score 5.	4 / 5
	Total	18 / 20 Passed

Description

75%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.

A solid description that clearly states what it covers (style, logging, and testing conventions for a specific two-stack project) and includes an explicit use-when clause. It falls short of excellent only in trigger specificity: the when-clause and keywords are generic rather than the concrete phrases a user would naturally say.

Suggestions

Add natural trigger variations users would actually say, such as "lint", "format", "unit tests", or "code review", to strengthen keyword coverage.

Make the when-clause more concrete, e.g., "Use when writing or reviewing Java backend or TypeScript frontend code in the SkillHub repo, adding tests, or touching logging."

Dimension	Reasoning	Score
Specificity	"Code style, logging, and testing conventions for SkillHub backend (Java) and frontend (TypeScript)" lists several concrete convention areas across two named stacks, matching the several-specific-actions anchor with minor gaps rather than the comprehensive coverage of a 5.	4 / 5
Completeness	It answers both what (conventions for style, logging, and testing across backend and frontend) and when ("Use when writing or reviewing code"), but the when-clause is generic rather than the concrete trigger phrases of a 5.	4 / 5
Trigger Term Quality	Natural terms like "code style", "logging", "testing", "Java", "TypeScript", and "reviewing code" are present, but common variations users would actually say ("lint", "format", "unit tests", "code review") are missing.	4 / 5
Distinctiveness Conflict Risk	The SkillHub/Java/TypeScript scoping gives it a clear project niche, but the broad "Use when writing or reviewing code" trigger fires on nearly any coding task, creating minor overlap risk with other code-related skills.	4 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: iflytek/skillhub
Path: .agents/skills/code-conventions/SKILL.md
Commit: 7352597

Reviewed: 10 days 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.