code-conventions

Code style, logging, and testing conventions for SkillHub backend (Java) and frontend (TypeScript). Use when writing or reviewing code.

Quality

79%

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/code-conventions/SKILL.md

Quality

Content

83%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.

A well-crafted, highly actionable conventions reference that is lean and assumes Claude's competence, with concrete class names, paths, and commands throughout. Its only real gap is the absence of any sequenced workflow with validation checkpoints, which is largely inherent to a reference-style skill.

Suggestions

Add a short 'Workflow' subsection for applying the conventions when modifying code (e.g. locate the right layer -> apply the matching convention -> run the appropriate test slice), with an explicit validation step.

Consider splitting the Java/Backend and TypeScript/Frontend sections into separate reference files linked from SKILL.md to improve progressive disclosure now that the body exceeds ~130 lines.

Include one or two minimal executable code snippets (e.g. a canonical exception-throw example or a TanStack Query hook) to make the conventions copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is lean throughout — tight bullets that state conventions without explaining what SLF4J, TanStack Query, or Feature-Sliced Design are, assuming Claude's competence; every line earns its place, matching the 'lean and efficient' anchor 5.	5 / 5
Actionability	Guidance is concrete and directly applicable: exact class names ('LocalizedDomainException'), package paths ('com.iflytek.skillhub.controller/'), file paths ('web/src/shared/lib/utils.ts'), and commands ('make test-backend-app'), fully actionable per the instruction-skill note despite the absence of code blocks.	5 / 5
Workflow Clarity	This is a reference/conventions skill with no real multi-step workflow to sequence; the testing section gives a command and a pitfall but lacks explicit ordered steps or validation checkpoints, matching 'sequence present but checkpoints missing or implicit' rather than higher anchors reserved for clearly sequenced workflows.	3 / 5
Progressive Disclosure	No bundle files exist and all content is inline in a single well-structured file with clear section headers and a layer table; structure is good and navigation is easy, but at ~130 lines the Java and TypeScript sections could plausibly be split into separate reference files, leaving minor organization gaps versus the ideal anchor 5.	4 / 5
	Total	17 / 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, third-person description that explicitly covers what the skill governs and when to invoke it, with good specificity for a project-scoped conventions skill. The main weakness is a generic 'when' clause that does not name the specific stacks, slightly limiting trigger precision.

Suggestions

Tighten the 'when' clause to name the stacks, e.g. 'Use when writing or reviewing SkillHub backend (Java) or frontend (TypeScript) code.'

Add common trigger synonyms users might say, such as 'linting', 'code review', or 'best practices', to broaden natural keyword coverage.

Consider listing one or two more concrete capability areas (e.g. 'error handling' or 'project structure') to push specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain plus several concrete areas — 'Code style, logging, and testing conventions' for 'backend (Java) and frontend (TypeScript)' — giving multiple specific actions with only minor coverage gaps, fitting the 'several specific actions' anchor rather than the fully comprehensive anchor 5.	4 / 5
Completeness	Explicitly answers both what ('Code style, logging, and testing conventions for SkillHub backend (Java) and frontend (TypeScript)') and when ('Use when writing or reviewing code'), but the 'when' clause is generic and does not reference the specific stacks, so it matches 'both what and when; when could be more explicit' rather than the fully concrete anchor 5.	4 / 5
Trigger Term Quality	Includes natural trigger phrases a user would say ('writing or reviewing code', 'code style') with good coverage, but misses common synonyms like 'linting', 'Java/TypeScript style', or 'best practices', so it sits at 'good keyword coverage; a few natural terms missing' rather than comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	The SkillHub-specific, Java/TypeScript-scoped framing gives it a clear niche with low conflict risk, but the broad 'writing or reviewing code' trigger leaves minor overlap risk with generic code-style skills, matching 'mostly distinct; minor overlap risk' rather than anchor 5.	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: b896c69

Reviewed: 5 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.