nextjs15-init
Use when user wants to create a new Next.js 15 project (Todo/Blog/Dashboard/E-commerce/Custom domain) with App Router, ShadCN, Zustand, Tanstack Query, and modern Next.js stack
75
68%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/nextjs15-init/SKILL.mdQuality
Discovery
89%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 excels at trigger terms and completeness with a clear 'Use when' clause and specific technology keywords. However, it lacks specificity about what concrete actions the skill performs beyond project creation - it doesn't explain whether it scaffolds files, configures tools, generates boilerplate, etc. The description is functional but could be more informative about capabilities.
Suggestions
Add specific actions the skill performs, e.g., 'Scaffolds project structure, configures build tools, generates boilerplate components, sets up state management'
Consider restructuring to lead with capabilities before the 'Use when' clause for better readability
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Next.js 15 project creation) and lists specific technologies (App Router, ShadCN, Zustand, Tanstack Query), but doesn't describe concrete actions beyond 'create a new project'. Missing details about what the skill actually does (scaffolding, configuration, file generation, etc.). | 2 / 3 |
Completeness | Explicitly answers both 'what' (create Next.js 15 projects with specific tech stack) and 'when' (starts with 'Use when user wants to create...'). The 'Use when' clause is present and provides clear trigger guidance. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'Next.js', 'project', 'Todo', 'Blog', 'Dashboard', 'E-commerce', 'App Router', 'ShadCN', 'Zustand', 'Tanstack Query'. These are all terms developers naturally use when requesting project scaffolding. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific technology stack (Next.js 15, App Router, ShadCN, Zustand, Tanstack Query) and project types listed. Unlikely to conflict with generic coding skills or other framework-specific skills due to the precise tech combination. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill has excellent workflow clarity with proper validation checkpoints for lint and build steps, but severely violates conciseness principles. The content is approximately 6x longer than recommended, with extensive explanations of domain options and presets that could be condensed into tables or moved to reference files. The interactive questionnaire format, while user-friendly, adds significant token overhead.
Suggestions
Condense domain options (Todo/Blog/Dashboard/E-commerce) into a simple table with columns: Domain | Fields | API Routes | Key Features - this could reduce ~100 lines to ~20
Move the detailed 'Custom selection' questions (Step 2) and 'Stack preset' descriptions to references/setup-guide.md, keeping only brief summaries in the main file
Replace verbose validation output examples with a single line: 'Run `npm run lint && npm run build` - fix any errors before proceeding'
Add executable code snippets for at least one domain (e.g., complete TodoItem.tsx component) instead of describing what will be generated
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines. Contains extensive explanations of domain options, preset choices, and step-by-step instructions that could be dramatically condensed. The skill explains concepts Claude already knows (what Todo/Blog apps are, what each library does) and includes redundant information throughout. | 1 / 3 |
Actionability | Provides concrete bash commands and folder structures, but most code examples are incomplete or pseudocode-like (e.g., '[폴더명]' placeholders). The actual boilerplate code generation is described rather than shown with executable examples. | 2 / 3 |
Workflow Clarity | Clear multi-step workflow with explicit validation checkpoints. Steps 3-4 include mandatory lint and build verification with success/failure examples, and the skill explicitly states 'lint와 build 모두 성공해야 다음 단계로 진행할 수 있습니다' (must pass both before proceeding). | 3 / 3 |
Progressive Disclosure | References setup-guide.md for detailed documentation, but the main file itself is a monolithic wall of text (~300 lines) that should be split. The comment at the bottom acknowledges '~50 lines total (max ~150 lines)' guideline but the content far exceeds this. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- bear2u/my-skills
- Commit
1be5394
- 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.