fullstack-developer
Modern web development expertise covering React, Node.js, databases, and full-stack architecture. Use when: building web applications, developing APIs, creating frontends, setting up databases, deploying web apps, or when user mentions React, Next.js, Express, REST API, GraphQL, MongoDB, PostgreSQL, or full-stack development.
72
58%
Does it follow best practices?
Impact
92%
1.16xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./awesome_agent_skills/fullstack-developer/SKILL.mdQuality
Discovery
74%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 benefits from a well-structured 'Use when' clause with many natural trigger terms, making it strong on completeness and trigger quality. However, it is very broad in scope, covering nearly all of web development, which creates high conflict risk with more specialized skills. The capabilities described are more like a domain label ('expertise') than concrete actions.
Suggestions
Narrow the scope or clarify when this skill should be chosen over more specialized frontend, backend, or database skills to reduce conflict risk.
Replace the vague 'expertise covering' with specific concrete actions like 'scaffolds React components, configures Express routes, writes database queries, sets up CI/CD pipelines'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (web development) and mentions technologies (React, Node.js, databases, full-stack architecture), but describes 'expertise' rather than listing concrete actions. It says 'building', 'developing', 'creating', 'deploying' which are somewhat generic verbs rather than specific capabilities like 'configure webpack builds' or 'set up database migrations'. | 2 / 3 |
Completeness | Clearly answers both 'what' (web development covering React, Node.js, databases, full-stack architecture) and 'when' with an explicit 'Use when:' clause listing specific trigger scenarios and technology names. | 3 / 3 |
Trigger Term Quality | Includes a strong set of natural keywords users would say: React, Next.js, Express, REST API, GraphQL, MongoDB, PostgreSQL, full-stack development, web applications, APIs, frontends, databases. These cover many common variations a user might mention. | 3 / 3 |
Distinctiveness Conflict Risk | This is extremely broad — covering React, Node.js, databases, APIs, frontends, deployment, and full-stack architecture means it would likely conflict with any more specialized skill for frontend development, backend development, database management, or deployment. It's essentially a catch-all for web development. | 1 / 3 |
Total | 9 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides excellent, executable code examples with proper TypeScript typing and error handling, but is severely bloated with generic web development knowledge that Claude already possesses. The technology stack lists, best practices, and architecture patterns sections are largely redundant and waste token budget. The content would benefit greatly from aggressive trimming and splitting into referenced files.
Suggestions
Remove the Technology Stack and Best Practices sections entirely — Claude already knows these conventions. Focus only on project-specific preferences or non-obvious choices.
Extract the Architecture Patterns directory trees and the Example Response into separate bundle files (e.g., ARCHITECTURE.md, EXAMPLES.md) and reference them from a concise overview.
Add validation checkpoints to the setup workflow (e.g., 'Verify migration: npx prisma studio' or 'Test endpoint: curl localhost:3000/api/posts').
Reduce the main SKILL.md to under 80 lines: a brief 'When to Apply' section, one representative code example, the Output Format checklist, and links to supporting files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose. The Technology Stack section is a laundry list of tools Claude already knows. Best Practices like 'keep components small and focused', 'use parameterized queries', and 'avoid N+1 queries' are generic advice Claude doesn't need. The Architecture Patterns section with directory trees adds little unique value. Much of this content restates common knowledge rather than providing novel, specific guidance. | 1 / 3 |
Actionability | The code examples are fully executable, typed TypeScript with proper imports, error handling, and Zod validation. The blog post example includes complete code, Prisma schema, dependency installation, and setup commands — all copy-paste ready. | 3 / 3 |
Workflow Clarity | The Output Format section provides a clear checklist for responses, and the setup commands are sequenced. However, there are no validation checkpoints (e.g., verify the migration succeeded, test the API endpoint) and no error recovery guidance for the multi-step setup process. | 2 / 3 |
Progressive Disclosure | The skill is a monolithic wall of text (~250 lines) with no references to external files. The Technology Stack listing, Architecture Patterns, and Best Practices sections could all be split into separate reference files. There is no bundle structure to support progressive disclosure. | 1 / 3 |
Total | 7 / 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
- Shubhamsaboo/awesome-llm-apps
- Commit
4fd8f22
- 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.