senior-fullstack
Fullstack development toolkit with project scaffolding for Next.js, FastAPI, MERN, and Django stacks, code quality analysis with security and complexity scoring, and stack selection guidance. Use when the user asks to "scaffold a new project", "create a Next.js app", "set up FastAPI with React", "analyze code quality", "audit my codebase", "what stack should I use", "generate project boilerplate", or mentions fullstack development, project setup, or tech stack comparison.
94
88%
Does it follow best practices?
Impact
98%
1.58xAverage score across 6 eval scenarios
Passed
No known issues
Quality
Discovery
92%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 is a strong description that clearly articulates specific capabilities across three domains (scaffolding, code analysis, stack guidance) and provides extensive trigger phrases in a well-structured 'Use when...' clause. The main weakness is that some trigger terms like 'analyze code quality' and 'audit my codebase' are generic enough to potentially conflict with dedicated code review or security audit skills. The description uses proper third-person voice and is well-organized.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: project scaffolding for named stacks (Next.js, FastAPI, MERN, Django), code quality analysis with security and complexity scoring, and stack selection guidance. These are clearly defined capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (scaffolding, code quality analysis, stack selection guidance) and 'when' with an explicit 'Use when...' clause containing numerous trigger phrases and scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural user phrases: 'scaffold a new project', 'create a Next.js app', 'set up FastAPI with React', 'analyze code quality', 'audit my codebase', 'what stack should I use', 'generate project boilerplate', plus broader terms like 'fullstack development', 'project setup', 'tech stack comparison'. | 3 / 3 |
Distinctiveness Conflict Risk | While the scaffolding and stack selection aspects are fairly distinct, terms like 'analyze code quality' and 'audit my codebase' could overlap with dedicated code review or linting skills. The 'fullstack development' trigger is also broad enough to potentially conflict with general coding skills. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured fullstack development skill with strong actionability and workflow clarity. The progressive disclosure is excellent, with appropriate separation between the overview and detailed reference guides. The main weakness is moderate verbosity—the trigger phrases section is unnecessary, and some parameter documentation is redundant with the usage examples.
Suggestions
Remove the 'Trigger Phrases' section entirely—this is metadata that belongs in frontmatter or the skill description, not in the body content.
Consider condensing the parameter tables since the usage examples already demonstrate the flags clearly; a single-line description per flag would suffice.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary content like the 'Trigger Phrases' section (Claude doesn't need to be told when to use a skill in this way) and the detailed parameter tables that largely repeat what's shown in the usage examples. The reference guide section is appropriately brief as summaries, but the overall document could be tightened. | 2 / 3 |
Actionability | Provides fully executable bash commands for all tools, clear parameter tables, and concrete sample output showing what to expect. The workflows include copy-paste ready command sequences with specific file paths and flags. | 3 / 3 |
Workflow Clarity | All three workflows are clearly sequenced with numbered steps. Workflow 1 includes a verification step (confirm package.json exists) and a quality check before proceeding. Workflow 2 explicitly includes a re-run validation step after fixing P0 issues, creating a proper feedback loop for the destructive/batch audit operation. | 3 / 3 |
Progressive Disclosure | The skill provides a clear table of contents, concise overviews of each tool and workflow inline, and appropriately delegates detailed content to one-level-deep reference files (references/architecture_patterns.md, references/development_workflows.md, references/tech_stack_guide.md) with clear descriptions of what each contains. | 3 / 3 |
Total | 11 / 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
- alirezarezvani/claude-skills
- Commit
f567c61
- 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.