backend-api
Skill do Backend Developer para definição de APIs, banco de dados, e lógica de servidor. Use quando precisar definir schemas de banco, endpoints REST/GraphQL, validação server-side, autenticação, migrations, ou qualquer lógica de backend. Trigger em: "API", "endpoint", "banco de dados", "schema", "migration", "backend", "servidor", "autenticação", "JWT", "middleware", "ORM", "Prisma", "PostgreSQL", "Node.js", "Express", "NestJS", "validação server-side".
77
71%
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/03-backend-api/SKILL.mdQuality
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 skill description that clearly defines its scope as backend development, lists concrete capabilities, and provides explicit trigger guidance with a comprehensive keyword list. The main weakness is its broad scope covering nearly all backend concerns, which could create overlap with more specialized skills in a large skill library. The description uses appropriate third-person voice and is well-structured.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: defining API schemas, database schemas, REST/GraphQL endpoints, server-side validation, authentication, migrations, and backend logic. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (defining APIs, database schemas, server logic, authentication, migrations) and 'when' with an explicit 'Use quando precisar...' clause and a dedicated 'Trigger em:' list of keywords. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including both general terms ('API', 'endpoint', 'banco de dados', 'backend', 'servidor') and specific technologies ('JWT', 'Prisma', 'PostgreSQL', 'Node.js', 'Express', 'NestJS', 'ORM'). These are terms users would naturally use when requesting backend work. | 3 / 3 |
Distinctiveness Conflict Risk | While the backend focus is clear, terms like 'API', 'banco de dados', and 'validação' could overlap with frontend API consumption skills, database administration skills, or full-stack skills. The scope is broad enough ('qualquer lógica de backend') that it could conflict with more specialized backend skills. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is highly actionable with excellent, executable code examples covering the full backend stack (Prisma, Zod, Express middleware, services). However, it is significantly over-verbose for a SKILL.md, inlining ~200+ lines of code that should be in referenced guide files, and includes boilerplate sections (inputs/outputs, when to use) that add little value. The workflow could be improved with explicit validation checkpoints for the overall development process.
Suggestions
Move the large code blocks (Prisma schema, validators, middleware, base service) into `docs/skill-guides/backend-api.md` or separate reference files, keeping only minimal representative snippets inline in SKILL.md.
Remove sections that describe process metadata Claude doesn't need (Quando Usar/Não Usar, Entradas/Saídas Esperadas, Evidência de Conclusão) or compress them to 1-2 lines each.
Add explicit validation checkpoints to the development workflow: e.g., 'After schema change → run `npx prisma validate` → run `npx prisma generate` → verify types compile' and 'Before handoff → validate OpenAPI spec → run integration tests'.
Trim explanations of standard patterns Claude already knows (REST verb conventions, JWT flow basics, pagination query params) to just the project-specific conventions and deviations.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines, inlining extensive code examples (full Prisma schemas, multiple middleware files, base service patterns, validation schemas) that could easily be in referenced files. It also explains conventions Claude already knows (REST verbs, pagination patterns, JWT flow) and includes sections like 'Quando Usar/Não Usar', 'Entradas/Saídas Esperadas', and 'Evidência de Conclusão' that add process overhead without actionable value. | 1 / 3 |
Actionability | The skill provides fully executable, copy-paste ready code examples throughout: complete Prisma schema, Zod validators with proper TypeScript types, middleware implementations, base service pattern, and specific endpoint patterns. All code is concrete and directly usable. | 3 / 3 |
Workflow Clarity | The migration strategy section includes a clear multi-step zero-downtime process with rollback guidance, and the auth flow is well-sequenced. However, there are no explicit validation checkpoints for the overall backend development workflow (e.g., 'run tests after schema change', 'validate OpenAPI spec before handoff'), and the migration section lacks a concrete 'validate -> fix -> retry' feedback loop. | 2 / 3 |
Progressive Disclosure | The skill references `docs/skill-guides/backend-api.md` for extended examples and multiple policy files, which is good. However, the massive amount of inline code (Prisma schema, validators, middleware, services) should be in referenced files rather than inline, making this a monolithic document that would benefit greatly from splitting content into separate reference files. | 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
- felvieira/claude-skills-fv
- Commit
e9f6648
- 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.