CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

64

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/03-backend-api/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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.

The body is a dense, actionable reference with strong executable examples and good offloading of the deepest detail to a real reference file. It loses points for inlining standard patterns Claude already knows and for being a pattern catalog without consistent validated workflows.

Suggestions

Move standard, well-known patterns (basic CRUD endpoint list, Zod basics, JWT login/refresh/logout flow) into a reference file or trim them, keeping only the non-obvious team conventions inline to improve conciseness.

Add explicit validation checkpoints to the core operations — e.g., a validate-fix-retry loop for schema/migration changes and a verification step after creating endpoints — to raise workflow clarity above the pattern-catalog baseline.

Close the minor executable gaps in the code samples (define or import `verifyAccessToken`, type the Express middleware args, avoid `model: any`) so examples are fully copy-paste ready.

DimensionReasoningScore

Conciseness

Mostly efficient and rich with non-obvious team decisions (per-endpoint rate limiting, jitter, circuit-breaker states, idempotency), but ~670 lines inline several standard patterns Claude already knows (basic CRUD, Zod basics, JWT flow) that could be tightened.

3 / 5

Actionability

Largely executable copy-paste code across Prisma, Zod, middleware, retry, circuit breaker, and better-sqlite3 patterns, with minor gaps such as the undefined `verifyAccessToken`, `model: any`, and untyped req/res/next signatures.

4 / 5

Workflow Clarity

A pattern catalog rather than a unified workflow: the zero-downtime migration checklist and auth flow are well-sequenced with rollback/staging checkpoints, but most operations (endpoint creation, schema changes) lack explicit validate-then-fix-retry feedback loops.

3 / 5

Progressive Disclosure

Well-sectioned with clearly signaled one-level-deep references to the existing `references/idempotencia-e-postgres-avancado.md` (cited twice), but substantial code and detail remain inlined in the body that could live in reference files.

4 / 5

Total

14

/

20

Passed

Description

95%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.

The description is specific, comprehensive, and clearly distinguishes the skill with strong trigger coverage and explicit when-guidance. The only demerit is the second-person imperative voice, which the rubric penalizes on specificity.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('schemas de banco, endpoints REST/GraphQL, validação server-side, autenticação, migrations') with comprehensive coverage, but the imperative second-person 'Use quando precisar' triggers the rubric's voice penalty (-1) from a clear 5.

4 / 5

Completeness

Explicitly answers both 'what' ('definição de APIs, banco de dados, e lógica de servidor') and 'when' ('Use quando precisar...' plus 'Trigger em:...') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Comprehensive natural terms including synonyms and specific stack names — 'API', 'endpoint', 'banco de dados', 'JWT', 'middleware', 'Prisma', 'PostgreSQL', 'Node.js', 'Express', 'NestJS' — matching the anchor for full coverage with synonyms and tech extensions.

5 / 5

Distinctiveness Conflict Risk

Clear backend niche with distinct triggers (JWT, Prisma, PostgreSQL, NestJS, migrations) that separate it from a frontend skill, with minimal overlap risk.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (678 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
felvieira/claude-skills-fv
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.