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".

72

Quality

88%

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

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 highly actionable with executable code and clear, validated workflows for risky database operations. The main weakness is a moderate amount of concept-explaining prose and inlined advanced detail that could be offloaded to reference files for better token efficiency.

Suggestions

Trim rationale prose that explains well-known concepts (e.g., the thundering-herd and circuit-breaker-state explanations) to one-line justifications, since Claude already knows these.

Move the full circuit-breaker, rate-limit, and alternate better-sqlite3 stack implementations into the references file, keeping only the decision rule and a minimal snippet inline.

Type the middleware signatures (req, res, next) and resolve the undefined verifyAccessToken so the auth code is fully copy-paste executable.

DimensionReasoningScore

Conciseness

Dense and largely efficient with executable code and decisive guidance, but includes some rationale prose explaining concepts Claude largely knows (thundering herd, circuit-breaker states, RLS rationale) that could be trimmed.

4 / 5

Actionability

Multiple copy-paste-ready code blocks (Prisma schema, Zod validators, middleware, better-sqlite3 repos, circuit breaker) covering common cases, with minor gaps like untyped (req, res, next) and undefined verifyAccessToken.

4 / 5

Workflow Clarity

Auth flow is numbered and migrations include an explicit zero-downtime checklist with a validation checkpoint (UP in staging → verify coexistence → DOWN → verify → promote), providing strong feedback loops for destructive/db operations.

5 / 5

Progressive Disclosure

Good section structure with a real, one-level-deep, clearly signaled reference (references/idempotencia-e-postgres-avancado.md), though substantial detailed code (circuit breaker, rate limiting, services, alternate stack) is inlined in SKILL.md that could live in references.

4 / 5

Total

17

/

20

Passed

Description

96%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.

A strong, well-structured description that names concrete actions and provides an explicit trigger list covering natural phrases and specific technologies. The only minor weakness is slight overlap risk with frontend API skills through generic terms like 'API' and 'endpoint'.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('schemas de banco, endpoints REST/GraphQL, validação server-side, autenticação, migrations') with comprehensive coverage of backend capabilities.

5 / 5

Completeness

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

5 / 5

Trigger Term Quality

Comprehensive trigger list with natural terms plus tech synonyms ('API', 'banco de dados', 'JWT', 'Prisma', 'PostgreSQL', 'Node.js', 'Express', 'NestJS', 'middleware', 'ORM').

5 / 5

Distinctiveness Conflict Risk

Clear backend niche anchored by specific tech (JWT, Prisma, PostgreSQL, NestJS); minor overlap risk with closely related frontend/API skills via shared terms 'API' and 'endpoint'.

4 / 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 (676 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.