Name: backend-expert
Rating: 72 (1 reviews)
Author: alpacapurpura

backend-expert

Implements FastAPI endpoints, creates SQLAlchemy 2.0 async models, generates idempotent Alembic migrations, structures bounded contexts following DDD (domain→infrastructure→application→api), and produces typed Pydantic v2 DTOs. Runs inside Docker (visionarias_brain_dev). Use when: 'create an endpoint', 'modify the backend', 'create a new entity', 'update a service', 'database logic', 'fix a backend bug', 'add a migration', 'create a repository', 'agrega un campo', 'nueva ruta API', 'corrige el servicio', or any Python/FastAPI/SQLAlchemy/Alembic task.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

The canonical home for this skill is backend-expert in alpacapurpura/luana-method

Quality

Content

85%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.

A dense, well-structured SOP with executable patterns, three sequenced workflows, and strong validation/feedback loops for destructive and batch operations. Progressive disclosure is good and references are real, though one reference path is inconsistent and a few constraints are duplicated.

Suggestions

Resolve the runtime-quality-checklist.md path mismatch: the body links backend-expert/references/runtime-quality-checklist.md but the bundle file is at references/runtime-quality-checklist.md.

De-duplicate the SQLAlchemy 2.0 constraint, which appears both in the quick-reference patterns block and again in the CRITICAL constraints section.

Consolidate the runtime-quality-checklist references (it is called out in the runtime checklist section, the Constraints section, and the Project invariants section) into a single canonical pointer.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's competence; code snippets and checklists are tight with little padding. A few constraints are repeated across sections (e.g. SQLAlchemy 2.0 and runtime-quality-checklist referenced twice), which keeps it just below a 5.	4 / 5
Actionability	Concrete executable code (correct vs prohibited SQLAlchemy, Pydantic DTO, idempotent Alembic raw SQL) and specific commands (make extraction-contract, make arch-test) cover common cases. Minor gaps: some workflow steps point to references rather than giving inline detail, and a few steps are directive without code.	4 / 5
Workflow Clarity	Three clearly sequenced workflows (Inside-Out, Code-First, Outside-In) with mandatory TDD RED steps, an OBLIGATORIO runtime-quality checklist gate, and an analytics extraction-contract feedback loop (update contract -> regen md -> run architecture test -> single commit) that includes explicit validation checkpoints.	5 / 5
Progressive Disclosure	Well-signaled one-level-deep references to real files in references/ (architecture-rules, database, testing, standards, runtime-quality-checklist, etc.) with a clear "leer solo cuando aplique" section. One path inconsistency (body cites backend-expert/references/runtime-quality-checklist.md while the file lives at references/runtime-quality-checklist.md) keeps it below a 5.	4 / 5
	Total	17 / 20 Passed

Description

92%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 highly specific, third-person description that covers what the skill does and when to use it with concrete bilingual trigger phrases. It is dense but every clause earns its place and conflict risk is low given the niche framing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Implements FastAPI endpoints", "creates SQLAlchemy 2.0 async models", "generates idempotent Alembic migrations", "structures bounded contexts following DDD", "produces typed Pydantic v2 DTOs") with comprehensive coverage of the backend domain.	5 / 5
Completeness	Explicitly answers both "what" (the enumerated capabilities) and "when" via a clear "Use when:" clause with concrete trigger phrases, satisfying both halves concretely.	5 / 5
Trigger Term Quality	Strong natural trigger coverage including bilingual phrases users would say ("create an endpoint", "add a migration", "agrega un campo", "nueva ruta API", "corrige el servicio") plus broad tech terms, though some are command-style rather than conversational synonyms.	4 / 5
Distinctiveness Conflict Risk	A clear niche (FastAPI/SQLAlchemy 2.0/Alembic/DDD backend work inside a named Docker container) with specific bilingual triggers makes overlap with other skills minimal.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing, 1 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: alpacapurpura/ap_sales_agent
Path: .claude/skills/backend-expert/SKILL.md
Commit: d31f7bc

Reviewed: ~19 hours ago

Table of Contents

Discovery Implementation Validation

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.