CtrlK
BlogDocsLog inGet started
Tessl Logo

backend-expert

Especialista Senior en Python, FastAPI y Domain-Driven Design (DDD) para backend. Úsalo cuando necesites crear endpoints, modificar lógica de negocio, diseñar entidades, actualizar servicios o trabajar con bases de datos.

62

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 ./.agents/skills/backend-expert/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 well-structured, lean role skill with actionable per-layer procedures and a sensible progressive-disclosure split into reference files. Its weaknesses are missing validation/feedback steps in the feature and modification workflows (which involve database migrations) and small navigation defects: incorrect reference link paths and an orphaned standards.md bundle file.

Suggestions

Add an explicit validation checkpoint to the feature and modification SOPs (e.g., a final step: run the module's pytest suite and Alembic migration check before declaring done) so the DB-touching workflows have feedback loops and workflow clarity is no longer capped at 3.

Fix the reference link paths: the body points to "backend-expert/references/*.md" but the files live at "references/*.md" relative to SKILL.md — correct the links so navigation works.

Either reference "standards.md" from the knowledge-base section (it covers typing and code standards relevant to every task) or remove it from the bundle so all reference files are discoverable.

DimensionReasoningScore

Conciseness

The body is directive and lean — every section gives instructions (file paths, layer conventions, banned patterns) with no explanations of concepts Claude already knows. Minor trims are possible (persona framing "Actúas como un Arquitecto Backend Senior", the "Directiva Cero"/"Código como Documentación" branding), which keeps it at the 4 anchor rather than the fully lean 5.

4 / 5

Actionability

Concrete guidance throughout: exact doc paths ("docs/domains/INDEX.md"), concrete file patterns ("repositories/[nombre]_repository.py"), and specific syntax rules ("session.execute(select(Model))", soft delete via "deleted_at"). It falls short of the 5 anchor because some steps stay high-level ("Genera la migración de Alembic" with no command, "Crea los DTOs" with no schema example).

4 / 5

Workflow Clarity

The three SOPs are clearly sequenced (Inside-Out for features, code-first for modifications, Outside-In for bug fixes), but only the bug-fix flow has a validation checkpoint ("Red Test" reproduction, regression-test verification). The feature and modification SOPs include database migrations with no test or verification step, and the rubric caps workflow clarity at 3 when DB-touching workflows lack feedback loops — so this cannot score 4 despite the good sequencing.

3 / 5

Progressive Disclosure

The body is a clear overview with well-signaled, purpose-mapped references ("Estructura y DDD", "Base de Datos", "Testing") that are one level deep, and all three referenced files exist in the bundle. Minor organization gaps keep it below 5: the links point to "backend-expert/references/..." while the files actually live at "references/..." (broken relative paths), and the bundled "standards.md" is never referenced from the overview.

4 / 5

Total

15

/

20

Passed

Description

78%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 description with an explicit trigger clause, concrete action list, and a well-defined niche; it reads like the good examples in the rubric. Its only deductions are the second-person "Úsalo cuando necesites" phrasing and keyword coverage that omits common variations (API, tests, migrations).

DimensionReasoningScore

Specificity

The description lists several concrete actions ("crear endpoints, modificar lógica de negocio, diseñar entidades, actualizar servicios o trabajar con bases de datos") over a named domain, which matches the 4 anchor — but the explicit second-person trigger clause ("Úsalo cuando necesites...") incurs the rubric's 1-point voice penalty, bringing it to 3.

3 / 5

Completeness

It explicitly answers both what ("Especialista Senior en Python, FastAPI y Domain-Driven Design (DDD) para backend") and when ("Úsalo cuando necesites crear endpoints... trabajar con bases de datos") with a concrete 'Use when...' clause carrying five distinct trigger phrases, matching the 5 anchor.

5 / 5

Trigger Term Quality

Natural user-facing trigger phrases are present ("crear endpoints", "modificar lógica de negocio", "diseñar entidades", "actualizar servicios", "trabajar con bases de datos"), giving good keyword coverage; common variations like API, migraciones, tests, or refactor are missing, so it fits the 4 anchor rather than the comprehensive 5.

4 / 5

Distinctiveness Conflict Risk

The FastAPI + DDD backend niche is clearly distinct from frontend, DevOps, or data skills, but it would overlap with a generic Python/general-coding skill on phrases like "modificar lógica de negocio" or "actualizar servicios", matching the 4 anchor (minor overlap risk with closely related skills) rather than the minimal-conflict 5.

4 / 5

Total

16

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 missing, 3 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository
alpacapurpura/ap_sales_agent
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.