CtrlK
BlogDocsLog inGet started
Tessl Logo

architect-be

Sub-architect Backend. Invocado por /architect orchestrator. Lee 01-spec.md + (02-design-ui.md si mixed) + story YAML. Produce 03-arch-be.md con: endpoints, DTOs Pydantic, SQLA models, migrations idempotent, services, repositories, tests requeridos, cross-cutting (tenant isolation, currency, master-data, PII). Cross-module audit obligatorio. Activa cuando /architect spawna o user dice: '/architect-be', 'arq backend', 'diseña BE'.

72

Quality

89%

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

82%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 technical-design workflow that is token-efficient and highly actionable, with clear sequencing and validation gates. Main gaps are placeholder-substitution in code examples and the absence of an explicit retry feedback loop.

Suggestions

Add a brief validate→fix→retry loop after Step 1's cross-module audit (e.g., re-run grep and re-check overlap before committing to EXTEND/NEW) to strengthen workflow_clarity.

Where placeholders like `<kw>` and `{module}` appear, include one fully-resolved concrete example so the code is copy-paste runnable.

Consider moving the large DTO/SQLA/migration code templates into a referenced template file to reduce inline bulk and improve progressive_disclosure.

DimensionReasoningScore

Conciseness

Lean and token-efficient: terse directives, compact tables, and focused code blocks with no explanation of concepts Claude already knows (no primers on FastAPI, Pydantic, or SQLAlchemy); every line earns its place.

5 / 5

Actionability

Provides concrete, mostly executable guidance (DTO/SQLA model skeletons, `op.execute` migration snippets, grep commands), but relies on placeholders like `<kw>` and `{module}` that require substitution before running, leaving minor gaps versus copy-paste-ready code.

4 / 5

Workflow Clarity

Clear four-step sequence with explicit checkpoints (Step 1 overlap-decision branches, Step 3 "REVIEW FAIL automático" gate, top-of-file HARD GATE), but lacks a validate→fix→retry feedback loop within the skill itself.

4 / 5

Progressive Disclosure

Well-organized into clearly labeled sections (Skills cargados, Workflow, Anti-patterns, Output format) with a one-level-deep, clearly signaled external reference ("Seguir template docs/specs/templates/03-arch-template.md"); no nested or buried references, though the bulk of detail lives inline in this single file.

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 dense, highly specific description that clearly states what it does and when to activate it, with natural trigger terms and explicit scope boundaries against sibling skills. Only minor overlap risk via the shared /architect orchestrator spawn.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and outputs ("Lee 01-spec.md", "Produce 03-arch-be.md con: endpoints, DTOs Pydantic, SQLA models, migrations idempotent, services, repositories, tests requeridos, cross-cutting"), giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both what (reads spec + produces 03-arch-be.md with enumerated sections) and when ("Activa cuando /architect spawna o user dice...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Provides several natural trigger phrases a user of this workflow would say ("'/architect-be'", "'arq backend'", "'diseña BE'") plus the orchestrator spawn condition, covering synonyms and variations.

5 / 5

Distinctiveness Conflict Risk

Clear backend-architecture niche with distinct triggers and explicit boundaries ("Diseñar agentic surfaces (eso es /architect-agentic)", "Diseñar FE (eso es /architect-fe)"), but it shares the /architect orchestrator spawn path with sibling sub-architect skills, leaving minor overlap risk.

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

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.