architect

Architect orchestrator Luana v4 (post pm-redesign 2026-05 Punto 4). Lee 01-spec.md (de /po-ux o /po) + 02-design-agentic.md (si agentic) en stories state=refined. Decide qué surfaces toca (BE/FE/agentic). Spawna `architect-orchestrator` (single agent type, full-stack) que internamente carga las skills `architect-be` + `architect-fe` + `architect-agentic` según surface — produce 03-arch.md consolidado + 03-arch-{be,fe,agentic}.md por surface en una sola pasada. Reúne y produce el READY PACKAGE: 03-arch.md (consolidado) + 04-validators.yaml (★CRITICAL — pytest/playwright/shell commands must_pass:true ejecutables, 4 categories: non_functional/functional/visual/agentic_eval) + 05-guidelines.md (patterns required/forbidden + files in scope) + 06-tickets.yaml (work units atómicos). Cierra story state refined → ready. Activa cuando user dice: '/architect', 'diseñemos la arq', 'tickets', 'qué tickets salen', 'arquitectura técnica', 'cómo lo construimos técnicamente', 'cerrá el ready package'.

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

Quality

Content

77%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 content is highly actionable and well-sequenced with strong validation feedback loops, but it suffers from verbosity and a monolithic structure where large templates are inlined instead of split into reference files. Version-history annotations add token cost without execution value.

Suggestions

Move the large 04-validators.yaml and 05-guidelines.md templates into separate reference files under references/ and link to them inline, reducing the body to an overview.

Remove or relocate the 'Histórico' rationale blocks and scattered version-cement dates ('2026-05-08', '2026-05-19') to an 'old patterns' section so they no longer pad the active workflow.

Consolidate the repeated v4.1 rule statements that recur across Steps 5–8 into a single canonical constraints section to cut redundant tokens.

Dimension	Reasoning	Score
Conciseness	The body is ~711 lines and densely actionable but padded with internal version-history annotations ('post pm-redesign 2026-05 Punto 4', 'formalized 2026-05-08 después del 2do uso exitoso', 'cement 2026-05-19') and 'Histórico' rationale blocks that add tokens without aiding execution.	3 / 5
Actionability	Fully executable — concrete Agent() spawn template with complete prompt, copy-paste YAML templates for 04-validators/06-tickets, concrete file paths and shell commands (pytest/playwright/vitest) covering the common cases.	5 / 5
Workflow Clarity	Clear 9-step sequence with explicit validation checkpoints (Step 3 cross-module audit, Step 4 verify 03-arch.md, Step 8 ready-package checklist) and feedback loops via the iteration policy (on_fail/on_cap_reached) for a destructive/batch-style operation.	5 / 5
Progressive Disclosure	No bundle files exist; the SKILL.md is a monolithic ~711-line document with large inlined templates (the 04-validators.yaml template alone spans ~250 lines, the 05-guidelines template ~100 lines) that belong in separate reference files, and external references are only listed at the end rather than well-signaled inline.	3 / 5
	Total	16 / 20 Passed

Description

100%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 concrete and comprehensive, naming specific artifacts and actions, providing natural trigger phrases, and explicitly stating both what the skill does and when to activate it. It is highly distinct from other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Lee 01-spec.md', 'Spawna architect-orchestrator', 'carga las skills architect-be + architect-fe + architect-agentic', 'produce 03-arch.md consolidado + 03-arch-{be,fe,agentic}.md', and the full READY PACKAGE of four named artifacts — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (spawn orchestrator, produce 03-arch/04-validators/05-guidelines/06-tickets) and 'when' via the explicit 'Activa cuando user dice:' clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases a user would actually say — '/architect', 'diseñemos la arq', 'tickets', 'qué tickets salen', 'arquitectura técnica', 'cómo lo construimos técnicamente', 'cerrá el ready package' — covering synonyms and command forms.	5 / 5
Distinctiveness Conflict Risk	Clear niche as architect orchestrator producing a ready package with distinct triggers ('/architect', 'arquitectura técnica', 'cómo lo construimos técnicamente') that are unlikely to fire for unrelated skills.	5 / 5
	Total	20 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (719 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	12 / 16 Passed

Repository: alpacapurpura/luana-method
Path: claude/skills/architect/SKILL.md
Commit: caa08df

Reviewed: ~21 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.