ux-agentico

UX agéntico Luana v4 (post pm-redesign 2026-05 Punto 4). Diseña FLUJOS CONVERSACIONALES (no UI tradicional) para agentic-stories state=refining. Toma 01-spec.md (de /po) y produce 02-design-agentic.md en docs/product/stories/{story-id}/ con: turn-by-turn happy path, state machine agente, tools sequence, prompt slot architecture, voice constraints, error recovery, eval policy (personas+rubrics+pass^k), cost/latency budget, observabilidad. Al ratificar diseño → transition state=refining→refined. Carga skills sales-agent-expert, copilot-expert, tessl__langgraph, claude-api. Si descubre edge cases → delta-spec.md → /po ratifica. Activa cuando user dice: '/ux-agentico', 'diseñemos el flujo conversacional', 'cómo conversa el agente', 'flujo del copilot', 'turn-by-turn', 'experiencia agéntica'.

Quality

81%

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

70%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 a well-sequenced, highly actionable 13-step workflow with concrete templates and strong validation/approval checkpoints. Its main weaknesses are moderate redundancy and the absence of any progressive-disclosure bundle files, leaving a fair amount of inlined detail in the single SKILL.md.

Suggestions

Extract the long input-path catalog and eval-policy templates into reference files (e.g. references/inputs.md, references/eval-policy.md) and link them one level deep from the relevant steps to reduce inlined bulk.

Consolidate the repeated scope/engine-vs-brand-extension rules that appear in the decision matrix, the 'Engine vs brand-extension scope' section, and Anti-patterns to remove redundancy.

Move or mark time-sensitive markers like 'v4 (post pm-redesign 2026-05)' and '2026-05-15' into a version/deprecation note so the main flow stays evergreen.

Dimension	Reasoning	Score
Conciseness	Mostly efficient — uses ASCII diagrams, tables, and code blocks rather than prose explaining known concepts — but includes some redundancy (scope rules and anti-patterns restate the decision matrix) and time-sensitive version markers ('v4', '2026-05-15') that could be tightened.	3 / 5
Actionability	Highly concrete guidance: exact file paths, a cache-aware slot architecture with TTLs, tool tables, eval-policy values, and cost budgets that are largely copy-paste-ready for the design artifact; minor gaps where example turns are skeleton/illustrative rather than fully fleshed out.	4 / 5
Workflow Clarity	Thirteen clearly numbered steps with explicit validation/approval checkpoints (Step 12 '¿Apruebas? ¿Cambios?' → 'Loop hasta aprobación'), hard gates, and STOP/escalate rules for risky scope changes; feedback loops are present for the iterative design process.	5 / 5
Progressive Disclosure	Well-organized into sections, but no bundle files exist and all detail (input-path catalog, eval policy templates, anti-patterns) is inlined in SKILL.md, so content that could be split into one-level-deep references instead makes this a single-file monolith.	3 / 5
	Total	15 / 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.

The description is comprehensive and third-person, explicitly covering both what the skill does and when to activate it, with a strong list of concrete capability areas and natural trigger phrases. The only minor gap is that some trigger terms are command-style rather than purely natural-language synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'turn-by-turn happy path, state machine agente, tools sequence, prompt slot architecture, voice constraints, error recovery, eval policy (personas+rubrics+pass^k), cost/latency budget, observabilidad' — giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both 'what' ('Diseña FLUJOS CONVERSACIONALES...produce 02-design-agentic.md...con:') and 'when' ('Activa cuando user dice: ...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Provides several natural trigger phrases a user would say ('diseñemos el flujo conversacional', 'cómo conversa el agente', 'flujo del copilot', 'turn-by-turn', 'experiencia agéntica') plus the command '/ux-agentico'; good coverage though a few terms lean technical/command-style rather than natural synonyms.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — conversational flow design for agentic stories — with specific triggers that distinguish it from the /po-ux UI-standard skill, yielding minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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

	Total	14 / 16 Passed

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

Reviewed: ~22 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.