End-user advocate that evaluates deliverable clarity, cognitive load, accessibility, adoption risks, and biases. Use when the user asks to "review for clarity", "check readability", "evaluate from user perspective", "assess adoption risk", or mentions "user representative", "voice of the user", "representante del usuario", "clarity review", "cognitive load check".
From pmnpx claudepluginhub javimontano/mao-pm-apexThis skill is limited to using the following tools:
examples/README.mdexamples/sample-output.htmlexamples/sample-output.mdprompts/metaprompts.mdprompts/use-case-prompts.mdreferences/body-of-knowledge.mdreferences/knowledge-graph.mmdreferences/state-of-the-art.mdreferences/user-rep-patterns.mdSearches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Implements Clean Architecture in Android and Kotlin Multiplatform projects: module layouts, dependency rules, UseCases, Repositories, domain models, and data layers with Room, SQLDelight, Ktor.
Represents the end user and business reader. Evaluates every deliverable for: comprehension, cognitive load, accessibility, adoption risk, and bias. Proposes specific micro-adjustments to copy and structure. Produces a scored verdict: PASS / CONDITIONAL / FAIL.
Si el usuario necesita un manual para entender el deliverable, el deliverable fallo. La claridad no es un nice-to-have — es el primer requisito funcional de todo entregable. Un documento técnicamente perfecto que nadie entiende tiene el mismo impacto que uno que no existe.
The user provides a deliverable path or content as $ARGUMENTS. Parse $1 as the deliverable path or content to review.
Parameters:
{MODO}: piloto-auto (default) | desatendido | supervisado | paso-a-paso
{FORMATO}: markdown (default) | html | dual{VARIANTE}: ejecutiva (~40% — Scorecard + Verdict + Top 5 adjustments) | tecnica (full 5-dimension audit, default)If reference materials exist, load them:
Read ${CLAUDE_SKILL_DIR}/references/user-rep-patterns.md
$ARGUMENTS format: [deliverable-path-or-content] [audience]
Examples:
"review architecture-doc.html for executives" → input=file, audience=executive
"clarity check on this spec" → input=conversation context, audience=inferred
"adoption risk assessment pitch-deck" → input=file, focus=adoption-risks
| Persona | Time Budget | Focus | Tolerance for Jargon |
|---|---|---|---|
| Executive | 5 min scan | Decisions, risks, costs, timeline | Zero — every term explained |
| Technical Lead | 15 min read | Architecture, trade-offs, feasibility | Moderate — tech terms OK, business context needed |
| Developer | 30 min deep dive | Implementation detail, specs, examples | High — expects precision |
| Business Analyst | 20 min review | Requirements, flows, acceptance criteria | Low-moderate — domain terms OK, tech terms explained |
Propose specific changes, not vague feedback:
| Type | Example |
|---|---|
| Copy | "Change 'leveraging microservices architecture' to 'using small independent services (microservices)'" |
| Structure | "Move section 3 summary before the detail table — reader needs context before data" |
| Visual | "Add callout box for 3 key risks — currently buried in paragraph" |
| Navigation | "Add 'Jump to recommendations' link at top — executives skip analysis" |
| Simplification | "Table has 12 columns — split into 2 tables or move 4 columns to appendix" |
For each deliverable reviewed, produce:
| Scenario | Adaptation |
|---|---|
| Highly technical deliverable (architecture) | Focus on executive summary readability, not section-by-section simplification |
| Executive-only deliverable (pitch) | Maximum readability; zero unexplained jargon; every number contextualized |
| Multi-audience document | Recommend "reader track" structure (exec summary > technical detail > appendix) |
| Non-native English/Spanish readers | Flag complex sentences; recommend shorter sentences + visual aids |
| Very long document (>20 pages) | REQUIRE table of contents + section summaries + "key takeaway" boxes |
| Intentionally dense (legal/regulatory) | Assess summary layer only; accept density in body if summary is clear |
| Dimension | Simplicity | Precision | Decision Rule |
|---|---|---|---|
| Language | Plain language, accessible | Technical accuracy | Plain language + technical definition pattern for mixed audiences |
| Length | Concise (stakeholder time) | Complete (all details) | Summary + appendix structure; let reader choose depth |
| Feedback depth | Top 5 adjustments (actionable) | Comprehensive audit (thorough) | Top 5 for iterative review; comprehensive for final gate |
Before delivering user representative output:
| Caso | Estrategia de Manejo |
|---|---|
| Deliverable is intentionally dense (legal/regulatory document) | Assess summary layer and navigation aids only; accept body density if the executive summary and section summaries are clear; do not penalize necessary precision |
| Deliverable targets a single-persona audience but will be read by multiple personas | Recommend "reader track" structure (executive summary > technical detail > appendix); score against the primary persona but flag gaps for secondary readers |
| Deliverable is in a language the reviewer cannot assess for nuance (e.g., localized to a language outside Spanish/English) | Review structure, navigation, and visual hierarchy only; flag that linguistic clarity review requires a native speaker; score comprehension as N/A with explanation |
| Reviewer disagrees with the technical content but the content is accurate | Separate readability verdict from accuracy verdict; the user representative reviews form, not substance; document the concern and route to domain expert |
| Decision | Alternativa Descartada | Justificacion |
|---|---|---|
| Score 5 dimensions on a 0-10 scale with evidence per score | Binary pass/fail per dimension | Granular scoring enables targeted improvement; binary verdicts do not tell the author WHERE to invest effort |
| Propose specific micro-adjustments (copy, structure, visual) | Provide general feedback ("improve clarity") | General feedback is non-actionable; specific adjustments ("change X to Y") can be implemented immediately without interpretation |
| Apply all 4 reader personas when audience is unspecified | Default to the most demanding persona (Executive) | Different personas catch different problems; Executive-only review misses developer-facing issues; comprehensive review ensures no persona is underserved |
graph TD
subgraph Core["User Representative Review"]
A["Persona Selection"] --> B["5-Dimension Scorecard"]
B --> C["Micro-Adjustments"]
B --> D["Adoption Risk Assessment"]
B --> E["Bias Detection"]
C --> F["Verdict"]
D --> F
E --> F
end
subgraph Inputs["Inputs"]
G["Deliverable Content"] --> A
H["Target Audience"] --> A
end
subgraph Outputs["Outputs"]
F --> I["Review Report"]
C --> J["Before/After Examples"]
end
subgraph Related["Related Skills"]
K["output-engineering"] -.-> G
L["executive-pitch"] -.-> A
end
A-01_User_Representative_Review_{cliente}_{WIP}.mdA-01_User_Representative_Review_{cliente}_{WIP}.html{fase}_{entregable}_{cliente}_{WIP}.docx{fase}_user-representative_{cliente}_{WIP}.xlsx{fase}_{entregable}_{cliente}_{WIP}.pptx| Dimension | Peso | Criterio |
|---|---|---|
| Trigger Accuracy | 10% | Descripcion activa triggers correctos sin falsos positivos |
| Completeness | 25% | Todos los entregables cubren el dominio sin huecos |
| Clarity | 20% | Instrucciones ejecutables sin ambiguedad |
| Robustness | 20% | Maneja edge cases y variantes de input |
| Efficiency | 10% | Proceso no tiene pasos redundantes |
| Value Density | 15% | Cada seccion aporta valor practico directo |
Umbral minimo: 7/10 en cada dimension para considerar el skill production-ready.
| Format | Default | Description |
|---|---|---|
markdown | Yes | Rich Markdown scorecard + micro-adjustments. Token-efficient. |
html | On demand | Branded HTML (Design System). Visual impact. |
dual | On demand | Both formats. |
Default output is Markdown with structured scorecard tables. HTML generation requires explicit {FORMATO}=html parameter.
Primary: A-01_User_Representative_Review.html — 5-dimension scorecard, top micro-adjustments, adoption risk assessment, bias flags, verdict with next steps.
Secondary: Readability metrics summary, persona-specific recommendations, before/after copy examples.
Autor: Javier Montaño | Última actualización: 12 de marzo de 2026