Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Design An Interface

ASecurity

Design-an-interface skill with N=3 parallel alternatives and architectural vocabulary. Use when designing a new module interface, when user mentions 'varias alternativas', 'design this module', or '/design-an-interface'.

50 stars
0 votes
0 copies
0 views
Added 9/27/2026
ai-agentsgobash

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 10/5/2026

$npx -y skills add gonzalezpazmonica/savia --skill design-an-interface --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Design An Interface?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Design An Interface
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/gonzalezpazmonica-design-an-interface/badge)](https://www.skillsdirectory.com/skills/gonzalezpazmonica-design-an-interface)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
layer: peripheral
name: design-an-interface
description: "Design-an-interface skill with N=3 parallel alternatives and architectural vocabulary. Use when designing a new module interface, when user mentions 'varias alternativas', 'design this module', or '/design-an-interface'."
metadata:
  # --- metadata.savia.* (SE-333) ---
  savia.attribution: "Clean-room re-implementation of mattpocock/skills/design-an-interface (MIT, 26.4k*). Prose and process are original."
  savia.maturity: beta
  savia.category: architecture
  savia.context: fork
  savia.context_cost: medium
  savia.priority: high
  savia.se: SE-087
  savia.tags: "architecture, interface-design, parallel-agents, sdd"
---

# Skill: Design an Interface

> **Attribution**: Clean-room re-implementation of `mattpocock/skills/design-an-interface` (MIT). SE-087.

Genera 3 disenos alternativos de interfaz en paralelo y consolida en tabla comparativa con recomendacion justificada.

## Authoritative Paths

> Lee estos paths antes de actuar.

| Para | Lee este path |
|---|---|
| Vocabulario arquitectonico | `docs/rules/domain/architectural-vocabulary.md` |
| Codigo existente del proyecto | `projects/<nombre>/` |
| Specs SDD activas | `docs/propuestas/SPEC-*.md` |
| Reglas de dominio | `docs/rules/domain/` |

## Cuando usar

- Se necesita disenar una interfaz nueva para un modulo y no hay precedente claro.
- Se quiere comparar enfoques antes de comprometerse con uno.
- La spec SDD requiere definicion de interfaz antes de implementar.

## Cuando NO usar

- La interfaz ya existe y solo necesita extension — leer el codigo y ampliar.
- El scope es un metodo privado o una funcion de utilidad (demasiado granular).
- La interfaz tiene un patron establecido en el proyecto — seguir el patron existente.

## Decision Checklist

1. El modulo esta definido con nombre y contexto de uso? Si NO: solicitar antes de continuar.
2. Hay restricciones conocidas (rendimiento, compatibilidad, framework)? Si NO: asumir ninguna y documentarlo.
3. Existe codigo relacionado en el proyecto? Si SI: designar como base para Diseno C.

### Abort Conditions

- Si el nombre del modulo es vago o el contexto insuficiente: pedir aclaracion y abortar.
- Si las restricciones implican un unico diseno posible: no lanzar alternativas, documentar la restriccion.

## Workflow

`Recibir → Lanzar 3 sub-agentes paralelos → Consolidar tabla → Recomendar`

### Sub-agentes en paralelo (mismo mensaje, sin dependencias)

Agent tool (Task en OpenCode) con `subagent_type=architect`; cada prompt incluye el vocabulario de SE-082.

**A — Maxima simplicidad**: minimo metodos, sin estado, facilidad de uso.
**B — Maxima flexibilidad**: extensible, plugin-friendly, facil de mockear.
**C — Pragmatico**: equilibrio A+B, inspirado en codigo existente del proyecto.

### Formato de output de cada sub-agente

```
Interface: <NombreInterfaz>
Methods:
  - <metodo>(<param>: <tipo>): <retorno>
Invariants:
  - <descripcion>
Trade-offs:
  + <ventaja>
  - <desventaja>
```

### Consolidacion

Tabla comparativa con columnas: Criterio | Diseno A | Diseno B | Diseno C.
Criterios minimos: numero de metodos, estado requerido, testabilidad, extension futura, coherencia con codigo existente.

### Recomendacion

Un parrafo usando vocabulario de `docs/rules/domain/architectural-vocabulary.md`:
- **Module**, **Interface**, **Seam**, **Depth**, **Leverage**, **Locality**.
- Justificar por que el diseno elegido maximiza Depth y Locality para el contexto dado.

## Outputs esperados

- Tabla comparativa de los 3 disenos.
- Recomendacion con justificacion en vocabulario arquitectonico.
- Opcionalmente: fichero `docs/propuestas/<modulo>-interface-design.md` si se requiere trazabilidad.
  Sin frontmatter no entra en `INDEX.md`. Con frontmatter, regenera el indice o el gate `--check` de validate-ci-local falla:

```bash
bash scripts/propuestas-index-gen.sh
```

## Memory hooks

Cuando la usuaria elige diseno, guardarlo (`--source` es obligatorio por SE-072; sin el, exit 1 y no se guarda nada):

```bash
bash scripts/memory-store.sh save --type decision --title "interface design: <modulo>" \
  --content "<diseno elegido y por que>" --source user:explicit
```

## Related

- Rule: `docs/rules/domain/architectural-vocabulary.md` (SE-082 — vocabulary obligatorio en outputs)
- SE-074: `scripts/parallel-specs-orchestrator.sh` — disenos grandes (>1h por agente). Solo acepta IDs de spec en `docs/propuestas/` (no hay "design tracks"): escribir cada alternativa como spec y planificar antes de lanzar:
  `bash scripts/parallel-specs-orchestrator.sh --dry-run <SPEC-A> <SPEC-B> <SPEC-C>`
- Skill: `.opencode/skills/spec-driven-development/SKILL.md`
- Agent: `.opencode/agents/architect.md`
- Roadmap: `docs/ROADMAP.md`

Attribution

gonzalezpazmonicagonzalezpazmonica
View sourceSee grades on GitHubMore from gonzalezpazmonica →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →