user-context

por openai

Cargar o gestionar las preferencias de enrutamiento de origen duraderas del complemento de Análisis de Datos, la lógica de incorporación, el progreso de configuración y el registro de la capa semántica.

npx skills add https://github.com/openai/role-specific-plugins --skill user-context

User Context

User Context stores the product and design references a designer uses often, so future Product Design work starts from the right sources.

Use this skill when the user asks to:

  • set up Product Design
  • get started with Product Design
  • onboard with Product Design
  • save product or design sources
  • see what Product Design remembers
  • update saved product or design context
  • remember a Product Design preference
  • setup my plugin

Critical Overrides

  • Refer to the Plugin router $index before proceeding.
  • Follow $critical-overrides.
  • Before offering onboarding or saving context for future conversations, confirm that local shell access is available, $CODEX_HOME can be resolved, and $CODEX_HOME/state/plugins/product-design/ exists and is writable or can be created in a writable parent directory. If user-context.md already exists, confirm that it is writable too.
  • If any check cannot be completed or fails, persistent context is unavailable. Do not offer saved-context onboarding or claim that new context was saved for future conversations. If the user asks to save something, explain that it can be used in the current conversation but not saved for future conversations.

Saved User Context

If user-context.md exists, use it by default.

Use saved product URLs, Figma files, screenshots, reference images, codebase paths, Storybook, tokens, design systems, brand assets, component refs, browser preferences, and share targets to ground Product Design work.

Ideation, prototypes, audits, clones, and critiques should match the saved product context unless the user asks for something different.

When a workflow needs visual grounding, attach or include relevant saved screenshots, reference images, tokens, design language, and component references in ImageGen, ideation, prototype, audit, and critique work.

State File

Saved context lives here:

$CODEX_HOME/state/plugins/product-design/user-context.md

Saved screenshots and reference images live next to it:

$CODEX_HOME/state/plugins/product-design/assets/

If the file does not exist, continue normally unless the user asks to set up Product Design, save context, or the current task is blocked by missing product/design context.

Preflight

When any Product Design workflow needs saved context, run:

python3 scripts/user_context_preflight.py

Use the returned saved entries as the starting context for the task.

If the script reports that no saved context exists, continue from the current user prompt unless setup context is required.

Do not browse, open, or inspect every saved reference during preflight. Inspect only the saved references needed for the current task.

Setup

Use references/onboarding.md when the user asks to set up Product Design, asks what Product Design can remember, asks what Product Design knows about their product, or provides product/design references to save.

For setup-only requests, explain what Product Design can remember and ask for useful sources.

Adjust the context-gathering request to match the user's request. First-time setup differs from updating existing context.

Do not inspect the workspace, install dependencies, scaffold a prototype, generate images, run audits, or start implementation during setup.

After the user provides references to save, run:

python3 scripts/init_user_context.py

Then add the references to the created user-context.md.

Save

Save useful, durable Product Design context:

  • Product URLs
  • Figma files
  • Screenshots and reference images
  • Codebase paths
  • Storybook and component docs
  • Design tokens and theme sources
  • Brand, logo, icon, illustration, image, and asset sources
  • Preferred browser, capture tools, and share targets
  • Team conventions that make future Product Design work more accurate

When the user provides screenshots or reference images to save, copy them into assets/ next to user-context.md and link them from the saved entry.

Give each saved image a clear, descriptive filename that says what the image shows. Use names future Product Design runs can understand without opening the file.

Good image names:

assets/chatgpt-settings-modal-dark-mode.png
assets/payment-sheet-mobile-error-state.png
assets/product-dashboard-sidebar-navigation.png
assets/storybook-primary-button-states.png
assets/brand-logo-lockup-purple-gradient.png
assets/onboarding-flow-welcome-step.png
assets/checkout-confirmation-screen.png
assets/account-menu-open-state.png

Do not save secrets, credentials, API keys, private tokens, copied customer data, or anything that should not persist.

Use this structure:

# {Category}

- Description: {what this category is and when future Product Design runs should use it}

## Saved Links And Context

{Saved reference or fact}
- Date Added: YYYY-MM-DD.
- File: assets/{clear-descriptive-name}.png
- Useful Context: {what this reference represents}
- Future Use: {how future Product Design work should use it}

Include File: only when the saved entry has a local image file.

When a category has no saved references yet, use exactly:

status: not provided

Keep saved context curated. Prefer a few high-value references over a dump of every possible URL or file.

Read

  • Do not treat status: not provided as a fact.
  • Read through scripts/user_context_preflight.py when local shell access is available.
  • Use saved context as default grounding, then inspect only what the current task needs.

Más skills de openai

release
openai
Realizar un lanzamiento de Symphony incrementando la versión confirmada, integrándola, etiquetando el commit fusionado y verificando el flujo de trabajo de lanzamiento de Burrito. Usar cuando se solicite…
signing-entitlements
openai
Inspeccionar problemas de firma, entitlements, runtime reforzado y Gatekeeper en aplicaciones de macOS. Usar cuando se solicite diagnosticar fallos de firma de código, entitlements faltantes,…
building-ai-agent-on-cloudflare
openai
Crea agentes de IA en Cloudflare usando el Agents SDK con gestión de estado, WebSockets en tiempo real, tareas programadas, integración de herramientas y chat…
epigraphdb-skill
openai
Envía solicitudes compactas a la API de EpiGraphDB para ontología, literatura, MR, genes-fármacos y evidencia de vías de soporte. Úsalo cuando un usuario desee resúmenes concisos de EpiGraphDB.
runtime-behavior-probe
openai
Planificar y ejecutar investigaciones de comportamiento en tiempo de ejecución con scripts de sonda temporales, matrices de validación, controles de estado e informes centrados en hallazgos. Usar solo cuando…
deep-security-scan
openai
Úsalo cuando el usuario solicite un escaneo de seguridad de Codex profundo, exhaustivo, de múltiples pasadas o que reduzca la varianza, en todo el repositorio o en una ruta específica. Ejecuta pasadas independientes repetidas…
define-security-policy
openai
Definir, revisar o actualizar la guía de SECURITY.md para un repositorio o componente. Úselo cuando el usuario quiera aclarar qué debe revisar Codex Security, qué está fuera de…
validation
openai
Usar cuando Codex ya está en la fase de validación de un escaneo de seguridad o el usuario solicita explícitamente determinar si uno o más posibles hallazgos de seguridad…