coordinate-external-ag…
Coordinate independently operated external agents through durable handoffs. Use when work crosses hosts, sessions, accounts, services, queues, boards, pull…
Design, implement, validate, and troubleshoot App Intents, App Entities, App Shortcuts, and system-surface integrations. Use when exposing a focused app action or content to Siri, Spotlight, Shortcuts, widgets, controls, Live Activities, or hardware interactions.
$ npx -y skills add gaelic-ghost/socket --skill app-intents-workflow --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/app-intents-workflowContext preview
The summary Claude sees to decide when to auto-load this skill.
Design, implement, validate, and troubleshoot App Intents, App Entities, App Shortcuts, and system-surface integrations. Use when exposing a focused app action or content to Siri, Spotlight, Shortcuts, widgets, controls, Live Activities, or hardware interactions.
name: app-intents-workflow description: Design, implement, validate, and troubleshoot App Intents, App Entities, App Shortcuts, and system-surface integrations. Use when exposing a focused app action or content to Siri, Spotlight, Shortcuts, widgets, controls, Live Activities, or hardware interactions.
Expose the smallest useful action and content surface outside an app without turning system integration into a second app architecture. Apple documents App Intents as the bridge that makes app actions and data discoverable in system experiences; select real user-recognizable verbs and entities before adding an intent type.
1. Apply the Apple docs gate through `explore-apple-swift-docs`. Confirm the framework, platform availability, and target system surface before changing code. 2. Define one user-recognizable verb and the minimum data it needs. Prefer an existing app domain type; do not invent a parallel intent-only repository, store, or DTO layer. 3. Classify the surface: direct action, parameterized action, entity lookup, App Shortcut, Spotlight result, widget/control action, Live Activity action, or hardware interaction. 4. Read `references/intent-entity-and-shortcut-shapes.md` for intent, entity, query, shortcut, and result patterns. Read `references/system-surfaces-and-validation.md` for indexing, extension boundaries, privacy, and validation. 5. Implement the narrow intent and make `perform()` call the existing domain action or explicit app handoff. Keep parameter confirmation, failures, and result output descriptive and user-facing. 6. Add `AppEntity` only when people need to select, search, or inspect app-owned content. Give entity display representations stable identifiers and use the appropriate query shape; do not expose private, transient, or unverifiable data. 7. Add App Shortcuts only for actions people plausibly invoke repeatedly. Use short, natural phrases and real parameter defaults rather than advertising every internal operation. 8. For widgets, controls, Live Activities, and Spotlight, validate the owning extension and system-surface contract rather than assuming the main app target alone is enough. 9. Validate discovery, parameter resolution, cancellation/failure behavior, app handoff, accessibility, and privacy on the intended platform. Record system-surface limitations separately from app behavior.
Stuff for Agents on macOS Promo audio: Socket Codex Marketplace Promo
Coordinate independently operated external agents through durable handoffs. Use when work crosses hosts, sessions, accounts, services, queues, boards, pull…
Assign worktree, branch, write, validation, integration, and cleanup ownership before parallel repository work. Use when a worker will inspect or modify…
Design framework-neutral agent and automation workflows before implementation. Use when choosing between Codex app automations, codex exec, Codex subagents,…
Design evaluation workflows for agent, skill, prompt, and automation behavior before implementation. Use when choosing eval cases, graders, thresholds,…
Design safe n8n workflows with deterministic routing, credentials, idempotency, recovery, local-model checks, drafts, and exact approval gates.
Coordinate bounded worker tasks with a launch envelope, report-back, escalation, and synthesis contract. Use before spawning, resuming, steering, cancelling,…