coordinate-external-ag…
Coordinate independently operated external agents through durable handoffs. Use when work crosses hosts, sessions, accounts, services, queues, boards, pull…
Diagnose SwiftUI rendering, scrolling, update, CPU, memory, image, layout, and animation performance from code and evidence. Use when a SwiftUI feature is slow, janky, broadly invalidating, memory-heavy, or needs a code-first audit before Instruments capture.
$ npx -y skills add gaelic-ghost/socket --skill swiftui-performance-audit --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/swiftui-performance-auditContext preview
The summary Claude sees to decide when to auto-load this skill.
Diagnose SwiftUI rendering, scrolling, update, CPU, memory, image, layout, and animation performance from code and evidence. Use when a SwiftUI feature is slow, janky, broadly invalidating, memory-heavy, or needs a code-first audit before Instruments capture.
name: swiftui-performance-audit description: Diagnose SwiftUI rendering, scrolling, update, CPU, memory, image, layout, and animation performance from code and evidence. Use when a SwiftUI feature is slow, janky, broadly invalidating, memory-heavy, or needs a code-first audit before Instruments capture.
Make performance work evidence-led: inspect the smallest relevant SwiftUI data-flow and view slice first, name code-level suspicion separately from runtime proof, then hand trace capture to the existing Xcode or SwiftPM testing workflow.
1. Apply the Apple docs gate through `explore-apple-swift-docs`. Confirm current Observation and SwiftUI behavior before proposing a performance change. 2. Collect the target view, reproduction steps, data flow, device/simulator, build configuration, and the observed symptom. 3. Classify the symptom as invalidation, identity churn, body computation, layout, image, animation, CPU, or retained-memory pressure. 4. Read `references/code-smells-and-remediation.md` and identify only code-backed suspicions. Mark each finding as suspected until a capture proves it. 5. Prefer narrow ownership, stable identity, precomputation outside `body`, downsampled images, localized state, and reduced layout complexity. Do not use `equatable()` or `@State` as an unmeasured cache. 6. When code inspection is insufficient, hand trace capture to `xcode-testing-workflow` for scheme/destination work or `swift-package-testing-workflow` for package-first workloads. 7. Compare the same reproduction before and after the change. Report CPU, frame behavior, allocations, and view-update evidence only when captured.
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,…