coordinate-external-ag…
Coordinate independently operated external agents through durable handoffs. Use when work crosses hosts, sessions, accounts, services, queues, boards, pull…
Capture and interpret reproducible iOS Simulator performance and memory evidence. Use when an iOS issue needs ETTrace/symbolication, a memgraph, leak ownership traces, or before/after runtime proof rather than a code-only guess.
$ npx -y skills add gaelic-ghost/socket --skill ios-runtime-forensics-workflow --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/ios-runtime-forensics-workflowContext preview
The summary Claude sees to decide when to auto-load this skill.
Capture and interpret reproducible iOS Simulator performance and memory evidence. Use when an iOS issue needs ETTrace/symbolication, a memgraph, leak ownership traces, or before/after runtime proof rather than a code-only guess.
name: ios-runtime-forensics-workflow description: Capture and interpret reproducible iOS Simulator performance and memory evidence. Use when an iOS issue needs ETTrace/symbolication, a memgraph, leak ownership traces, or before/after runtime proof rather than a code-only guess.
Provide two explicit evidence modes for a reproducible iOS Simulator issue: `performance-trace` for focused ETTrace/symbolicated latency or CPU work, and `memory-graph` for retained-object and leak ownership analysis. This skill owns evidence shape, not normal app build, launch, or UI driving.
1. Apply the Apple docs gate through `explore-apple-swift-docs`. Confirm the current Xcode/Simulator evidence mechanism before acting. 2. Define one reproduction, start/stop boundary, target app build, simulator UDID, OS, Xcode version, and expected release or latency behavior. 3. Select exactly one mode: `performance-trace` or `memory-graph`. Do not mix CPU and ownership conclusions in one unsupported capture. 4. For `performance-trace`, read `references/performance-trace-evidence.md`, capture a focused trace with matching symbols, and identify hot stacks only after symbolication. 5. For `memory-graph`, read `references/memory-graph-evidence.md`, drive the release-producing flow, capture a memgraph, inspect app-owned retained types, and follow ownership evidence to the retaining path. 6. Make the smallest root-cause change, then recapture the same flow on the same simulator where practical. 7. Report the exact capture boundary, tool/version context, what the artifact proves, what it does not prove, and the before/after delta.
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,…