coordinate-external-ag…
Coordinate independently operated external agents through durable handoffs. Use when work crosses hosts, sessions, accounts, services, queues, boards, pull…
Guide Swift Testing, XCTest holdouts, code coverage, xctestplan handoff conditions, async test design, semantic accessibility-test boundaries, test-fixture organization, and package test-diagnosis work in existing Swift Package Manager repositories. Use when Package.swift is the
$ npx -y skills add gaelic-ghost/socket --skill swift-package-testing-workflow --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/swift-package-testing-workflowContext preview
The summary Claude sees to decide when to auto-load this skill.
Guide Swift Testing, XCTest holdouts, code coverage, xctestplan handoff conditions, async test design, semantic accessibility-test boundaries, test-fixture organization, and package test-diagnosis work in existing Swift Package Manager repositories. Use when Package.swift is the
name: swift-package-testing-workflow description: Guide Swift Testing, XCTest holdouts, code coverage, xctestplan handoff conditions, async test design, semantic accessibility-test boundaries, test-fixture organization, and package test-diagnosis work in existing Swift Package Manager repositories. Use when Package.swift is the source of truth and the task is primarily about testing rather than package build or run work.
Use this skill as the primary execution workflow for test-focused work in existing Swift package components. Keep it focused on Swift Testing, XCTest holdouts, code coverage, `.xctestplan` handoff conditions, async-test guidance, semantic accessibility-test boundaries, performance-sensitive package workload profiling, filters, retries, fixtures, and package-level test diagnosis. `scripts/run-workflow.fsx` resolves the nearest package root and plans the test surface without classifying the containing repository.
1. Classify the request into one operation type:
2. Apply the Apple and Swift docs gate before any design, architecture, implementation, or refactor guidance:
3. Apply the shared Swift-package policy before giving implementation guidance:
4. Run `scripts/run-workflow.fsx` to resolve the nearest package root, confirm the request stays on the testing surface, and plan the package-testing command path. 5. Use `references/code-coverage.md` when the request needs SwiftPM collection, exported-JSON discovery, coverage reporting, comparison, or an explicit coverage-gate boundary. 6. Use `references/package-resources-testing-and-builds.md` when the request touches Swift Testing, XCTest, `.xctestplan`, accessibility-related semantic tests, fixtures, async test discipline, or test-related Debug/Release validation. 7. Use `references/performance-sensitive-testing-and-profiling.md` when the request touches package-first instrumentation, `OSSignposter`, `xctrace`, Time Profiler, Metal System Trace, Allocations, VM Tracker, Audio, MLX, local AI, streaming, or other performance-sensitive Apple silicon workloads. 8. Apply `../../shared/execution-surface-routing.md`; use `xcode-testing-workflow` only for `.xctestplan`, XCUITest, scheme, or destination work. 9. Report which parts were agent-executed, the docs relied on, the resolved package context, and any required next step or handoff.
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,…