coordinate-external-ag…
Coordinate independently operated external agents through durable handoffs. Use when work crosses hosts, sessions, accounts, services, queues, boards, pull…
Plan, run, filter, and triage Android tests and lint, including local unit tests, instrumentation and Compose UI test handoffs, Gradle variant tasks, lint configuration, lint baselines, failure explanations, emulator-aware validation routing, and readable next checks.
$ npx -y skills add gaelic-ghost/socket --skill testing-lint-workflow --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/testing-lint-workflowContext preview
The summary Claude sees to decide when to auto-load this skill.
Plan, run, filter, and triage Android tests and lint, including local unit tests, instrumentation and Compose UI test handoffs, Gradle variant tasks, lint configuration, lint baselines, failure explanations, emulator-aware validation routing, and readable next checks.
name: testing-lint-workflow description: Plan, run, filter, and triage Android tests and lint, including local unit tests, instrumentation and Compose UI test handoffs, Gradle variant tasks, lint configuration, lint baselines, failure explanations, emulator-aware validation routing, and readable next checks. license: Apache-2.0 compatibility: Designed for Codex and compatible Agent Skills clients working with Android Gradle projects. metadata: owner: gaelic-ghost repo: socket category: android-testing allowed-tools: Read Bash(rg:*) Bash(git:*) Bash(./gradlew:*) Bash(gradle:*) Bash(adb:*)
Run the narrowest useful Android tests and lint checks, explain failures clearly, and route emulator/device validation to the Android testing plugin.
The practical decision is which module, source set, variant, and task prove the work without turning every change into a full device run.
Use repo-local Gradle files, test files, lint config, checked-out dependency sources, and Dash.app docsets opportunistically for exact Gradle or Java questions. Use official documentation as authority for Android-specific testing and lint behavior:
Translate documentation into concrete test source sets, Gradle tasks, variants, and failure modes.
1. Identify test layout:
2. Identify lint setup:
3. Identify affected variants:
4. Identify validation level:
Start narrow, then widen:
./gradlew :app:testDebugUnitTest ./gradlew :app:lintDebug ./gradlew :app:connectedDebugAndroidTest
Use connected or managed-device tasks only when the user requested device validation or the change cannot be proved locally. If emulator operation is needed, hand off to the Android testing plugin instead of duplicating device-control steps here.
Run one Gradle command at a time.
Classify failures by first concrete break:
Report the command, module, variant, source set, first meaningful error, likely cause, and smallest next check.
Return:
1. `Test scope`: module, source set, variant, unit, instrumentation, Compose UI, or lint. 2. `Commands`: exact commands run or recommended. 3. `Result`: pass, fail, or skipped with concrete reason. 4. `Failure mode`: setup, compile, unit, instrumentation, Compose UI, lint config, lint finding, or emulator/device issue. 5. `Next check`: smallest code, test, lint, Gradle, or Android testing plugin 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,…