coordinate-external-ag…
Coordinate independently operated external agents through durable handoffs. Use when work crosses hosts, sessions, accounts, services, queues, boards, pull…
Trace Apple entitlements across project source, account/profile authorization, final signed main or nested code, and runtime policy or consent. Use for missing or rejected entitlements, export-only failures, helpers, and re-signing.
$ npx -y skills add gaelic-ghost/socket --skill diagnose-apple-entitlements --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/diagnose-apple-entitlementsContext preview
The summary Claude sees to decide when to auto-load this skill.
Trace Apple entitlements across project source, account/profile authorization, final signed main or nested code, and runtime policy or consent. Use for missing or rejected entitlements, export-only failures, helpers, and re-signing.
name: diagnose-apple-entitlements description: Trace Apple entitlements across project source, account/profile authorization, final signed main or nested code, and runtime policy or consent. Use for missing or rejected entitlements, export-only failures, helpers, and re-signing.
Trace one desired behavior through tracked project source, developer-account/profile authorization, the final signed artifact and all nested code, and the observed runtime result. Identify the owner that must change without treating an entitlement as user consent or successful access.
1. Define the desired operation, target, platform/OS, distribution channel, artifact, and exact runtime error. Apply the Apple docs gate through `explore-apple-swift-docs` and establish whether current Apple documentation requires or permits the capability. 2. Create the five-state record in `references/five-state-entitlement-comparison.md`: desired behavior, tracked source, account/profile authorization, signed result, and runtime result. 3. Inspect tracked source: Xcode capability, `.entitlements`, Info.plist usage description, build settings, target membership, helper/extension/XPC configuration, generated-project source, configuration, and archive/export settings. 4. Inspect account authorization: Team/App ID, capability enablement, restricted-entitlement approval, certificate, provisioning profile entitlements, environment/device scope, and whether the change is portal-only or API-supported. 5. Treat the actual built/exported artifact as source of truth for signed state. Follow `references/artifact-and-nested-code-inspection.md` for the main executable, helpers, extensions, XPC services, frameworks, daemons/tools, and embedded profiles. 6. Compare exact keys and values. Preserve public, restricted, private/undocumented, development-only, environment, and exception classifications only when supported by current evidence. Read `references/restricted-and-private-entitlements.md`. 7. Evaluate runtime controls separately: App Sandbox, Hardened Runtime, library validation, TCC/user consent, service authorization, Gatekeeper/notarization, Data Vault/SIP/platform policy, and responsible process identity. 8. If the artifact was re-signed, patched, exported differently, or otherwise transformed, record a new artifact identity and invalidate assumptions about the original signature/notarization behavior. 9. Classify the mismatch and select exactly one next owner using `references/routing-and-validation.md`. Make the source/account/build change through that owner's workflow, rebuild/export, and repeat the signed and runtime comparisons. 10. Report every state, exact mismatch, owner, evidence/confidence, validation result, and what remains unproven.
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,…