/evaluate-language-model
Design repeatable language-model capability, quality, behavior, regression, or safety evaluations. Use when creating cases and graders, comparing a treatment with a baseline, or deciding whether a checkpoint passes.
$ npx -y skills add gaelic-ghost/socket --skill evaluate-language-model --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/evaluate-language-model
Context preview
The summary Claude sees to decide when to auto-load this skill.
Design repeatable language-model capability, quality, behavior, regression, or safety evaluations. Use when creating cases and graders, comparing a treatment with a baseline, or deciding whether a checkpoint passes.
The macOS Marketplace for Codex Promo audio: Socket Codex Marketplace Promo
Other skills on socket.
- /coordinate-external-agents
Coordinate independently operated external agents through durable handoffs. Use when work crosses hosts, sessions, accounts, services, queues, boards, pull requests, or human-owned task systems and cannot rely on an in-run subagent result.
Open skill - /coordinate-worktrees-and-threads
Assign worktree, branch, thread, artifact, write, validation, integration, and cleanup ownership before parallel repository work. Use when launching or resuming a worker that will inspect or modify repository state outside the coordinator's single worktree.
Open skill - /design-agent-automation-workflow
Design framework-neutral agent and automation workflows before implementation. Use when choosing between Codex app automations, codex exec, Codex subagents, OpenAI Agents SDK services, LangGraph graphs, Hermes-specific workflows, full-auto execution, auto-with-escalation, or no
Open skill - /design-agent-eval-workflow
Design evaluation workflows for agent, skill, prompt, and automation behavior before implementation. Use when choosing eval cases, graders, thresholds, regression runs, full-auto gates, or escalation points for Codex skills, repo-local agents, OpenAI Agents SDK services,
Open skill - /design-n8n-agent-workflow
Design safe n8n workflows with deterministic routing, credentials, idempotency, recovery, local-model checks, drafts, and exact approval gates.
Open skill - /orchestrate-agent-work
Coordinate bounded work across in-run subagents or worker tasks. Use before spawning, resuming, steering, cancelling, or closing workers when the coordinator needs a structured launch envelope, required report-back, escalation, and synthesis contract.
Open skill