菜单
Re-explain the previous response in plain, easy-to-understand language. No jargon, no acronyms without unpacking, short sentences. Use when the user types /eli5 — they want the same content as the last assistant turn, but accessible to a non-expert.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Session closing checklist for Git state, documentation, handoff files, and Munin memory. Use when the user invokes /close or asks to wrap up a session, including work that touched multiple repositories.
Resolve a batch of GitHub tickets via parallel headless Claude Code sessions — one isolated git worktree per ticket, gated permissions, triple review (Codex + local-model first-pass + orchestrator comment), interrupt-resume, and merge orchestration. Use when the user wants many well-scoped tickets solved autonomously across one or more repos.
Run an adversarial debate with Claude to stress-test a draft, plan, research claim, or design decision. Use when Codex needs structured cross-model critique before finalizing a consequential decision, architecture, protocol, research claim, security assessment, or product priority.
Run an adversarial debate with a cross-model reviewer (Codex or Antigravity/agy) to stress-test a draft, plan, research claim, or design decision. Use this whenever you need structured critique before finalizing decisions.
Run a cross-model PR review using Codex CLI. Invokes Codex headless to review the current branch diff, then reads findings and fixes issues or reports to user.
Sweep the Munin signals/friction corpus (report_friction self-reports), group recurring failures, and file consolidated GitHub issues routed to their owning repos + the Grimnir Roadmap board. Use when the user wants to triage accumulated friction, turn friction signals into tickets, or asks "what friction have we collected / let's file tickets for it".
| name | eli5 |
| description | Re-explain the previous response in plain, easy-to-understand language. No jargon, no acronyms without unpacking, short sentences. Use when the user types /eli5 — they want the same content as the last assistant turn, but accessible to a non-expert. |
Take the immediately previous assistant message and re-explain it in plain language.
Previous message: "The harness misconfig invalidated prior aider+qwen-coder ranking. Real picture: aider and opencode are comparable when aider has per-task file scope."
ELI5: "Earlier I had aider set up wrong, so its scores were unfairly low. With the right settings, aider does about as well as opencode — they're roughly tied."
