菜单
Use when the user invokes `$digest`, asks for a multi-agent wave digest or progress summary, or asks "what's the status of the wave" / "where are things".
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when the current repo is explicitly governed by team-collab: `obsidian-docs/` exists in cwd/ancestor, repo `AGENTS.md`/`CLAUDE.md` imports team-collab, the cwd is under a registered code/docs path, or the user asks for team-collab handoff/checkpoint/docs governance/Feishu automation. Do not use solely because a global config file exists.
Use when the user invokes `$gate`, asks whether a PR/merge is ready, asks to gate-check or merge-gate a multi-agent task, or asks "can this merge?".
Use when the user invokes `$wave`, asks to start or enter a multi-agent wave, or asks to spin up / set up a wave for a batch of tasks coordinated across agents.
Use when the user invokes `$checkpoint`, asks for a checkpoint, or asks to update CURRENT/NEXT/RISKS/TODO without committing or pushing.
Use when the user invokes `$docs-refresh`, asks to update Obsidian project docs from a stale audit/dev record, or wants old docs archived while active docs become current.
Use when the user invokes `$handoff`, asks for a handoff, or asks to finish a team-collab session by updating CURRENT/NEXT/RISKS/TODO and syncing docs.
| name | digest |
| requires_protocol | >=0.6.0,<0.7.0 |
| description | Use when the user invokes `$digest`, asks for a multi-agent wave digest or progress summary, or asks "what's the status of the wave" / "where are things". |
This is a Codex-friendly command wrapper for the multi-agent wave digest. Codex does not currently support arbitrary custom top-level slash commands like /digest, so the supported Codex entry point is:
$digest <slug>
The digest aggregates a whole wave into one view: what needs a decision, what's blocked, what's merge-ready, the merge order, truth-source/resource risks, and which agents have gone stale. $digest is the human→coordinator shortcut for "where are things right now".
team-collab-protocol skill and its references/multi-agent.md flow. If the protocol skill is not available in the current session, read ~/.codex/skills/team-collab-protocol/SKILL.md; if that file is missing, stop and tell the user to run team-collab install-skills --agent codex --force.command -v team-collab. If missing, stop and tell the user to install the CLI with npm install -g @embodot/collab@latest, then refresh skills with team-collab install-skills --agent codex --force if needed.$digest as the wave slug. If none is given, infer the wave from the current working directory (multi-agent/<slug>/ subtree). If still unknown, ask which wave.team-collab multi-agent digest --wave <slug>
--refresh-truth-source. If they asked about a specific time window, add --since <duration>.multi-agent/<slug>/digests/*.md and makes a local docs commit; --refresh-truth-source may also update agent status files. It does not auto-push, so cross-machine visibility requires an explicit docs repo push.If a future Codex version supports custom slash commands and /digest reaches the model as plain user text, handle it exactly the same way as $digest.