Track and surface sub-agent dispatch calibration ratios. Extract from JSONL transcript or read existing ledger. Per-agent clean/blocked/errored/partial trends.
中文简介正在准备中。当前显示原文说明。
The day-one first-win menu. Three dead-simple, high-value tasks (two zero-dependency) that each put a real, usable artifact in the operator's hands in minutes, so the "ship something real" promise is met on day one and never waits on a connector or OAuth.
中文简介正在准备中。当前显示原文说明。
实测评分 未实测
查看安装方法安装前可以查看交给 AI 代理的指令内容。
The operator has just met you (via /operator-setup). Now give them proof of work: a real
artifact they can use today. This is what satisfies the "ship something real, fast" promise
on day one, instead of making them wait for a longer pipeline.
Offer these three. Lead with the two zero-dependency tasks so the win never stalls waiting on an inbox connection or any login beyond their Claude account:
Turn your last post into a week of social posts. (zero-dependency, default) Ask them to paste their most recent newsletter, blog post, or even a few sentences about what they do. Produce five to seven platform-ready posts in their voice, each with a clear hook. If they have nothing to paste, use the known-good example below so they still get a result.
Turn a rough idea into a structured plan. (zero-dependency, default) Ask for the idea in a sentence. Produce a structured plan: the outcome, the steps in order, the first action they can take today, and what "done" looks like. Concrete, not generic.
Today's three priorities from your inbox. (only if connected) If an inbox connector is set up, summarize their inbox into three priorities for today. If not, they paste a handful of emails or notes and you do the same thing. Never block on OAuth or a connector. This task always has the paste-in fallback.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Track and surface sub-agent dispatch calibration ratios. Extract from JSONL transcript or read existing ledger. Per-agent clean/blocked/errored/partial trends.
中文简介正在准备中。当前显示原文说明。
Compose the AIgent's body state by reading existing signals. Lazy compute. Never polled. Reports the five pressures + recommended reflex.
中文简介正在准备中。当前显示原文说明。
Generate a structured delegation brief for any task
中文简介正在准备中。当前显示原文说明。
Quarterly skill that walks the skill-index against the actual SKILL.md files on disk, reports drift (skills indexed that no longer exist, skills on disk that aren't enrolled, skills whose descriptions have changed since enrollment). Hardens the auto-enrollment pipeline against silent rot.
中文简介正在准备中。当前显示原文说明。
When a [CADDY] hint fires and the principal is confused why, /caddy-explain walks the scoring transparently — which trigger matched, what points it earned, what the threshold was, what other skills were close. Pairs with the legibility thesis. Caddy's decisions should be inspectable on demand.
中文简介正在准备中。当前显示原文说明。
Enroll a skill into Caddy's index so it can be surfaced when the right prompt arrives. Use when a new skill is created, copied in, or when a skill needs updated triggers. Usage — "/caddy-enroll <path to SKILL.md>".
中文简介正在准备中。当前显示原文说明。