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.
The English summary is being prepared. Showing the original description.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
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.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Track and surface sub-agent dispatch calibration ratios. Extract from JSONL transcript or read existing ledger. Per-agent clean/blocked/errored/partial trends.
The English summary is being prepared. Showing the original description.
Compose the AIgent's body state by reading existing signals. Lazy compute. Never polled. Reports the five pressures + recommended reflex.
The English summary is being prepared. Showing the original description.
Generate a structured delegation brief for any task
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
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>".
The English summary is being prepared. Showing the original description.