AGENT SKILL

ketchup

Catch the user up on what changed in this chat since their last message, with every item waiting on them. Use for 'catch me up on this thread' or 'what did I miss'. For past sessions, use recall.

License 许可
MIT
最近更新
2026-11-15
Stars
★ 1
Forks
0

01 前言 Front Matter

tip
catches you up on this chat since your last message | catch me up | what did i miss | what happened while i was away | where are we
card
Catch up and keep track | 2 | Catches the operator up on everything in this chat since their last message and lists every waiting item, each one decidable from the reply alone. | Reach for it when a thread ran on while you were away. | op: the operator
name
ketchup
description
Catch the user up on what changed in this chat since their last message, with every item waiting on them. Use for 'catch me up on this thread' or 'what did I miss'. For past sessions, use recall.

02 资源文件 3

03 SKILL.md 正文

Ketchup

Source: pstack, pstack/skills/ketchup/SKILL.md

Catch the user up on what changed in this chat since the last message they wrote before /ketchup, and help them understand each change, not only where it stands. Then lay out every call waiting on them so they can make it from your reply alone. Notifications, wakes of a watch, messages from other threads and subagent results are not their messages. Assume the user remembers their last message and nothing after it.

Use /bro's voice, not its task: plain words, short sentences, no jargon, like one person catching up another. Say what changed for the user, not how you did it. Say "the tests pass", not "CI is green". Leave out hashes, file paths, commands, build numbers, and test counts unless the user needs one to act. Call each PR, branch, or thread by a name the user would know, not by a label you invented. If a fact needs context to make sense, give the context or leave the fact out.

Gather what changed

Keep this turn read-only. Make visuals only from what you already have: do not change code, start an app or a job, or post anything. Collect your own work since that message, reports from subagents, and messages from anyone else in this chat. Check the current state of each PR, CI run, or thread this chat touched: gh pr view <number> --json state,mergeable,statusCheckRollup for a pull request, and the T3 Code tool t3_thread_read for a thread this one launched. Say which are still running and which you could not check. Check each number you will show against the facts it comes from, and say so when you correct one.

In a home, "this chat" is the home's whole pipeline. Place every row of this home and of every home under it in its stage (brief, queued, scout, crew, check, PR, review, fix, merge), with dependency chains. For each row that has not moved, give its cause and its age. Draw it as one HTML page with html_preview and then html_render, slowest stage first. Do this even when the user does not ask for a visual.

An action item is a call or step only the user can take, such as a product choice, an approval, an irreversible action, or access you lack. Include any still waiting on the user, even one raised before their last message. Work you can still do yourself is not an action item. Never make up a call to fill the reply. A step the user did not ask for and the work does not need is not an action item, unless it is irreversible and waiting on the user: give it one line and no visual.

One call can cover many items, such as each PR in a set awaiting merge. For each item, collect its link, what it changes for users, the evidence behind your pick, its risk, and your pick. Write "unknown" for a fact the call needs that you do not know. Leave out a link you do not have.

Where jbus runs, it holds the one list of what waits on the user. In a home, the catch-up names only that home's items: a scoped home's own, and a root home's own with every scope's under it, and never another project's. Outside a home it names every project's. This prints it, with this thread's id in place of <threadId> (T3 Code's t3_thread_configure with no arguments gives it as threadId):

if [ -n "${ZSH_VERSION:-}" ]; then emulate sh; fi
ME='<threadId>'
R=$(basename "$(dirname "$(git rev-parse --path-format=absolute --git-common-dir 2> /dev/null)")")
H=~/.local/state/home/$R
M=
case $ME in
'' | *'<'* | *'>'*) ;;
*)
    for f in "$H"/home-id "$H"/*/home-id; do
        if [ -f "$f" ] && [ "$(awk 'NF {print $(1); exit}' "$f")" = "$ME" ]; then
            M=$(dirname "$f")
            break
        fi
    done ;;
esac
P=$R
if ! command -v jbus > /dev/null; then
    echo "no list: jbus is not installed or set up here, so what waits on the user is not known"
elif [ -n "$M" ] && said=$(jbus --project "$P" needs --home "$M" 2> /dev/null); then
    printf '%s\n' "$said"
elif [ -z "$M" ] && said=$(jbus needs 2> /dev/null); then
    printf '%s\n' "$said"
else
    echo "no list: jbus is not installed or set up here, so what waits on the user is not known"
fi

$M is this home's directory, found by the home-id that holds this thread's id, and empty outside a home. $P is the home's project, which jbus names after the repo.

In a home, the reply opens with what it printed, as it printed it: each item, what it holds and the reply that answers it. Each item is an action item too, with its reply as the way to answer it. A refused go and a row a home can clear by itself are not on the list, and are no action item.

Write the reply

Spend words on the calls, not on the story. Keep what happened under 100 words, not counting pictures, and shorter when less happened. Leave out work that changed nothing for the user. Give each item about 30 words. The reply grows with the number of items: two items need well under 150 words in all, not counting pictures, and thirty need far more. Never shrink items to fit: no count in place of a list, and no link in place of an item. A link can add depth, but the reply alone must be enough to decide.

Open with one short sentence that names what waits on the user, or says nothing does. The action items give the detail. If nothing happened and nothing waits on the user, say so and stop. In a home, that sentence is the list jbus printed, as it printed it.

Then show what happened, pictures first. Embed inline the screenshots and videos the work produced, then any diagram that explains a change. Then sum up in one short bullet per thing the user asked for: what came of it, and whether it is done, still running, failed, or not checked. Write each line the way you would say it out loud: "Search was slow from a missing index", not "Search review: done" or "Slow search: missing index". Name any bug found and fixed on the way. Each line must stay true when read alone. Never mark something done that still waits on the user, and leave out anything the action items say. Under the summary, give at most three short lines that change what the user knows or must do. Then name in one line any work left that you can do yourself.

Then list the action items. Ask the call the user owns, such as merge, approve, or pick, and give your pick. A step you would take first goes in your pick. So does anything that must happen first, and anything that cannot be undone. Give the number or link of each PR, issue, or agent a call is about, also in a call between options.

Fit the shape to the call. A call about one item is one bullet: the call, your pick, what it changes for users, the evidence behind your pick, and its risk, with the item named once. When items share a call, write the call and your pick once, then give each item its own bullet, riskiest first: its link and name, what it changes for users, the evidence behind your pick, and its risk. Name an item's pick only where it differs from the call's. Give each item's risk even when it is low, such as "Low risk: only the colors change." Say what waiting costs only when it is more than a delay, such as a deadline or lost data.

For a call between options, give every option the work weighed, each with what it gets the user and what it costs, and the current state when there is one. Those costs are the call's risk, so add no separate risk line. When the screenshots above show the options, write each option's gain and cost under its screenshot.

Visuals

A visual is a picture: a screenshot, a video, or a diagram or chart drawn as an HTML page. A Markdown table is not a visual, even with before and after columns.

When something is easier to grasp as a picture than as sentences, draw it: how a design or system works, a PR stack or dependency chain with each PR's state, a before and after of a fix, or options side by side. Never draw a status list, a list of action items, or boxes with nothing connecting them. Never give a fact twice, in text or across visuals.

Keep each visual small enough to read at a glance: at most six boxes, with at most eight words in each. Write labels as plain words a person would say, not tags like "Tests: pass". A fact that needs a sentence belongs in the text, or nowhere.

The home's pipeline page from "Gather what changed" is the one exception to these limits: it shows every row, grouped by stage and joined by its chains, with each stalled row's cause and age.

Embed screenshots and videos inline when the change is visible, not only as links. If a visible change has none, mark its summary line "No screenshot yet," and say there what changed on screen. Draw diagrams and charts from facts you have, as one HTML page shown with html_preview and then html_render. Never invent a number, and never draw or generate a picture of a screen you did not capture. Link only artifacts that exist.

04 同仓库更多 Skills