Skip to content
  1. Skills at a glance
  2. Report, review, get smoother over time
  3. /pstack:ketchup

/pstack:ketchup

Call when needed

In one lineSounds like "catch up": what changed, and which decisions are waiting on you. It only reads, never changes anything.

When to use
You stepped away and want a quick update.
Install with
bro
Say it like this
/pstack:ketchup

Just asking vs. using it

The same request, typed plainly or with /pstack:ketchup. Here's what changes.

Just askingWith /pstack:ketchup
Tells the long story and buries what needs your decision.Opens by naming what waits on you, and gives its pick for each call.
Fills the update with hashes, file paths and build numbers.Says what changed for you in plain words, leaving out IDs you don't need.
Invents numbers or pictures of screens it never captured.Checks each number against its source and embeds only real screenshots and videos.

What the document says

3 sections, about 1150 words, 5 min to read. Click a section to read it.

OpeningIt catches you up from your last message before /pstack:ketchup, explains each change, and lists every call you must make, in /pstack:bro's plain voice.

  1. 1Gather what changedChanges nothing this turn, checks each PR, CI run and agent this chat touched, and lists only calls you alone can make.
  2. 2Write the replyOpens with what waits on you, keeps the story under 100 words, and gives each item its pick, evidence and risk.
  3. 3VisualsDraws only when a picture explains better: six boxes at most, eight words each. Tables and status lists don't count.

See the wording worth borrowingRead the full text

Wording worth borrowing

A few sentences from the original: what each one makes the AI do, why it works, and how you can borrow it.

  1. Draw the reader's starting line

    Assume the user remembers their last message and nothing after it.

    Makes the AI
    Start from your last message: nothing you already know, nothing you missed.
    Why it works
    "What the reader knows" becomes one point in time, so the AI doesn't have to guess where to begin.
    Borrow it
    When you ask for a handover note, add: "Assume the reader saw last Friday's update and nothing after it."
  2. Set the tone with a pair of examples

    Say "the tests pass", not "CI is green".

    Makes the AI
    Report results in words you understand, not jargon.
    Why it works
    "Plain words" is vague. One "say this, not that" pair is far more precise than a string of adjectives.
    Borrow it
    To get a tone, give a pair: "Write 'ships tomorrow', not 'ETA T+1'."
  3. Define the key word first

    An action item is a call or step only the user can take

    Makes the AI
    List only the calls you truly have to make; it doesn't push its own work onto you.
    Why it works
    Everyone reads "action item" differently. Define it, then say what counts and what doesn't.
    Borrow it
    If a word in your prompt matters, define it on the spot: "Here, 'done' means it works when opened on a phone."
  4. Say which rule wins

    Never cut items or shrink them to stay under a word count

    Makes the AI
    Keep the reply short, but never drop a call you need to make.
    Why it works
    "Short" and "complete" can clash. Saying which wins stops the AI from cutting what matters to stay short.
    Borrow it
    When you give two goals, add which comes first: "Keep it short, but give every change's risk, even if that makes it longer."
  5. Give a standard it can check

    Each line must stay true when read alone.

    Makes the AI
    Each summary line is complete on its own and can't be taken out of context.
    Why it works
    It's a rule the AI can check line by line, which is easier to follow than "be clear".
    Borrow it
    When you ask for a summary, add: "Each line should still make sense if forwarded on its own."

Full text

The SKILL.md the AI reads, as written.

descriptionCatch the user up on what changed in this chat since their last message, in plain words and small visuals. List every item waiting on them with what they need to decide it from the reply alone. Use for /pstack:ketchup.

Ketchup

Catch the user up on what changed in this chat since the last message they wrote before /pstack: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 and subagent results are not their messages. Assume the user remembers their last message and nothing after it.

Use /pstack: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 agent 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 agent this chat touched. Check each number you will show against the facts it comes from, and say so when you correct one.

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.

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 cut items or shrink them to stay under a word count: 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.

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, a Mermaid diagram, a chart or diagram from /visualize (Cursor) or your harness's charting tool, or a generated image. 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.

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: a Mermaid diagram for how things connect and a chart for numbers (/visualize in Cursor, or your harness's charting tool). Never invent a number, and never draw or generate a picture of a screen you did not capture. Link only artifacts that exist.

Original by Lauren Tan (poteto), MIT license. Checked against the pstack mirror at 97de40d. View on GitHub

An unofficial beginner's guide to pstack, not its official docs. pstack is made by poteto; the official repo is the source of truth for commands and behavior. The original guide source is on GitHub.

Hosted by airali. Adapted from Xiaoxiaodong's MIT-licensed guide.