Repository navigation
feat(pstack): add /ketchup skill - #539
Merged
Merged
Conversation
/ketchup catches the user up on everything since their last message, in plain words. Each action item gets an executive summary with enough context to decide. The skill points at /bro for its voice and sits next to /recall in the README and /poteto-help tables. Bump pstack to 0.15.16. Co-authored-by: lauren <poteto@users.noreply.github.com>
Anchor the catch-up on the last message the user wrote before /ketchup, scope it to this chat, keep the turn read-only, carry forward decisions still waiting on the user, and take only /bro's voice. Add a /ketchup close call next to /recall in /poteto-help. Co-authored-by: lauren <poteto@users.noreply.github.com>
Co-authored-by: lauren <poteto@users.noreply.github.com>
cursor
Bot
force-pushed
the
lauren/pstack-ketchup-skill-118e
branch
from
October 10, 2026 22:43
875103f to
bfe1073
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Why
People who run many agent chats at once keep typing the same prompt when they come back to a chat. "Catch me up on everything since my last message, and give me enough context on any action item to make a call."
/ketchupturns that prompt into one command. Motivating post.What changed
pstack/skills/ketchup/SKILL.md. It is typed-only. It recaps this chat from the last message the user wrote before/ketchup, and it takes its plain voice from/broby link./ketchuprow to the README skills table and the/poteto-helpskill table, plus a close call that separates it from/recall.Scope
/recallstill rebuilds context across past chats./ketchupcovers only the current chat./brois unchanged./ketchuplinks to it for voice and skips its restating step.Blast Radius
/ketchupis typed-only, so it adds nothing to the skill list in other sessions and runs only when a user types it. No existing skill's behavior changes. The/poteto-helpedit adds one table row and one sentence to an existing close call.Verification
node scripts/validate-plugins.mjspasses./ketchupon a made-up chat. Both found the same three decisions, led with the count, kept the rename and the flaky test retry out of the action items, and named the work they could not check. On an empty span, both gave a one-line reply and stopped./ketchupline. The reply started from the user's earlier message, not from the notification or the command./interrogatereviewers (Opus and Grok) read the diff. Fixed: the starting message, the scope to this chat, the read-only turn, decisions still waiting from before the user's last message, the/brorestating step, and the/recallclose call.