pstack: self-unblock empirical forks with a sketch instead of asking#122
Merged
Conversation
Prototype was UI-only (layout/interaction, the eye is the test). Broaden the trigger and steps 1/5 so a throwaway sketch can settle a behavioral or timing fork by observation (which behavior, which timing, which approach), not just a visual one. This is the destination the new self-unblock trigger routes to.
Before asking the human a which-approach / how-should-I / what-should-this-do question, classify it. If the answer is empirical (observable by running something), sketch it via the Prototype playbook and let the result decide; reserve the ask for a genuine product or preference call. Wires Never Block on the Human to Prototype, and broadens the Prototype catalog entry to match.
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes using high effort and found 3 potential issues.
Bugbot Autofix is ON, but it could not run because the branch was deleted or merged before autofix could start.
Reviewed by Cursor Bugbot for commit 6c80c24. Configure here.
poteto
force-pushed
the
pstack/self-unblock-prototype
branch
from
6c80c24 to
e19a14d
Compare
Three gaps in the partial broadening. Step 3 still assumed a UI build, so it now names the script path for a behavioral or timing decision. The Reply still demanded screenshots, so it asks for the matching evidence instead. The AskQuestion trigger had no read-only carve-out, so a cited-answer Investigation no longer routes to a build.
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
1 participant
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.
Summary
AskQuestionreflex. Before asking the human a "which approach / how should I / what should this do" question, classify the fork. If the answer is empirical, observable by running something (behavior, timing, layout, output, perf), sketch it via the Prototype playbook and let the result decide. Reserve the ask for a genuine product or preference call no experiment can settle.Why
This wires together two pieces that already exist, Never Block on the Human and Prototype, at the moment they fail to fire. An agent hits an empirically decidable fork (a timing, behavior, layout, or perf question) and asks the human instead of running a cheap experiment. A throwaway probe usually answers faster, and it hands the human a result to react to instead of a decision to make.
Delivery
Two commits in dependency order. The Prototype playbook gains the empirical-fork capability, then poteto-mode adds the trigger that routes to it.
Note
Low Risk
Documentation-only changes to agent skill playbooks; no runtime code or security-sensitive behavior.
Overview
Adds a poteto-mode non-negotiable that runs before
AskQuestionon “which approach / how should I / what should this do” forks. The agent must classify the fork first. If the answer is observable by running something (behavior, timing, layout, output, perf, eval separability), it routes to the Prototype playbook instead of asking. Investigation stays read-only with cited evidence. Questions are reserved for product or preference calls no experiment can settle.The Prototype playbook and its index blurb are expanded beyond UI mocks to empirical and behavioral forks: scoping includes behavior/timing/approach, build step allows a minimal script (not only HTML/CSS), verification covers logging/printing/watching output, and replies call for observed evidence as well as screenshots.
Reviewed by Cursor Bugbot for commit b46c16d. Bugbot is set up for automated code reviews on this repo. Configure here.