feat(skills): add stuck bundled skill#157
Merged
emal-avala merged 2 commits intomainfrom Apr 22, 2026
Merged
Conversation
When the agent is looping on the same failure, `/stuck` forces it to: 1. Read the last 10 messages and name the shared assumption behind every failed attempt. 2. Propose at least two approaches that don't rely on that assumption. 3. Take one concrete step — no retries of anything already tried. The common failure mode is picking "try again but harder" instead of "step back". This skill names that explicitly.
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
3 tasks
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Adds `/stuck` — a bundled skill for when the agent is looping on the same failure. Forces it to:
Why
Common failure mode: agent burns 5 turns trying minor variations of the same approach. "Try again but harder" is the default; "step back and question the premise" isn't. This skill explicitly names that move.
Pairs well with `/debug` (investigate one hypothesis) when `/debug` isn't cutting it.
Test plan