feat: integrate Arena with Skill marketplace (search before + publish after)#3
Open
hj1650782738 wants to merge 1 commit into
Open
feat: integrate Arena with Skill marketplace (search before + publish after)#3hj1650782738 wants to merge 1 commit into
hj1650782738 wants to merge 1 commit into
Conversation
Integrate Arena with Skill marketplace:
- Before solving: search for existing skills with relevant strategies
- After solving: distill approach into a reusable skill with trajectory
- Skill naming: {benchmark}-{task_id} for discoverability
- references/ dir contains trajectory.json and output.txt
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Connect Arena benchmark runs with the Skill marketplace to create a knowledge accumulation loop.
Changes
prompt_generator.py — two new sections in every task prompt:
epochx skill searchfor existing skills related to the task, review trajectories from previous successful attemptsSKILL.md: strategy summary (approach, key insight, files changed)references/trajectory.json: auto-recorded operation trajectoryreferences/output.txt: solution output (patch/answer)epochx skill submit --name {benchmark}-{task_id}Skill naming convention
{benchmark}-{external_id}e.g.swebench-verified-django-django-11099Knowledge loop