swebench-debugging
Skill73 starsChanged 56 days agoApache-2.0View on GitHub
Apply a focused reproduce-fix-test workflow to SWE-Bench repository tasks.
In this repository25 other files it gives its agents.
- AGENTS.mdAGENTS.md
- check-release-deploymentsSkill
- contribute-adapterSkill
- contribute-apiSkill
- contribute-docsSkill
- create-beta-tagSkill
- create-rc-tagSkill
- create-release-tagSkill
- draft-release-notesSkill
- karpathy-guidelinesSkill
- maintain-ciSkill
- maintain-packagingSkill
- prepare-code-freezeSkill
- prepare-prSkill
- python-testsSkill
- qualify-harborSkill
- review-doc-styleSkill
- small-fixSkill
- update-project-versionSkill
- validate-changeSkill
- code-reviewSkill
- nemo-fabric-build-adapterSkill
- nemo-fabric-integrateSkill
- alternateSkill
- defaultSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Read the task and locate the smallest relevant implementation and test surface.
- Distinctive: line 11
Run the focused regression test first, then the nearest existing test module.
- Distinctive: line 14
Do not modify tests merely to make an incorrect implementation pass.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
SWE-Bench Debugging
- Read the task and locate the smallest relevant implementation and test surface.
- Reproduce the reported behavior before editing when the environment permits it.
- Make the narrowest implementation change that addresses the root cause.
- Run the focused regression test first, then the nearest existing test module.
- Inspect the final diff for generated files, debug output, and unrelated changes.
Do not modify tests merely to make an incorrect implementation pass.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.