swebench-pro
swebench-pro contém 5 skills coletadas de kimjune01, com cobertura ocupacional por repositório e páginas de detalhe dentro do site.
Skills neste repositório
Read-only diagnosis phase for SWE-bench instances. Walks the codebase, reproduces the failure, and produces a structured handoff for /craft. Single diagnostician; correction comes from the audit→recon outer loop, not a parallel blind. No edits, no external access.
Read-only diagnosis phase for SWE-bench instances. Reproduce the failure, identify the code that needs to change, and print a concise handoff for /craft. No edits, no external access.
Read-only diagnosis phase for SWE-bench instances -- the STATIC ablation arm for recon (prereg-pro-v1-feynman). Identical to recon in goal, typing, process, and handoff; it removes ONLY scoped diagnostic perturbation -- it may not run experiments during diagnosis. It may REASON about what an experiment would show, but it cannot execute one. "Write down the problem, think real hard, write down the solution." No edits, no external access.
Read-only diagnosis phase for SWE-bench instances. Walks the codebase, reproduces the failure, and produces a fix-plan handoff for /craft. Single diagnostician; correction comes from the audit->ask outer loop, not a parallel blind. No edits, no external access.
Implementation phase for SWE-bench instances. You generate the patch from the recon handoff; a codex subagent challenges it; the gate arbitrates. Loops until FAIL_TO_PASS tests pass. On audit re-entry, narrows a fix that regressed. Stops when gate is green or the attempt budget is exhausted.