{"id":77007,"plugin_id":"plugins_6ab41ed5b8c4819199eb5bbf91ce25f5","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-11-03T00:12:18.652Z","digest":"78fa1bea296a0847e34d9b85989e44261a3f11da5263207a178725819872079c","against":null,"payload":{"description":"Investigate runtime errors, failing tests, defects and regressions in software, data or AI code and implement a minimal safe fix.","included_files":[],"name":"debug-failure","skill_md_contents":"---\nname: debug-failure\ndescription: Investigate runtime errors, failing tests, defects and regressions in software, data or AI code and implement a minimal safe fix.\n---\n\n# Debug Failure\n\nUse this skill only for its stated purpose. Follow the shared source-of-truth, permission and evidence rules in `../../references/workflow-contract.md`. Read `../../references/debugging-playbook.md` for detailed method when necessary.\n\n## Procedure\n1. Capture expected versus actual behavior, error evidence, affected versions and earliest change.\n2. Inspect the failing code path and reproduce with an available test or minimal fixture where safe.\n3. Distinguish root cause from downstream symptoms; check the hypotheses against evidence.\n4. Apply a focused fix only after understanding invariants; add a regression test.\n5. Run targeted checks when tools allow. Do not report success without results.\nDeliver root cause, patch/diff, tests actually run, and remaining uncertainty.\n\n## Handoff rule\nState actual artifacts or grounded code findings and validation status. Never invent file paths, executed tests, tool access, or completed subagent work. Keep output proportionate to the user request.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}