Diagnose hard bugs and performance regressions through a structured reproduce-hypothesise-fix workflow.
npx skills add https://github.com/oskrgab/petrodb --skill diagnose-oskrgab
Please help me install this Agent Skill. Skill: diagnose Source: https://github.com/oskrgab/petrodb/tree/main/.agents/skills/diagnose Command: npx skills add https://github.com/oskrgab/petrodb --skill diagnose-oskrgab
High-intent search queries and answers about installing and using this skill.
Non-deterministic bugs are handled by raising the reproduction rate rather than seeking a clean repro. Loop the trigger 100 times, parallelise, add stress, narrow timing windows, or inject sleeps until the failure rate is high enough to debug against.
Performance regressions skip log-based probing. Establish a baseline measurement with a timing harness, profiler, or query plan, then bisect between known states to isolate the cause. Measure first, fix second.
Stop and say so explicitly rather than guessing. Ask for environment access, a captured artifact such as a HAR file, log dump, or core dump, or permission to add temporary production instrumentation before forming hypotheses.
Writing the test first proves it captures the real bug pattern by watching it fail, then confirms the fix by watching it pass. If no correct test seam exists, that architectural gap is itself documented as a finding.
The full six-phase loop is overkill for trivial, obvious bugs with known causes. Phases may be skipped only with explicit justification; the workflow targets hard bugs where the cause is genuinely unknown.
dhntDiagnose production errors by correlating logs, traces, and code paths.
haryelramalhoScan a codebase for architectural friction and generate an HTML report with before/after diagrams.
langgeniusAudits accessibility violations, applies source code fixes, and re-audits to verify.
henrycashe26Analyze and optimize React and TypeScript frontend performance using Lighthouse and React DevTools.
