Diagnose bugs and performance regressions through a structured reproduce-hypothesise-fix workflow.
npx skills add https://github.com/TrayMachi/dotfiles --skill diagnose-traymachi
Please help me install this Agent Skill. Skill: diagnose Source: https://github.com/TrayMachi/dotfiles/tree/main/agents/skills/diagnose Command: npx skills add https://github.com/TrayMachi/dotfiles --skill diagnose-traymachi
[DEBUG-xxxx] prefix so cleanup is a single grep, and the post-mortem phase records the confirmed root cause. - Use Case: A user reports that an export endpoint intermittently returns empty files. The Skill guides building a loop that replays the failing request 100 times, ranking hypotheses about race conditions, instrumenting the suspected boundary, and landing a regression test with the fix. ## Quick Start Ask the agent to diagnose the bug where the export endpoint intermittently returns empty files and follow the structured diagnosis loop.High-intent search queries and answers about installing and using this skill.
Raise the reproduction rate instead of chasing a clean repro: loop the trigger 100 times, parallelise, add stress, narrow timing windows, or inject sleeps. A 50%-flake bug is debuggable; a 1% flake is not, so keep increasing the rate until hypotheses can be tested against it.
Establish a baseline measurement first using a timing harness, profiler, or query plan, then bisect between known-good and known-bad states. Logs are usually the wrong tool for performance work; measure first and fix second.
Stop and say so explicitly rather than guessing. List what you tried, then ask for environment access, a captured artifact such as a HAR file or core dump, or permission to add temporary production instrumentation before forming hypotheses.
Write the regression test before the fix, but only at a correct seam that exercises the real bug pattern as it occurs at the call site. If no correct seam exists, that architectural gap is itself a finding worth flagging.
Generating 3-5 ranked falsifiable hypotheses prevents anchoring on the first plausible idea. Each hypothesis must state a testable prediction, and showing the list to the user lets domain knowledge re-rank it cheaply before testing begins.
abrahamgreysonTrace code paths and validate hypotheses to identify root causes of software bugs.
janpeterdLocate shallow modules and propose deepened interfaces for codebase architecture.
Ramprasad4121Prepare codebases for security review with static analysis and documentation.
ax-llmTrace Java agent behavior, usage, and action logs for Ax-generated agents.