Diagnose bugs and performance regressions through a structured reproduce-hypothesise-fix workflow.
npx skills add https://github.com/craft-ts/craft-ts --skill diagnose-craft-ts
Please help me install this Agent Skill. Skill: diagnose Source: https://github.com/craft-ts/craft-ts/tree/main/.agents/skills/diagnose Command: npx skills add https://github.com/craft-ts/craft-ts --skill diagnose-craft-ts
[DEBUG-...] prefix so cleanup is a single grep, and a post-mortem checklist captures the confirmed root cause. - Use Case: A user reports that an export button intermittently throws in production. The Skill guides building a high-rate reproduction loop, ranking hypotheses, instrumenting the failing boundary, writing a regression test at the correct seam, and verifying the fix against the original scenario. ## Quick Start Ask the agent to diagnose the bug where the export button intermittently throws an error in production.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 bug that fails 50% of the time is debuggable; one at 1% is not, so keep increasing the rate until hypotheses can be tested against it.
Build a fast, deterministic pass/fail signal first: a failing test, a curl script against a dev server, a CLI invocation with fixture input, or a headless browser script. Confirm the loop reproduces the exact symptom the user described before moving on to hypotheses.
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 log dump, or permission to add temporary production instrumentation. Do not hypothesise without a feedback loop.
Establish a baseline measurement first using a timing harness, performance.now(), a profiler, or a query plan, then bisect to find the regression point. Logs are usually the wrong tool for performance work; measure first and fix second.
Write the regression test before the fix, but only when a correct seam exists where the test exercises the real bug pattern as it occurs at the call site. If no correct seam exists, document that architectural gap as a finding instead of writing a shallow test.
pcortesReproduce bugs and collect stack traces, logs, and affected files.
haryelramalhoScan a codebase for architectural friction and generate an HTML report with before/after diagrams.
aist-ai-sastDiagnose MCP regression failures and implement durable fixes across test suites.
monmacllcappSet up and execute continuous fuzzing for open-source projects on OSS-Fuzz.