Diagnose broken, failing, incorrect, flaky, or unexpectedly slow software. Use whenever a user reports a bug, regression, crash, hang, visual defect, or unexplained behavior, even if they ask directly for a fix.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Diagnosing Bugs
Find the real failure before changing production code.
Treat a plausible explanation as a hypothesis, not a result.
## Procedure
1. Translate the report into an observable failure and an expected behavior.
2. Reproduce it end to end as closely as possible to the user path.
3. Preserve the failing command, fixture, screenshot, trace, or test as evidence.
4. Minimize the reproduction without changing the failure.
5. Rank concrete hypotheses and identify what observation would distinguish each one.
6. Inspect or instrument the narrowest relevant seam.
7. Add a regression test that fails for the reproduced defect.
8. Make the smallest robust fix at the cause, not at a downstream symptom.
9. Run the regression test, nearby tests, and the original end-to-end reproduction.
10. Report what caused the failure, what changed, and what remains unproven.
## Rules
- Do not edit merely because a suspicious line was found.
- Do not weaken a test to make the current behavior pass.
- For visual bugs, verify in a real terminal or browser at the dimensions and interaction that triggered the report.
…
The line at the top of this page pins the label git:20260816.716d56b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_gzwizyczyf7vumik
GET https://markdownregistry.com/api/v1/resolve?ref=miosa-osa/osa/diagnosing-bugs
GET https://markdownregistry.com/api/v1/blob/fac2394f42e7299a590346131dc68cc318b6568e54e0785dbee4678d11e2eac3
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
miosa-osa/osa · examples/skills/meeting-prep/SKILL.md · Research attendees, prepare talking points, and summarize previous interactions before meetings
kunolu/640-skills · sbtd-workflow-onboard/assets/external-skills/stable/skills/diagnosing-bugs/SKILL.md · Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports…
mxyhi/ok-skills · diagnosing-bugs/SKILL.md · Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports…
asymmetric-al/core · .agents/skills/diagnosing-bugs/SKILL.md · Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports…
oyadotai/oya-browser · .agents/skills/diagnosing-bugs/SKILL.md · This skill should be used when diagnosing a reported bug, intermittent failure, stuck operation, or performance…
oyadotai/oya-browser · .claude/skills/diagnosing-bugs/SKILL.md · This skill should be used when diagnosing a reported bug, intermittent failure, stuck operation, or performance…
jellydn/my-ai-tools · skills/diagnosing-bugs/SKILL.md · Build a tight, red-capable feedback loop before diagnosing failures, then minimize, test ranked hypotheses, and lock…
jellydn/my-ai-tools · configs/amp/plugins/my-ai-tools-skills/skills/diagnosing-bugs/SKILL.md · Build a tight, red-capable feedback loop before diagnosing failures, then minimize, test ranked hypotheses, and lock…
