urmzd/dotfiles / dot_agents/skills/diagnose-runtime
diagnose-runtime
VerifiedTriage LOCAL runtime failures on your own machine: crashes and errors, hangs and deadlocks, slowness and high CPU/memory, and hardware/serial/USB issues. Method: reproduce, isolate (bisect, log, strace/dtruss, sample), form a hypothesis, verify the fix holds. Read-mostly: it inspects processes and logs, it does not commit, push, or edit source. Use when the user asks "why does this error", "why does the system hang after generating the PDF", "why is the computer running hot", "why is image loading slow", or "this process is stuck". Do NOT use for CI/pipeline failures (use diagnose-ci) or for applying and re-shipping a fix (use fix-and-retry) -- this skill investigates and recommends only.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.3 KB |
| evals/eval_queries.json | config | 3.5 KB |
evals/eval_queries.json
View on GitHub{
"skill": "diagnose-runtime",
"description": "Routing evals: does the query trigger local runtime triage? Near-misses route to diagnose-ci (remote pipelines), fix-and-retry (apply + re-ship), and audit-security (suspicious process / compromise).",
"queries": [
{
"query": "determine the cause of this error I'm getting when I run the app",
"should_trigger": true,
"note": "Local crash/error triage -- the reproduce->isolate->hypothesize->verify loop."
},
{
"query": "explore why our system hangs after generating the pdf",
"should_trigger": true,
"note": "Classic local hang; likely an unclosed resource or a child process the parent waits on."
},
{
"query": "why is the computer running hot and the fan spinning constantly",
"should_trigger": true,
"note": "High-CPU triage: sort by pcpu before blaming hardware."
},
{
"query": "why is image loading so slow in my desktop app",
"should_trigger": true,
"note": "Slowness triage: separate decode from I/O from network with sample."
},
{
"query": "this process is stuck and won't respond, how do I find out where it's blocked",
"should_trigger": true,
"note": "Deadlock/hang: sample then spindump to see thread states."
},
{
"query": "my python script eats all my RAM over time, where's the leak",
"should_trigger": true,
"note": "Memory growth: watch RSS climb with ps -Ao pid,rss,comm -m."
},
{
"query": "the serial device on /dev/tty.usbserial isn't being detected, why",
"should_trigger": true,
"note": "Hardware/serial: check whether the OS sees the device at all."
},
{
"query": "what's holding the lock on this file, my build can't delete it",
"should_trigger": true,
"note": "Stuck file handle: lsof on the path to find the holder."
},
{
"query": "the test suite passes alone but hangs intermittently under load, help me find why",
"should_trigger": true,
"note": "Intermittent-under-load points at a resource limit (fds, pool), not logic."
},
{
"query": "port 8080 is already in use but I don't know what's holding it",
"should_trigger": true,
"note": "lsof -i :8080 to find the listener."
},
{
"query": "why did the CI pipeline fail on the last push",
"should_trigger": false,
"note": "Remote pipeline failure -- use diagnose-ci, not local runtime triage."
},
{
"query": "the GitHub Actions run is red, pull the failed step logs and tell me why",
"should_trigger": false,
"note": "Remote CI logs -- diagnose-ci owns gh run inspection."
},
{
"query": "fix the failing build and push it so CI goes green",
"should_trigger": false,
"note": "Apply + commit + re-ship loop -- fix-and-retry, not investigate-only."
},
{
"query": "I found the bug, now apply the patch, commit, and re-run until it passes",
"should_trigger": false,
"note": "Editing and re-shipping is out of scope; hand off to fix-and-retry."
},
{
"query": "there's an unknown process listening on a port and I think the machine is compromised",
"should_trigger": false,
"note": "Suspected compromise / suspicious listener -- audit-security, not a perf/correctness bug."
},
{
"query": "scan my repo for leaked API keys before I commit",
"should_trigger": false,
"note": "Secret-leak scanning -- audit-security."
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |