From Daily Agents
Use when the user needs to diagnose a problem on a live/remote server — over SSH (incl. bastion), docker exec, or kubectl exec. Read-only triage that finds root cause and hands back fix commands. Triggers like "server is down", "debug prod", "why is this host slow/erroring".
How this skill is triggered — by the user, by Claude, or both
Slash command
/daily-agents:live-debugThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Diagnose a single live host's problem **read-only** and produce a root-cause report plus the exact
Diagnose a single live host's problem read-only and produce a root-cause report plus the exact remediation commands for the user to run. You never change server state.
scripts/run.sh. Never call ssh,
docker, or kubectl directly — the gate enforces the whitelist, redacts secrets, and logs.run.sh on your own.run.sh only after they approve.run.sh prints BLOCKED, do not try to work around it. Treat it as off-list (tier 2).Intake. Ask for: the host/alias, the transport (ssh / ssh+bastion / docker / kubectl), and the symptom. Build the transport prefix — everything up to the shell that takes the command as one trailing arg:
ssh prod-web1 or ssh -J bastion [email protected]docker exec <id> sh -c ; docker host-side reads: sh -ckubectl exec -n <ns> <pod> -- sh -c ; cluster reads: sh -cSet the log once, then probe:
export LIVE_DEBUG_LOG="./live-debug-logs/<host>-$(date +%Y%m%d-%H%M%S).log"
bash scripts/run.sh "<transport-prefix>" "uptime"
A successful probe confirms transport + the gate. Tell the user the log path.
Triage, then pick a playbook. Read references/playbooks-linux.md, run the Triage block, and
branch to one of: service-down/crash-loop · high-CPU/load/mem · disk/IO · network/latency/errors.
For Windows hosts, read references/windows.md instead (instruction-only — self-enforce the
read-only rule there).
Stop when you have a root cause backed by evidence, OR the playbook is exhausted.
Report (in chat) using this shape:
Symptom: <what the user reported / what you confirmed>
Evidence: <key command outputs that prove it>
Root cause: <the why> — or "undetermined: <what's missing>"
Fix (run yourself):
$ <exact remediation command(s)>
Log: <LIVE_DEBUG_LOG path>
bash scripts/run.sh "<transport-prefix>" "<remote-command>" — validates the remote command against
references/whitelist.txt, blocks redirections / command-substitution / destructive flags, executes
over the transport, redacts secrets (see references/redaction.md), and appends command + output to
$LIVE_DEBUG_LOG. Read those reference files only when you need their detail.
One host per session. The gate + transport prefix are per-host by design, so multi-host fan-out can be layered on later without changing this engine.
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub sola1re/awesome-agents --plugin daily-agents