sno-ai/sno-station-skills / skills/T-delegation-and-work-orders/pl/skills/pl
pl
FlaggedMANUAL-ONLY — load solely when the human owner types `/pl`, uses `$pl`, or asks you to act as the Project Lead (PL). Supervise one project lane and its executor agents. A charter or dispatch means: you are an EXECUTOR, not the PL.
scripts/gpu-watch.t
View on GitHub#!/usr/bin/env bash
set -euo pipefail
script_dir="$(cd -- "$(dirname -- "$0")" && pwd)"
root=$(mktemp -d)
trap 'rm -rf -- "$root"' EXIT
export SNO_SCRATCH="$root/state" GPU_WATCH_SMI="$root/smi"
mkdir -p "$root/repo/ai-doc/ACTIVE/PL"
git -C "$root/repo" init -q
cat > "$root/smi" <<'SMI'
#!/usr/bin/env bash
cat "$GPU_WATCH_SAMPLE"
SMI
chmod +x "$root/smi"
cd "$root/repo"
tick() {
local rc=0
bash "$script_dir/gpu-watch.sh" --journey "$1" --tick-secs 60 --grace-mins 2 --stall-mins 1 --max-hours "$2" > "$root/out" || rc=$?
[[ "$rc" -eq "$3" ]] || { printf 'wrong exit: %s (wanted %s)\n' "$rc" "$3" >&2; exit 1; }
[[ -f $(sed -n '1p' "$root/out") ]]
}
export GPU_WATCH_SAMPLE="$root/sample"
printf '0, 30, 1024\n' > "$root/sample"
tick active 8 0
printf '0, 0, 1024\n' > "$root/sample"
tick active 8 3
grep -Fq 'GPU-WATCH: STALL' "$root/out"
tick never 8 0
tick never 8 0
tick never 8 4
grep -Fq 'GPU-WATCH: NEVER-STARTED' "$root/out"
printf '0, 30, 1024\n' > "$root/sample"
tick elapsed 0 0
grep -Fq 'GPU-WATCH: WINDOW-ELAPSED' "$root/out"
jq -e 'select(.journey == "active" and .event == "STALL")' ai-doc/ACTIVE/PL/gpu-watch.jsonl >/dev/null
jq -e 'select(.journey == "never" and .event == "NEVER-STARTED")' ai-doc/ACTIVE/PL/gpu-watch.jsonl >/dev/null
jq -e 'select(.journey == "elapsed" and .event == "WINDOW-ELAPSED")' ai-doc/ACTIVE/PL/gpu-watch.jsonl >/dev/null
[[ $(jq -c 'select(.max_util != null)' ai-doc/ACTIVE/PL/gpu-watch.jsonl | wc -l) -eq 6 ]]
printf 'ok - GPU ticks, exit codes, and audit trail\n'
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |