Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →qf-studio/pilot-aws
Operate the AWS-hosted Pilot daemon (founder box) — status, dashboard, logs, queue queries, start/stop/restart, rebuild/upgrade, metrics tunnel, troubleshooting. Auto-invoke when user says "pilot aws", "check the box", "aws daemon", "pilot on aws", "box status", "restart pilot on aws", "box logs", or any operation against the hosted daemon.
Passed 16 of 19 test cases with the skill, and 4 of 19 without it.
and 18 more in the full report
14 fixed5 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
The dashboard status panel shows PR #104 in stage 'rebase'. I suspect this is a UI mislabel bug. What exact SQLite query on the remote host database will report the true stage for PR #104?
| Checked | Without skill | With skill |
|---|---|---|
| Queries the autopilot_pr_state table in sqlite3 on the host | Missed | Passed |
| Selects the stage column for the target PR | Passed | Passed |
The instructions your model reads when the skill loads.
Since the S6-lite cutover (2026-07-16, TASK-409) the Pilot daemon runs on an
EC2 box, NOT locally. Local pgrep pilot returning 0 is correct.
INSTANCE i-0e0c1ca34e7b561f9 # "pilot-founder-box", t3.xlarge, eu-central-1a
PROFILE quantflow # export AWS_PROFILE=quantflow for every aws call
REGION eu-central-1
RUNNER i-0147f5c24d234cdbb # mgmt runner (AdministratorAccess) — IAM/privileged ops only
DAEMON tmux session "pilot" as ec2-user, wrapper /home/ec2-user/start-pilot.sh
SLACK alerts → #pilot-reports · merge asks → founder bot DM · chat → #pointer (3 config keys; restart to apply) — see .agent/system/references/reference_slack_notifications_routing.md
BINARY /var/lib/pilot/bin/pilot # ec2-user-owned (self-upgrade works, #4470); /usr/local/bin/pilot is a SYMLINK to it — never `sudo install` over the symlink; rollback at pilot.prev
STATE /home/ec2-user/.pilot → /var/lib/pilot/pilot-home (200GB data volume)
REPOS /Users/aleks.petrov/Projects → /var/lib/pilot/repos (path shim — ledger keys
on the macOS-era absolute paths; NEVER "fix" these symlinks)
DB /home/ec2-user/.pilot/data/pilot.db
LOG /home/ec2-user/.pilot/logs/daemon.log (+ daemon-stderr.log)
export AWS_PROFILE=quantflow AWS_DEFAULT_REGION=eu-central-1
CMD=$(aws ssm send-command --instance-ids i-0e0c1ca34e7b561f9 \
--document-name AWS-RunShellScript \
--parameters 'commands=["<shell here>"]' \
--query Command.CommandId --output text)
sleep 10
aws ssm get-command-invocation --command-id $CMD \
--instance-id i-0e0c1ca34e7b561f9 --query StandardOutputContent --output text
For multi-line/quote-heavy payloads write a JSON file and use
--parameters file:///tmp/x.json; for shipping FILES to the box, base64 the
content into the command (echo <b64> | base64 -d > target) — inline heredocs
with \n escapes DO NOT survive SSM JSON (verified failure mode).
test cases passed, vs 4 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.