🎁 Get the FREE AI Skills Starter GuideSubscribe →
BytesAgainBytesAgain
🦀 ClawHub

Agent Dashboard — real-time progress board for any task

by @qianlong2005

Push real-time progress and key metrics to a live statb.io dashboard during any long-running task. Use this skill whenever the agent is performing work that...

💡 Examples

Multi-file processing

# Start
curl -s 'https://statb.io/b/convert-imgs-a9x2/push?total=200&done=0&errors=0&status=1'

After each file

curl -s 'https://statb.io/b/convert-imgs-a9x2/push?done=+1'

On error

curl -s 'https://statb.io/b/convert-imgs-a9x2/push?errors=+1'

Finish

curl -s 'https://statb.io/b/convert-imgs-a9x2/push?status=0'

Code migration with metrics

curl -s 'https://statb.io/b/migrate-v3-kq82/push?files_total=48&files_done=+1&tests_pass=142&tests_fail=3'

Training loop

curl -s "https://statb.io/b/train-bert-e4p1/push?epoch=+1&loss=${LOSS}&acc=${ACC}&lr=${LR}"

🔒 Constraints

  • Always tell the user the board URL at the start so they can open it.
  • Push at meaningful intervals, not every line of code. Once per logical
  • step, batch, or every 10–30 seconds for continuous work.
  • Use increment (+N) for counters so concurrent pushes don't clobber.
  • Use set (plain number) for gauges like percentages, temperatures, rates.
  • Do not push sensitive data. Board IDs are unguessable but boards are
  • not access-controlled. Never push passwords, tokens, PII, or secrets.
  • Silent push. Use curl -s to suppress output. Push failures are
  • non-fatal — do not let a failed push stop the actual work.
  • Free tier limits: max 16 keys per board. Keep it focused.
  • View on ClawHub
    TERMINAL
    clawhub install statb

    🧪 Use this skill with your agent

    Most visitors already have an agent. Pick your environment, install or copy the workflow, then run the smoke-test prompt above.

    🔍 Can't find the right skill?

    Search 60,000+ AI agent skills — free, no login needed.

    Search Skills →