Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Report Evotown dispatch job completion after the agent finishes real work.
.claude/skills/exboys-evotown-dispatch-complete/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -27% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -62% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -49% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -74% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -66% | 0% |
Evotown dispatch messages include a footer like [evotown] job_id=job_…. Do not treat the OpenClaw hook HTTP response as task completion.
When the user-visible work is done:
bashevotown-agent-setup.py complete \ --job-id <job_id from the message> \ --status succeeded \ --summary "One-line outcome for the control plane"
On failure:
bashevotown-agent-setup.py complete --job-id <job_id> --status failed --exit-code 1 --summary "reason"
Requires EVOTOWN_ENGINE_INGEST_TOKEN (evi_…) in ~/.config/evotown/evotown.agent.env.
Alternatively POST run.completed to {EVOTOWN_URL}/api/v1/events with the same run_id as in the message footer.
Other measured skills in the registry, with their headline benchmark lift.