Smoke test
Skill jrausercisco/trmnl-agent-bridge/plugins/claude/trmnl-agent-bridge/skills/smoke-test
Publish local agent status snapshots to TRMNL Private Plugin webhooks.
npx -y skills add jrausercisco/trmnl-agent-bridge --skill smoke-testAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Run the TRMNL Agent Bridge smoke test in dry mode or live mode and summarize push and current-screen verification results.
SKILL.md
1.2 KB, 255 tokens by cl100k_base, as published. Nobody here has run it
Smoke Test
Use this skill when the user asks to test, validate, verify, or smoke-test the TRMNL Agent Bridge from Claude Code.
Dry Mode
Dry mode works without credentials and should be the default first check:
trmnl-agent smoke-test
From a local checkout:
PYTHONPATH=src python3 -m trmnl_agent_bridge.cli smoke-test
Live Mode
Use live mode only when the user has configured a test TRMNL Private Plugin webhook and explicitly wants a live push:
trmnl-agent smoke-test --push
When TRMNL device API credentials are also configured, verify the rendered screen path:
trmnl-agent smoke-test --push --fetch-screen --compare-screen --wait-seconds 30
Result Summary
Report:
- overall
ok - dry or live mode
- payload bytes and limit
- credential sources, never credential values
- push attempted and HTTP status when present
- current-screen fetch result when requested
- whether the before/after screen hash changed when comparison was requested
Do not echo webhook URLs, API tokens, device IDs, image URLs, or private payload bodies.