autobot-health-check
Skill21 starsChanged 45 days agoMITView on GitHub
Check an installed AutoBot workspace with its read-only doctor and focused runtime diagnostics. Use for installation health, capability readiness or a requested health report; a check alone does not authorize repairs.
In this repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- delegate-and-verifySkill
- finish-the-missionSkill
- first-timeSkill
- messages-inbox-triageSkill
- remember-and-improveSkill
- slack-inbox-triageSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Run from the verified installation root:
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
AutoBot health check
Resolve the intended installed project and receipt before running commands. Do not select a different installation or treat a release-source checkout as an installed workspace. Read docs/CLI-REFERENCE.md and docs/TROUBLESHOOTING.md from that installation when needed for interpretation.
Run from the verified installation root:
./runtime/bin/autoassist version
./runtime/bin/autoassist doctorThe installation doctor is read-only and does not need sign-in or Node. Separate installation integrity from optional capabilities. When Node 22 or newer is available, use the supported read-only core commands:
./runtime/bin/autoassist core status < /dev/null
./runtime/bin/autoassist core capabilities < /dev/null
./runtime/bin/autoassist core heartbeat < /dev/null
./runtime/bin/autoassist core orphans < /dev/nullScope any further inspection to the reported subsystem or requested root. Do not export private memory, dump whole task records, search personal stores, run tick, enable a service, change settings, perform a send or launch UI/permission probes as part of this check. Never run the release privacy scanner on a populated personal installation.
Report installation integrity, runtime availability and any actionable diagnostic separately. A missing optional integration is not proof the installation failed. Native Voice, Goals, Computer Use and schedules require actual native capability evidence; a local marker does not prove they work. Monitoring with no fresh observation is unknown, not proof of a stalled task.
For each relevant failure, give the observed code, affected capability and smallest next diagnostic or repair. Do not copy sensitive payloads into the report. Reuse an existing issue when appropriate. Run only the smallest focused check needed to resolve ambiguity, and stop once the affected contract is established.
Immediately before reporting changing runtime health, take one final bounded read of the authoritative result. State what was actually checked. A request to diagnose or report health does not authorize production repair; carry out a repair only when the user's request includes it.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

