monitor-iot-edge
Skill18 starsChanged 2 months agoApache-2.0View on GitHub
Monitor reviewed Grafana telemetry and freshness evidence for IoT devices and edge fleets. Use for smart devices, home automation sensors, remote equipment, wind turbines, space hardware, device-fleet freshness, missing telemetry, and bounded edge-health comparisons.
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- create-fusion-deliverablesSkill
- edit-fusion-designSkill
- handoff-fusion-engineeringSkill
- inspect-fusion-designSkill
- prepare-fusion-manufacturingSkill
- reconcile-fusion-dataSkill
- run-fusion-cloud-recipesSkill
- setup-autodesk-fusionSkill
- analyze-log-signalsSkill
- inspect-infrastructure-healthSkill
- investigate-application-performanceSkill
- review-business-kpisSkill
- setup-grafana-observabilitySkill
- audit-ios-readinessSkill
- plan-react-native-portSkill
- port-react-native-sliceSkill
- verify-swiftui-paritySkill
- audit-review-eval-validitySkill
- benchmark-review-configsSkill
- normalize-review-runsSkill
- recommend-review-reference-architectureSkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 3 are distinctive, and 7 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Run the fixed grafana.iot-edge pack for an enrolled device or fleet scope and preserve telemetry gaps explicitly.
- Very specific: line 12
Use only grafana_profile_status, grafana_list_packs, grafana_run_pack, grafana_get_evidence, and grafana_resolve_link.
- Distinctive: line 14
Never accept or construct provider queries, SQL, URLs, headers, datasource IDs, device identifiers, panel JSON, variables, or raw telemetry …
- Distinctive: line 15
Do not send device commands, change sampling, restart equipment, edit Grafana, or mutate alerts or datasources.
- Very specific: line 21
Call grafana_profile_status({profileAlias}).
- Very specific: line 22
Call grafana_list_packs({profileAlias}) and require the exact active pack ID grafana.iot-edge.
- Distinctive: line 23
Create one non-secret idempotency key and reuse it only for an exact retry.
- Very specific: line 24
Call grafana_run_pack with that key, the aliases, packId: "grafana.iot-edge", origin, current window, and optional baseline window.
- Very specific: line 26
Call grafana_get_evidence({reportRef,evidenceRef}) only for report-owned references needed to support a material device or fleet claim.
- Very specific: line 27
Call grafana_resolve_link({reportRef,linkRef}) only for a same-report link reference that helps a human inspect the enrolled Grafana view.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Monitor IoT and Edge
Run the fixed grafana.iot-edge pack for an enrolled device or fleet scope and preserve telemetry gaps explicitly.
Safety contract
- Use only
grafana_profile_status,grafana_list_packs,grafana_run_pack,grafana_get_evidence, andgrafana_resolve_link. - Accept only profile and scope aliases; one declared
LIVE,REPLAY, orSIMULATEDorigin; bounded current and baseline windows; and opaque references returned by these tools. - Never accept or construct provider queries, SQL, URLs, headers, datasource IDs, device identifiers, panel JSON, variables, or raw telemetry requests.
- Do not send device commands, change sampling, restart equipment, edit Grafana, or mutate alerts or datasources. This skill is observational only.
- Confirm
LIVEaccess. Never combineLIVE,REPLAY, andSIMULATEDtelemetry into one fleet claim.
Workflow
- Establish
profileAlias, an enrolled device or fleetscopeAlias, origin, and a current window no longer than seven days. Use an equal-duration, non-overlapping baseline only when change analysis is needed. - Call
grafana_profile_status({profileAlias}). Stop onERRORor blocked readiness; disclosePARTIALreadiness. - Call
grafana_list_packs({profileAlias})and require the exact active pack IDgrafana.iot-edge. - Create one non-secret idempotency key and reuse it only for an exact retry.
- Call
grafana_run_packwith that key, the aliases,packId: "grafana.iot-edge", origin, current window, and optional baseline window. - Review telemetry first and device freshness second. Preserve returned timestamps, units, severity, direction, nulls, and fleet/device distinctions.
- Call
grafana_get_evidence({reportRef,evidenceRef})only for report-owned references needed to support a material device or fleet claim. - Call
grafana_resolve_link({reportRef,linkRef})only for a same-report link reference that helps a human inspect the enrolled Grafana view. Never accept a URL as input.
A stale device is not necessarily offline, unsafe, or failed. An empty telemetry result is an evidence gap, not a zero measurement. Treat a freshness issue as rule-backed only when it has classification: SIGNED_RULE; treat classification: DEVIATION only as a deviation.
Interpret report status exactly
COMPLETE: expected telemetry and freshness evidence completed; evaluate the returned device and fleet signals.EMPTY: no usable telemetry was returned; do not substitute zero values or declare devices healthy.STALE: the latest evidence exceeds the reviewed freshness bound; state the age and affected scope.PARTIAL: some devices, signals, or expected evidence are missing, failed, or mixed; avoid a fleet-wide conclusion.CONTRADICTORY: telemetry conflicts; preserve the evidence references and withhold a single state claim.ERROR: collection failed or was rejected; report the sanitized error and stop.
Completion format
Return scope, origin, windows, overall status, telemetry summary and freshness by returned scope with returned severity and direction, issues with their returned classification, gaps and contradictions, evidence references for material claims, and only successfully resolved report-owned links.
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.

