agentsclimarketplace

Pilot digital twin setup

Skill TeoSlayer/pilot-skills/skills/pilot-digital-twin-setup

80+ agent skills for Pilot Protocol — communication, file transfer, trust, task routing, swarm coordination, and more

Install
npx -y skills add TeoSlayer/pilot-skills --skill pilot-digital-twin-setup

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 7 stars7 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

Deploy a digital twin platform with 4 agents. Use this skill when: 1. User wants to set up a digital twin for physical asset monitoring and predictive maintenance 2. User is configuring agents for sensor ingestion, physics simulation, or anomaly detection 3. User asks about predictive maintenance, asset health monitoring, or real-vs-predicted comparison Do NOT use this skill when: - User wants basic metrics collection (use pilot-metrics instead) - User only needs event filtering without a twin model (use pilot-event-filter instead) - User wants a single alert notification (use pilot-alert instead)

The file declares its own license as AGPL-3.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

6.4 KB, ~1.5k tokens by cl100k_base, as published. Nobody here has run it

Digital Twin Setup

Deploy 4 agents: sensor-bridge, model-engine, anomaly-detector, and action-planner.

Roles

RoleHostnameSkillsPurpose
sensor-bridge<prefix>-sensor-bridgepilot-stream-data, pilot-metrics, pilot-gossipIngests real-time telemetry from physical assets
model-engine<prefix>-model-enginepilot-dataset, pilot-task-router, pilot-consensusMaintains physics model, runs simulations
anomaly-detector<prefix>-anomaly-detectorpilot-event-filter, pilot-alert, pilot-audit-logDetects drift between real and predicted behavior
action-planner<prefix>-action-plannerpilot-webhook-bridge, pilot-cron, pilot-slack-bridgeSchedules maintenance, notifies field teams

Setup Procedure

Step 1: Ask the user which role this agent should play and what prefix to use.

Step 2: Install the skills for the chosen role:

# For sensor-bridge:
clawhub install pilot-stream-data pilot-metrics pilot-gossip
# For model-engine:
clawhub install pilot-dataset pilot-task-router pilot-consensus
# For anomaly-detector:
clawhub install pilot-event-filter pilot-alert pilot-audit-log
# For action-planner:
clawhub install pilot-webhook-bridge pilot-cron pilot-slack-bridge

Step 3: Set the hostname and write the manifest to ~/.pilot/setups/digital-twin.json.

Step 4: Tell the user to initiate handshakes with the peers for their role.

Manifest Templates Per Role

sensor-bridge

{
  "setup": "digital-twin", "role": "sensor-bridge", "role_name": "Sensor Bridge",
  "hostname": "<prefix>-sensor-bridge",
  "skills": {
    "pilot-stream-data": "Ingest real-time sensor telemetry from physical assets.",
    "pilot-metrics": "Track sensor health, sampling rates, and data quality.",
    "pilot-gossip": "Discover and sync with peer sensor bridges."
  },
  "data_flows": [{ "direction": "send", "peer": "<prefix>-model-engine", "port": 1002, "topic": "telemetry", "description": "Unified telemetry stream from physical assets" }],
  "handshakes_needed": ["<prefix>-model-engine"]
}

model-engine

{
  "setup": "digital-twin", "role": "model-engine", "role_name": "Model Engine",
  "hostname": "<prefix>-model-engine",
  "skills": {
    "pilot-dataset": "Store physics model parameters and simulation state.",
    "pilot-task-router": "Route simulation tasks across asset models.",
    "pilot-consensus": "Reconcile model state across redundant engines."
  },
  "data_flows": [
    { "direction": "receive", "peer": "<prefix>-sensor-bridge", "port": 1002, "topic": "telemetry", "description": "Real-time sensor data" },
    { "direction": "send", "peer": "<prefix>-anomaly-detector", "port": 1002, "topic": "prediction", "description": "Expected behavior baselines and drift metrics" }
  ],
  "handshakes_needed": ["<prefix>-sensor-bridge", "<prefix>-anomaly-detector"]
}

anomaly-detector

{
  "setup": "digital-twin", "role": "anomaly-detector", "role_name": "Anomaly Detector",
  "hostname": "<prefix>-anomaly-detector",
  "skills": {
    "pilot-event-filter": "Filter predictions by drift threshold and severity.",
    "pilot-alert": "Emit anomaly alerts for critical deviations.",
    "pilot-audit-log": "Log all detected anomalies with evidence snapshots."
  },
  "data_flows": [
    { "direction": "receive", "peer": "<prefix>-model-engine", "port": 1002, "topic": "prediction", "description": "Model predictions to compare" },
    { "direction": "send", "peer": "<prefix>-action-planner", "port": 1002, "topic": "anomaly-alert", "description": "Anomaly alerts with severity and root cause" }
  ],
  "handshakes_needed": ["<prefix>-model-engine", "<prefix>-action-planner"]
}

action-planner

{
  "setup": "digital-twin", "role": "action-planner", "role_name": "Action Planner",
  "hostname": "<prefix>-action-planner",
  "skills": {
    "pilot-webhook-bridge": "Push maintenance orders to field team systems.",
    "pilot-cron": "Schedule maintenance windows during low-impact periods.",
    "pilot-slack-bridge": "Notify operations teams of recommended interventions."
  },
  "data_flows": [
    { "direction": "receive", "peer": "<prefix>-anomaly-detector", "port": 1002, "topic": "anomaly-alert", "description": "Anomaly alerts to act on" },
    { "direction": "send", "peer": "external", "port": 443, "topic": "maintenance-order", "description": "Work orders to field management systems" }
  ],
  "handshakes_needed": ["<prefix>-anomaly-detector"]
}

Data Flows

  • sensor-bridge -> model-engine : real-time telemetry from physical assets (port 1002)
  • model-engine -> anomaly-detector : predictions and expected behavior baselines (port 1002)
  • anomaly-detector -> action-planner : anomaly alerts with severity and root cause (port 1002)
  • action-planner -> external : maintenance orders to field team systems (port 443)

Workflow Example

# On sensor-bridge -- stream telemetry:
pilotctl --json publish <prefix>-model-engine telemetry '{"asset_id":"PUMP-A7","sensors":{"temperature_c":87.3,"vibration_mm_s":4.2}}'
# On model-engine -- send prediction:
pilotctl --json publish <prefix>-anomaly-detector prediction '{"asset_id":"PUMP-A7","drift_pct":{"temperature":6.3,"vibration":50.0}}'
# On anomaly-detector -- alert planner:
pilotctl --json publish <prefix>-action-planner anomaly-alert '{"asset_id":"PUMP-A7","severity":"warning","anomaly_type":"bearing_degradation"}'

Dependencies

Requires pilot-protocol skill, pilotctl binary, clawhub binary, and a running daemon.

What ships with it: 1 file

5.0 KB alongside SKILL.md

Gives 0 of the 12 instructions most project setup skills give in ~1.5k tokens

Counted across 999 of the 1,637 authors here whose files we hold, read 2026-08-07

  • Ask one question at a timein 29 of 999, across 28 files
  • Detect the package manager from lockfilesin 28 of 999, across 9 files
  • Present findings to the userin 26 of 999, across 5 files
  • Explore current repo statein 24 of 999, across 3 files
  • Update the agent skills block in place if it existsin 24 of 999, across 3 files
  • Install husky lint-staged and prettierin 23 of 999, across 4 files
  • Create the lintstagedrc filein 22 of 999, across 3 files
  • Commit all changed filesin 22 of 999, across 3 files
  • Run lint-staged to verify it worksin 22 of 999, across 3 files
  • Create the husky pre-commit filein 21 of 999, across 2 files
  • Create a prettierrc file if missingin 21 of 999, across 2 files
  • Initialize huskyin 21 of 999, across 2 files

Said here and by no other author read

  • ask the user which role and prefix to use
  • install skills for the chosen role
  • set the hostname for the chosen role
  • write the manifest to digital-twin.json
  • tell the user to initiate handshakes with peers

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.