Pilot Model Share
Distribute ML model files with model card metadata and version tracking over Pilot Protocol. Use this skill when: 1. You need to share PyTorch, ONNX, or SafeTensors model files between agents 2. You want to distribute models with metadata (architecture, training info, metrics) 3. You need model versioning and compatibility checking Do NOT use this skill when: - You need to transfer datasets (use pilot-dataset instead) - You need to transfer general files (use pilot-share instead) - You need real-time model inference results (use pilot-rpc instead)
Install
npx skills add TeoSlayer/pilot-skills --skill pilot-model-sharegit clone --depth 1 https://github.com/TeoSlayer/pilot-skills.git /tmp/pilot-skills
mkdir -p ~/.claude/skills
cp -r /tmp/pilot-skills/skills/pilot-model-share ~/.claude/skills/pilot-model-sharePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# pilot-model-share
ML model distribution with model cards, metadata, and version tracking.
## Commands
### Publish Model Availability
```bash
pilotctl --json publish "$PEER" models --data '{"type":"model_available","name":"resnet50","version":"1.0.0","framework":"pytorch"}'
```
### Request Model
```bash
pilotctl --json send-message "$DEST" --data '{"type":"model_request","name":"resnet50","preferred_format":"onnx"}'
```
### Send Model with Metadata
```bash
pilotctl --json send-message "$DEST" --data '{"type":"model_metadata","name":"llama3_8b","file":{"checksum":"abc123"}}'
pilotctl --json send-file "$DEST" "$MODEL_FILE"
```
### Validate Checksum
```bash
EXPECTED_CHECKSUM=$(pilotctl --json inbox | jq -r '.messages[] | select(.type == "model_metadata") | .file.checksum' | head -1)
ACTUAL_CHECKSUM=$(md5sum "$RECEIVED_MODEL" | cut -d' ' -f1)
[ "$EXPECTED_CHECKSUM" = "$ACTUAL_CHECKSUM" ] && echo "Model verified"
```
## Workflow Example
```bash
#!/bin/bash
# Model distribution
PEER="agent-b"
share_model() {
local model_file="$1"
local model_name="${2:-$(basename $model_file .pth)}"
pilotctl --json publish "$PEER" models --data "{\"type\":\"model_available\",\"name\":\"$model_name\"}"
}
share_model "model.pth" "my-model"
```
## Dependencies
Requires pilot-protocol, pilotctl, jq, and md5sum.Details
- Skill name
pilot-model-share- Repository
- TeoSlayer/pilot-skills
- Path
skills/pilot-model-share/SKILL.md- License
- AGPL-3.0
- Repo updated
- 9 November 2026
FAQ
What does the Pilot Model Share skill do?
Distribute ML model files with model card metadata and version tracking over Pilot Protocol. Use this skill when: 1. You need to share PyTorch, ONNX, or SafeTensors model files between agents 2. You want to distribute models with metadata (architecture, training info, metrics) 3. You need model versioning and compatibility checking Do NOT use this skill when: - You need to transfer datasets (use pilot-dataset instead) - You need to transfer general files (use pilot-share instead) - You need real-time model inference results (use pilot-rpc instead)
How do I install the Pilot Model Share skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add TeoSlayer/pilot-skills --skill pilot-model-share. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Pilot Model Share popular?
It lives in TeoSlayer/pilot-skills, which has 9 GitHub stars and 3 forks.
Related skills
Pilot A2a Bridge
9TeoSlayer/pilot-skills
Bridge A2A (Agent-to-Agent) protocol messages over Pilot tunnels. Use this skill when: 1. You need to connect A2A agents across different networks 2. You want to route A2A messages through Pilot's overlay network 3. You're building multi-agent systems that need reliable messaging Do NOT use this skill when: - Agents are on the same local network (use direct A2A instead) - You need raw TCP/UDP access (use pilot-protocol directly) - The daemon is not running
Pilot Ad Campaign Manager Setup
9TeoSlayer/pilot-skills
Deploy an ad campaign management system with 4 agents that automate campaign strategy, creative production, real-time bidding, and performance analytics. Use this skill when: 1. User wants to set up an automated ad campaign management pipeline 2. User is configuring an agent as part of an advertising or media buying workflow 3. User asks about automating campaign strategy, creative testing, or bid optimization across agents Do NOT use this skill when: - User wants to track a single metric (use pilot-metrics instead) - User wants a one-off data stream (use pilot-stream-data instead)
Pilot Agent Marketplace Setup
9TeoSlayer/pilot-skills
Deploy a decentralized agent marketplace with 4 agents. Use this skill when: 1. User wants to set up an agent capability marketplace 2. User is configuring a directory, matchmaker, escrow, or gateway agent 3. User asks about capability discovery, auctions, or escrow settlement Do NOT use this skill when: - User wants to discover a single agent (use pilot-discover instead) - User wants to run a single auction (use pilot-auction instead)
Pilot Momy
9TeoSlayer/pilot-skills
Local directory of known agents with cached metadata. Use this skill when: 1. Maintaining a persistent directory of frequently contacted agents 2. Caching agent metadata for offline reference 3. Building a local address book of trusted or favorite agents Do NOT use this skill when: - You need real-time network discovery (use pilot-discover instead) - You need to visualize relationships (use pilot-network-map instead) - You need to establish new trust (use pilot-trust instead)
Pilot Ml Training Pipeline Setup
9TeoSlayer/pilot-skills
Deploy an end-to-end ML training pipeline with 4 agents. Use this skill when: 1. User wants to set up a machine learning training pipeline 2. User is configuring a data prep, training, evaluation, or serving agent 3. User asks about ML model lifecycle management across agents Do NOT use this skill when: - User wants to share a single model file (use pilot-model-share instead) - User wants to transfer a dataset (use pilot-dataset instead)
Pilot Presence
9TeoSlayer/pilot-skills
Real-time online/offline/busy presence tracking for agent fleets using ping and pub/sub. Use this skill when: 1. You need to track which agents are online/offline/busy 2. You need to broadcast presence changes to interested peers 3. You need to discover available agents for task routing 4. You need to maintain a real-time agent directory Do NOT use this skill when: - You only need static peer discovery (use pilotctl trust instead) - You need detailed health metrics (use pilot-metrics instead) - You need persistent audit logs (use pilot-event-log instead)
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.