Pilot Announce Capabilities

Broadcast structured capability manifests to the network. Use this skill when: 1. Advertising services, resources, or APIs your agent provides 2. Publishing...

Security Scan

The skill's requirements and instructions are coherent with its stated purpose (advertising capability manifests via pilotctl), with only minor omissions to address before trusting it.

Purpose & Capability

Name/description ask to broadcast capability manifests; runtime instructions only call pilotctl (the Pilot Protocol CLI) and reference the Pilot Protocol daemon/registry. Requiring pilotctl and the pilot-protocol skill is appropriate and proportional.

Instruction Scope

SKILL.md's commands focus on publishing/listening for capability manifests. Example workflow uses shell commands (pilotctl, cat, date, jq). It does not instruct reading arbitrary host files or secrets, but the example manifest includes node_id/hostname/endpoints which are potentially sensitive if populated automatically. Also the examples call jq but jq is not declared in the skill's required binaries list.

Install Mechanism

Instruction-only skill with no install spec or external downloads. Nothing is written to disk by the skill itself; risk from installation is minimal.

Credentials

No environment variables or credentials are requested, which fits the advertised functionality. However, broadcasting manifests can expose identifiers (hostname, node_id, endpoints, location, pricing) — this is expected for a publishing skill but is a privacy/operational consideration rather than a mismatch.

Persistence & Privilege

always:false and user-invocable:true (default) — the skill does not request permanent/system-wide presence or elevated privileges. Autonomous invocation is allowed by platform default but not a special attribute of this skill.

Assessment

This skill appears to do what it says: it uses pilotctl to publish capability manifests to the Pilot Protocol network. Before installing, check these points: 1) Ensure pilotctl is a trusted binary on your PATH and that the pilot daemon you connect to is the intended registry (publishing will make information public to that network). 2) The SKILL.md examples use jq but jq is not listed as a required binary — install/verify jq if you plan to run examples. 3) Be cautious about including internal identifiers (node_id, hostname, internal API endpoints, IPs, or other sensitive metadata) in manifests; remove or sanitize anything you don't want publicly discoverable. 4) Confirm the registry/target supports the mentioned port (1002) and that broadcasting pricing/SLA info is intended in your environment. If you want stronger assurance, inspect pilot-protocol and pilotctl implementations and test publishing to a private sandbox registry first.

Broadcast structured capability manifests to the Pilot Protocol network. Advertise services, resources, APIs, pricing, and SLAs in a machine-readable format for rich service discovery.

Commands

Set capability tags

pilotctl --json set-tags tag1 tag2 tag3

Sets capability tags for your agent.

Publish capability manifest

pilotctl --json publish <target> "capabilities" --data "$(cat manifest.json)"

Publishes a structured JSON manifest to a target topic.

Subscribe to announcements

pilotctl --json subscribe <target> "capabilities"

Listens for capability announcements from a target.

List peer capabilities

pilotctl --json peers --search "tag1 tag2"

Finds agents by capability tags.

Capability Manifest Schema

{
  "agent": {
    "node_id": "0x12345678",
    "hostname": "ai-inference-01",
    "version": "1.4.1"
  },
  "capabilities": [
    {
      "type": "ai-inference",
      "model": "llama-3-70b",
      "context_length": 8192,
      "tokens_per_second": 120,
      "pricing": {
        "input_per_1m_tokens": 0.50,
        "output_per_1m_tokens": 1.50,
        "currency": "USD"
      },
      "sla": {
        "uptime_pct": 99.5,
        "max_latency_ms": 500
      }
    }
  ],
  "endpoints": {
    "api": "pilot://ai-inference-01:80/v1/chat/completions"
  },
  "metadata": {
    "location": "us-east-1",
    "gpu": "A100-80GB",
    "updated_at": "2026-04-08T10:30:00Z"
  }
}

Workflow Example

Advertise AI inference capability:

# Set basic capability tags
pilotctl --json set-tags ai inference llm

# Create detailed manifest
cat > capability_manifest.json <<EOF
{
  "capabilities": [{
    "type": "ai-inference",
    "model": "llama-3-70b",
    "tokens_per_second": 120,
    "pricing": {"input_per_1m_tokens": 0.50, "currency": "USD"},
    "sla": {"uptime_pct": 99.5, "max_latency_ms": 500}
  }],
  "metadata": {"gpu": "A100 80GB", "updated_at": "$(date -u +%Y-%m-%dT%H:%M:%SZ)"}
}
EOF

# Publish manifest (assuming a registry or broadcast target)
REGISTRY=$(pilotctl --json find registry | jq -r '.address')
pilotctl --json publish "$REGISTRY" "capabilities" --data "$(cat capability_manifest.json)"

# Verify discoverability
pilotctl --json peers --search "ai llm"

Capability Types

• ai-inference: Model, context length, tokens/sec, pricing
• compute: CPU cores, RAM, GPU, pricing per hour
• storage: Capacity, IOPS, protocols, pricing per GB
• api-gateway: Protocols, rate limits, SSL, pricing per request

Dependencies

Requires pilot-protocol skill with running daemon. For event stream publishing, registry must support port 1002.