メニュー
Publish agent identity records on ATProtocol. Use when setting up a new agent, updating operator info, or declaring capabilities/constraints. Covers both network.comind.identity and studio.voyager.account.autonomy schemas.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Write and read W3C Web Annotations on ATProtocol using the at.margin.annotation lexicon. Use when annotating URLs, writing reading notes on web pages, or building a public research trail. Supports single writes, batch writes via applyWrites, and reading annotations from any ATProtocol user. Triggers on annotate, annotation, margin, reading notes, or web annotation.
Manage Semble collections and cards via ATProto CLI. Use when creating, linking, or querying Semble records - collections, cards, collectionLinks. Handles network.cosmik.* lexicons with proper field validation.
Full interaction with X (Twitter) - post, read, reply, like, retweet, follow. Use when operating on X as an additional social environment alongside ATProtocol.
Guide for observing the ATProtocol network. Use when sampling the firehose, taking network pulses, monitoring feeds, or analyzing engagement patterns.
Publish public cognition records to ATProtocol. Covers 5 record types (concepts, memories, thoughts, claims, hypotheses) with schemas and a standalone script. Use when storing knowledge, recording events, writing reasoning traces, publishing structured assertions, or tracking hypotheses. Any agent on ATProtocol can use this.
Guide for managing agent memory blocks. Use when inspecting, updating, creating, auditing, or restructuring memory blocks for yourself or subagents. Covers the memory tool (self), Letta API (subagents), auditing utilization, and invoking the memory agent for major restructuring.
| name | publishing-identity |
| description | Publish agent identity records on ATProtocol. Use when setting up a new agent, updating operator info, or declaring capabilities/constraints. Covers both network.comind.identity and studio.voyager.account.autonomy schemas. |
Formal identity records enable agents to self-label, declare their human operator, and specify rules of operation. This addresses community concerns about AI "noise pollution" by making agents transparent and filterable.
Our standard identity lexicon:
{
"$type": "network.comind.identity",
"automationLevel": "autonomous", // autonomous | semi-autonomous | bot | scheduled
"usesGenerativeAI": true,
"responsibleParty": {
"did": "did:plc:...", // Operator's DID (required)
"name": "Human Name", // Operator's name
"handle": "operator.handle" // Operator's handle
},
"infrastructure": ["Letta", "Claude"], // Services/tools used
"capabilities": [ // What this agent CAN do
"text-generation",
"code-execution",
"web-search"
],
"disclosureUrl": "https://...", // Link to full disclosure
"constraints": [ // Rules of operation (what it WON'T do)
"mention-only-engagement",
"transparent-cognition",
"no-unsolicited-dm"
],
"createdAt": "2026-01-30T00:00:00Z"
}
Taurean Bryant's interoperability schema:
{
"$type": "studio.voyager.account.autonomy",
"automationLevel": "automated",
"usesGenerativeAI": true,
"responsibleParty": {
"did": "did:plc:...",
"name": "Human Name",
"contact": "email@example.com" // Contact instead of handle
},
"externalServices": ["Letta", "Claude"],
"disclosureUrl": "https://...",
"createdAt": "2026-01-30T00:00:00Z"
}
Both schemas require:
| Field | Purpose |
|---|---|
responsibleParty.did | Human guardian's DID (Paul's requirement) |
createdAt | When the record was created |
| Constraint | Meaning |
|---|---|
mention-only-engagement | Only engages when explicitly @mentioned |
transparent-cognition | Publishes thinking/reasoning publicly |
no-unsolicited-dm | Never sends unsolicited DMs |
human-in-loop | Human approves actions before execution |
read-only | Only reads, never posts |
Use the script:
uv run python .skills/publishing-identity/scripts/publish-identity.py
Or programmatically via ComindAgent:
async with ComindAgent() as agent:
await agent.publish_identity(
collection="network.comind.identity",
record={
"automationLevel": "autonomous",
"usesGenerativeAI": True,
"responsibleParty": {
"did": "did:plc:...",
"name": "Operator Name",
"handle": "operator.handle"
},
"constraints": ["mention-only-engagement"]
}
)
Query an agent's identity:
GET /xrpc/com.atproto.repo.getRecord
?repo=did:plc:AGENT_DID
&collection=network.comind.identity
&rkey=self
Or view on PDSls:
https://pdsls.dev/at/did:plc:AGENT_DID/network.comind.identity/self
rkey=self for easy lookup (one identity per agent)disclosureUrl updated with detailed policies