菜单
Use Mirra to the places a space publishes to — its corporate x, blog, newsletter — and the drafted copy waiting to go out to them. use listchannels to see what this space.... Covers all Space Channels SDK operations via REST API.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | mirra-channels |
| description | Use Mirra to the places a space publishes to — its corporate x, blog, newsletter — and the drafted copy waiting to go out to them. use listchannels to see what this space.... Covers all Space Channels SDK operations via REST API. |
| allowed-tools | Read, Bash(curl:*, jq:*) |
The places a space publishes to — its corporate X, blog, newsletter — and the drafted copy waiting to go out to them. Use listChannels to see what this space publishes to and which channels are healthy, then createDraftSet to file per-channel copy drafted from a burst update card; a teammate reviews and approves it in the app before anything is sent. After you actually post, record the outcome with markDraftSent (which attaches the live post back to the update card that produced it) or markDraftFailed (which flags the channel as needing reconnection). These ops never post anything themselves. The space is taken from your credential, not from arguments.
You need the user's API key. Ask for these if not provided:
API_KEY: Mirra API key (generated in Mirra app > Settings > API Keys)API_URL: Defaults to https://api.fxn.world (only ask if they mention a custom server)All operations use a single POST endpoint with the resource ID and method in the body:
curl -s -X POST "${API_URL}/api/sdk/v2/resources/call" \
-H "Content-Type: application/json" \
-H "x-api-key: ${API_KEY}" \
-d '{
"resourceId": "channels",
"method": "{operation}",
"params": { ...args }
}' | jq .
Replace {operation} with the operation name from the table below.
Legacy alternative:
POST ${API_URL}/api/sdk/v1/channels/{operation}with args as the request body also works but is not recommended for new integrations.
| Operation | Description |
|---|---|
listChannels | The channels this space publishes to, with the per-channel limits you must draft within (characte... |
createDraftSet | File drafted copy for review, one draft per channel. Nothing is sent — a teammate edits, approves... |
getDraftSet | Read one draft set, including which drafts are queued for sending. Call this when you receive a c... |
listPendingDraftSets | Draft sets in this space still awaiting review or partially sent. Useful for a nightly reminder f... |
markDraftSent | Record that you posted one draft. This also attaches the live post back to the update card it cam... |
markDraftFailed | Record that a post failed. Also writes the reason onto the channel itself, which is what surfaces... |
listChannelsThe channels this space publishes to, with the per-channel limits you must draft within (character cap, whether a title is required). Call this before drafting — a channel that is disabled or carrying lastError should not get copy written for it.
Returns:
AdapterOperationResult: Returns: channels (the space registry), descriptors (per-type limits and voice hints)
Example:
curl -s -X POST "${API_URL}/api/sdk/v2/resources/call" \
-H "Content-Type: application/json" \
-H "x-api-key: ${API_KEY}" \
-d '{"resourceId":"channels","method":"listChannels","params":{}}' | jq .
Example response:
{
"channels": [
{
"id": "ch_1",
"type": "twitter",
"label": "@fxn",
"enabled": true,
"healthy": true
}
]
}
createDraftSetFile drafted copy for review, one draft per channel. Nothing is sent — a teammate edits, approves and presses Send, which calls you back to do the posting. Idempotent per source card revision: calling twice for the same card returns the existing set rather than making a second one. IMPORTANT: bail out before calling this when the triggering event has revised:true, or every revision of a burst card re-drafts the same work.
Arguments:
sourceCardId (string, required): The update card this copy was drafted from (cardId from the items.update.published event)drafts (array, required): One per channel: [{ channelId, channelType, channelLabel, title?, body }]. channelId/type/label come from listChannels. Respect each channel's character cap — an over-length draft cannot be approved.Returns:
AdapterOperationResult: Returns: setId, created (false when this call matched an existing set), draftCount
Example:
curl -s -X POST "${API_URL}/api/sdk/v2/resources/call" \
-H "Content-Type: application/json" \
-H "x-api-key: ${API_KEY}" \
-d '{"resourceId":"channels","method":"createDraftSet","params":{"sourceCardId":"6a64b5923657f98c84d1531c","drafts":[{"channelId":"ch_1","channelType":"twitter","channelLabel":"@fxn","body":"Spaces can now hold their own credentials."}]}}' | jq .
Example response:
{
"setId": "6a6600112233445566778899",
"created": true,
"draftCount": 1
}
getDraftSetRead one draft set, including which drafts are queued for sending. Call this when you receive a channels.send.requested event — it tells you exactly what a person approved and what the final edited copy says.
Arguments:
setId (string, required): The draft set id (from the send event)Returns:
AdapterOperationResult: Returns: set (with drafts and their statuses), stale (true if the source card has been revised since drafting)
Example:
curl -s -X POST "${API_URL}/api/sdk/v2/resources/call" \
-H "Content-Type: application/json" \
-H "x-api-key: ${API_KEY}" \
-d '{"resourceId":"channels","method":"getDraftSet","params":{"setId":"6a6600112233445566778899"}}' | jq .
Example response:
{
"stale": false
}
listPendingDraftSetsDraft sets in this space still awaiting review or partially sent. Useful for a nightly reminder flow.
Returns:
AdapterOperationResult: Returns: sets, count
Example:
curl -s -X POST "${API_URL}/api/sdk/v2/resources/call" \
-H "Content-Type: application/json" \
-H "x-api-key: ${API_KEY}" \
-d '{"resourceId":"channels","method":"listPendingDraftSets","params":{}}' | jq .
Example response:
{
"count": 1
}
markDraftSentRecord that you posted one draft. This also attaches the live post back to the update card it came from, so the card later reads "shipped this, and here is where we said so". Deduped on url — a retried dispatch adds one link, not two.
Arguments:
setId (string, required): The draft set idchannelId (string, required): Which channel was posted tosentUrl (string, required): Permalink to the live postReturns:
AdapterOperationResult: Returns: setId, status (the set's status after this draft settled)
Example:
curl -s -X POST "${API_URL}/api/sdk/v2/resources/call" \
-H "Content-Type: application/json" \
-H "x-api-key: ${API_KEY}" \
-d '{"resourceId":"channels","method":"markDraftSent","params":{"setId":"6a6600112233445566778899","channelId":"ch_1","sentUrl":"https://x.com/fxn/status/1"}}' | jq .
Example response:
{
"setId": "6a6600112233445566778899",
"status": "sent"
}
markDraftFailedRecord that a post failed. Also writes the reason onto the channel itself, which is what surfaces the Reconnect prompt in the app — and is the only trace that survives once the draft set is deleted. Always call this on failure rather than swallowing the error.
Arguments:
setId (string, required): The draft set idchannelId (string, required): Which channel failederror (string, required): What went wrong, in words a teammate can act onReturns:
AdapterOperationResult: Returns: setId, status (the set's status after this draft settled)
Example:
curl -s -X POST "${API_URL}/api/sdk/v2/resources/call" \
-H "Content-Type: application/json" \
-H "x-api-key: ${API_KEY}" \
-d '{"resourceId":"channels","method":"markDraftFailed","params":{"setId":"6a6600112233445566778899","channelId":"ch_1","error":"The X token was revoked"}}' | jq .
Example response:
{
"setId": "6a6600112233445566778899",
"status": "partiallySent"
}
All SDK responses return the operation payload wrapped in a standard envelope:
{
"success": true,
"data": { ... }
}
The data field contains the operation result. Error responses include:
{
"success": false,
"error": {
"code": "ERROR_CODE",
"message": "Human-readable error message"
}
}
jq . to pretty-print responses, jq .data to extract just the payloaddata.results or directly in data (check examples)--fail-with-body to curl to see error details on HTTP failuresexport API_KEY="your-key"Use Mirra to living dashboards — natively-rendered grids of typed widgets (stat, image_card, list, progress, sparkline) that flows keep current by pushing data into them..... Covers all Dashboards SDK operations via REST API.
Use Mirra to execute user-defined scripts in aws lambda. Covers all Scripts SDK operations via REST API.
Use Mirra to the space's shared work-ledger. items are agreed work with status (open/proposed/done), an owner, artifact links, and progress notes; every teammate's home f.... Covers all Work Items SDK operations via REST API.
The team work-ledger ritual for agents on a Mirra space: track agreed work, propose discoveries (then ask in chat), relay approvals, close what ships, and publish ONE narrated update card per work burst — revise, never stack. Rides the Mirra items adapter / MCP work-ledger tools.
START HERE for anything Mirra. Load this whenever the repo you're working in has a .mirra/ directory (it's linked to a Mirra team space), or your human mentions their Mirra space, teammates' updates, or the team ledger. Directs the ambient team rituals — record work in the shared ledger, publish update cards, ask the space before expanding scope — and indexes every detail-level mirra-* skill.
Use Mirra to create feed items with flexible content blocks for user notifications and action results. Covers all Feed Items SDK operations via REST API.