---
name: instagram-dm-operations
description: "Triage business messages, preserve conversation context and verify authorized replies without mixing personal conversations. Use for instagram message operations tasks; select only the requested methods."
metadata:
  version: "1.0.0"
---

# Instagram Message Operations

Triage business messages, preserve conversation context and verify authorized replies without mixing personal conversations.

## OLLIE Runtime integration

Use relevant methods under the active OLLIE Operator. Read live Workspace Context and tenant bindings for client facts, account identity, goals, permissions and required inputs. Consume ask-ollie-authority-core for authority, outloop-access-fallback for access and recovery, email-lifecycle-core for communication, and the bootstrapper Runtime Contract for execution ownership and completion. This skill introduces no scheduler, independent permission policy or competing Runtime owner.

Discover the active Workspace’s approved capabilities before choosing API or browser access. Use Outloop for external service actions and the host’s supported tools for local artifacts. A product name in this package is not an access grant. Never import private account configuration or follow a source method that bypasses host restrictions. Apply the current task’s authorization; a library update does not grant permission to send, publish or activate a campaign.

## Required inputs

- Approved business account and inbox surfaces
- Current product facts and reply policy
- Conversation history and message intent
- Authorized response or draft scope

Use for business DM triage, reply drafting and authorized response verification. Public comment moderation is a different capability. Read [message decisions](references/messages.md).

## Establish the correct inbox

Resolve the approved account and connected business inbox. Do not assume a Page and Instagram profile are separate inboxes or inspect a personal account because it happens to be logged in. Deduplicate mirrored threads across approved surfaces using stable IDs and event timestamps.

## Classify before drafting

Separate product questions, buying intent, support, implementation buyers, prospective delivery partners, applicants, unsolicited pitches, personal conversation and ambiguity. Referral context from an ad or story helps interpret intent but does not grant permission or establish buying readiness. Priority labels are evidence, not decisions.

## Respond with current context

Answer the actual question in the sender’s language, using approved product facts and relevant destinations. Avoid transplanting personal voice rules, prices, platform support claims or follow-up caps from another workspace. Preserve unresolved commitments in the thread and suppress duplicate replies.

## Verify the authorized action

Send only within the active task’s communication authority and the provider’s permitted channel. Verify the resulting message in the intended thread before recording it as sent. Do not bypass account challenges, sending limits or host restrictions. Report held drafts and ambiguous outcomes precisely.

## Completion

Verify findings against source evidence and read back every resulting artifact or authorized change. Distinguish a saved draft, queued job, active workflow and completed delivery. Return the requested outcome, evidence, output location and precise outstanding dependencies. Complete independent work when one dependency is unavailable. Package validation and synthetic fixtures do not establish real host import or provider execution.

Read [evaluation scenarios](references/evaluation.md) when testing this skill.