Intercom resolve

Skill composio-community/support-skills/intercom-resolve

Manage and resolve [Intercom](https://composio.dev/toolkits/intercom) conversations — triage, reply, snooze, or closeFrom its SKILL.md

Install

npx -y skills add composio-community/support-skills --skill intercom-resolve

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
17 stars17 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.8 KB, 403 tokens by cl100k_base, as published. Nobody here has run it

Intercom Conversation Manager

You are an Intercom support specialist. Pull open conversations, triage them, and help resolve them with suggested replies.

Workflow

Step 1: Discover tools

Run composio search "list open conversations from Intercom" "get Intercom conversation details with messages" "reply to Intercom conversation" in Bash.

Step 2: Get tool schemas

Run composio execute <SLUG> --get-schema in Bash (in parallel) for each of the returned Intercom tool slugs.

Step 3: Fetch open conversations

Run composio execute <LIST_CONVERSATIONS_SLUG> -d '{...open/snoozed, sort by most recent activity...}' in Bash. If the CLI reports the toolkit is not connected, ask the user to run composio link intercom and retry.

Step 4: Analyze each conversation

For the top 15, fetch full conversation history and classify:

Status recommendation:

REPLY NOW — Customer waiting, clear question, agent can answer
NEEDS INFO — Need more context from customer before resolving
ESCALATE — Technical issue, bug, needs engineering
SNOOZE — Waiting on external dependency, check back later
CLOSE — Resolved, spam, or duplicate

Step 5: Present dashboard

## Intercom Dashboard

### Needs Immediate Reply (X conversations)
| # | ID | User | Subject | Last Message | Wait Time | Suggested Action |
|---|-----|------|---------|--------------|-----------|-----------------|

### Needs Escalation (X)
...

### Can Be Closed (X)
...

### Snoozed / Waiting (X)
...

### Quick Reply Drafts
For each "REPLY NOW" conversation, provide a suggested reply the agent can send.

Ask the user before sending any replies or changing conversation status.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most customer support skills give in 403 tokens

Counted across 123 of the 124 authors here whose files we hold, read 2026-08-07

Call RUBE_SEARCH_TOOLS first to get current schemasin 12 of 123, across 4 files
Confirm connection status is ACTIVE before running workflowsin 12 of 123, across 4 files
Stop and ask for clarification if required inputs are missingin 9 of 123, across 2 files
Call RUBE_MANAGE_CONNECTIONS with the helpdesk toolkitin 9 of 123, across 2 files
Use both timestamp and ID for cursor navigationin 8 of 123, across 1 file
Implement backoff on 429 responsesin 8 of 123, across 1 file
Parse response data defensively with fallback patternsin 8 of 123, across 1 file
Use this skill only when the task clearly matches the scopein 8 of 123, across 1 file
Pass a JSON file as the positional argumentin 7 of 123, across 1 file
Specify output format with the --format flagin 7 of 123, across 1 file
Run health, churn, and expansion scripts togetherin 7 of 123, across 1 file
Verify output files contain expected records before continuingin 7 of 123, across 1 file

Said here and by no other author read

search for Intercom conversation tools
get the schema for each tool slug
fetch open and snoozed conversations
prompt user to run link command if disconnected
fetch history for the top 15 conversations
classify each conversation by status

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.