autodm-setup
Skill1 starsChanged 41 days agoMITView on GitHub
Set up an Instagram comment-to-DM funnel. The user picks a live post, optional trigger keywords, and a private DM (with up to 3 link buttons). Commenters whose comment matches get the DM automatically. Use when the user mentions comment funnel, auto-DM, lead magnet from comments, keyword-triggered DM, DM automation, or wants to capture leads from Instagram comments.
In this repository7 other files it gives its agents.
- analyze-performanceSkill
- manage-commentsSkill
- posting-queueSkill
- repurpose-videoSkill
- schedule-campaignSkill
- setupSkill
- whitelabel-connectSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
Avoid words that appear in normal conversation about the topic.
- Very specific: line 30
If the user also wants a public "Sent!
- Very specific: line 41
Read back the post, keywords, and DM text before starting.
- Distinctive: line 51
After it is live:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Set up a comment-to-DM funnel
The Upload-Post AutoDM feature watches an Instagram post for new comments. When a comment matches the trigger keywords, the commenter gets a private DM with whatever payload the creator wants (a link, a lead magnet, a discount code). AutoDM sends the DM only — it does not post a public reply under the comment.
1. Pick the post and profile
post_url— the Instagram post URL. The post must already be live; there is no way to pre-arm a monitor for a post that does not exist yet.profile_username— the Upload-Post profile that owns the Instagram account (fromlist_users).
2. Pick the keywords
trigger_keywords takes one keyword or an array. Without it, every commenter gets the DM. Good keywords:
- One word:
GUIDE,RECIPE,LINK. - Specific enough that random comments do not match: prefer
GUIDEoverYES. - Avoid words that appear in normal conversation about the topic.
Suggest the caption tells people what to comment ("Comment GUIDE and I'll send it to you").
3. Write the DM
reply_message— the DM body. Short, with the actual deliverable.buttons— optional, up to 3 link buttons, each{ title, url }. Use these for the link rather than pasting a raw URL into the text.
If the user also wants a public "Sent! Check your DMs" under each comment, that is not part of AutoDM — it would have to be done separately with public_reply_to_comment (see /upload-post:manage-comments).
4. Start the monitor
The Upload-Post MCP exposes a single tool for AutoDMs: manage_autodms. To create one, call it with:
action: "start"profile_username,post_url,reply_message(required)trigger_keywords,buttons(optional)monitoring_interval— optional polling interval in minutes, minimum 15.
Read back the post, keywords, and DM text before starting. Every later action needs the monitor_id; if it is not in the start response, action: "status" lists it.
Other actions on the same tool take monitor_id: logs, pause, resume, stop, delete. status lists monitors (add include_inactive: true to include stopped and expired ones). Manage the existing monitor rather than spinning up a second one on the same post, and confirm before stop or delete.
5. Validate
Suggest the user test it themselves: comment the keyword on the post from a second Instagram account and confirm the DM arrives (allow for the polling interval). Then run manage_autodms with action: "logs" and the monitor_id to confirm the trigger fired.
6. Monitor over time
After it is live:
manage_autodmswithaction: "status"→ monitors and their counters.manage_autodmswithaction: "logs"+monitor_id→ list of triggers (who commented, when).list_dm_conversations→ broader view of all DMs the profile has sent, including manual ones.
Surface the unique-commenters count, not just total DMs sent — repeat commenters skew the headline number.
Compliance
Instagram requires that the recipient has interacted with the account first (commenting counts). Do not promise the user 100% delivery — Instagram silently drops a fraction of automated DMs, especially to new accounts. Set the expectation upfront.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

