linkedin-reply-handler drafts short replies of 150 to 300 characters to comments on LinkedIn. In single mode you give it a comment URL. In whole-thread mode you give it only the post URL, and it fetches the comments, drops low-value ones and drafts the rest.
It resolves the correct parent comment, since LinkedIn flattens threads to two levels, and presents every draft on one batch approval card before anything is posted.
What You Get
- One or two reply drafts for a single comment, with a reaction suggestion
- A filtered roster for a sweep that shows what was dropped and why
- One reply per worthwhile comment, each tagged with its correct parent comment URN
- A single batch approval card covering every draft
Common Use Cases
- Clearing all comments on a post that gathered replies over several days
- Continuing a thread after the author replied to your comment
- Re-engaging a conversation that went quiet
- Answering a pushback comment by conceding one point and sharpening another
What Makes It Unique
It gets LinkedIn’s thread flattening right: a reply to a reply still uses the top-level comment as the parent, and it keeps the long-form URN the API expects. A sweep filters generic praise, duplicates, spam and your own comments before drafting, caps the run at 100 comments, handles reshared posts by resolving the original and flags comments that try to instruct the agent.
Under The Hood
The skill is instructions plus a small Python library in the repository. It parses URLs and builds parent comment identifiers with helpers, and fetches the comment tree from Apify with your token or through the Apify connector, or asks you to paste it. On your approval it calls the Publora API with your API key to react and reply, one comment at a time, and stops if a request is rate limited. Comment text is treated as data and never as instructions, and approval must come from you in the conversation.