Skip to content
SkillModel-led3,313 tokens in use

linkedin-reply-handler

Draft a reply to one LinkedIn comment, or sweep a whole thread from the post URL and draft a reply to every comment worth answering in one batch.

6,078 stars on the repository MIT Licensesergebulaev/linkedin-skills · skills/linkedin-reply-handler
npx skills add sergebulaev/linkedin-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing linkedin-reply-handler costs

107tokens idle
3,313tokens in use
5,628tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter11/15
  • Structure25/25
  • Examples12/15
  • Output10/15
  • Size10/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity96
  • Maintenance100
  • Community64
  • Maturity28
  • Momentum40

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.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers