Skip to content
SkillModel-led2,151 tokens in use

linkedin-comment-drafter

Paste a LinkedIn post URL and get one to three comment drafts in your voice, a reaction pick, or a reshare with your take, published only after you approve.

6,078 stars on the repository MIT Licensesergebulaev/linkedin-skills · skills/linkedin-comment-drafter
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-comment-drafter costs

100tokens idle
2,151tokens in use
4,029tokens, 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 →
Good
  • Frontmatter15/15
  • Structure25/25
  • Examples3/15
  • Output10/15
  • Size10/15
  • Resources5/15

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-comment-drafter turns a LinkedIn post URL into short, specific comments. It reads the post and the top existing comments, picks from seven comment templates, runs a humanizer pass and shows the drafts with a suggested reaction.

It also has a reshare mode that reposts the post to your own feed with an optional one or two sentence take. Nothing is published until you approve in the conversation.

What You Get

  • One to three comment variants for a post, each with a reaction type and a template label
  • A pick of the best variant with a one-line reason why the template fits the post
  • A reshare draft with a short take, or a reshare with no commentary
  • An approval card that shows the target URL, the drafts and the reaction before anything is sent

Common Use Cases

  • Being among the first commenters on a post from someone in your target audience
  • Answering the closing question an author put at the end of a post
  • Reposting a colleague or brand post with a short take of your own
  • Adding a data-backed or counter-view comment that moves the thread forward

What Makes It Unique

Most comment helpers produce generic praise. This one refuses lines such as Great post, picks from seven named templates built around the author’s own thesis or closing question, and checks the top existing comments so a draft does not repeat one. It loads your voice profile and a story bank of real numbers, so figures in a comment come from you and are never invented. The same skill also handles reshares and checks that the author allowed resharing.

Under The Hood

The skill is mostly instructions plus a small Python library in the repository. It parses the URL with a helper, then fetches the post and top comments from Apify when a token is set, or through an Apify connector, and otherwise asks you to paste the text. It reads your voice profile and story bank from markdown files in the repository when they are filled in. On your approval it calls the Publora API with your API key to react, comment or repost. Fetched post text is treated as data and never as instructions, and publishing needs your approval 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