Skip to content
SkillModel-led672 tokens in use

li-dm

Writes the 200-character LinkedIn invite note, the first message after they accept and two follow-ups, each tied to a specific reason to reach out.

3,760 stars on the repository MIT LicenseJakeschincariol/linkedin-agent-skill · skills/li-dm
/plugin marketplace add Jakeschincariol/linkedin-agent-skill /plugin install linkedin-agent
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing li-dm costs

69tokens idle
672tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. 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
  • Frontmatter12/15
  • Structure19/25
  • Examples9/15
  • Output10/15
  • Size15/15
  • Resources10/15

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 →
Needs attention
  • Development activity28
  • Maintenance4
  • Community52
  • Maturity16
  • Momentum40

li-dm writes outreach for one specific person on LinkedIn. It first asks who they are, the real reason to write today and what you want, and says so if there is no reason to message them.

It then drafts the invite note under 200 characters with the count shown, a two to four sentence first message that gives something before it asks, a follow-up four days later and a close-the-loop message ten days later. Then it stops, and you send each message by hand.

What You Get

  • An invite note under 200 characters with the character count shown
  • A first message of two to four sentences that references the invite and gives something before asking
  • A follow-up for day four that adds something new, and a close-the-loop message for day ten
  • A set of limits: you send every message by hand, never claim a mutual connection that does not exist and stay at 20 invites a day or fewer

Common Use Cases

  • Reaching out to a prospect whose post you want to respond to
  • Asking someone in your field for a short call
  • Following up without a bump message that adds nothing
  • Checking whether you have a real reason to message someone at all

What Makes It Unique

It begins with a gate: no specific reason today means no message. The invite note asks for nothing, the first message gives before it asks and has no calendar link, and the sequence ends after two follow-ups. It also states the safety limits that protect your account.

Under The Hood

The skill is instructions only, with no scripts. It asks you for the person’s name, role, company and your reason for reaching out, then writes the messages in the chat and runs them through the humanizer skill. It does not log in to LinkedIn, fetch web pages, call APIs, send messages or write files.

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