Skip to content
SkillModel-led895 tokens in use

li-plan

Plans your LinkedIn week: which posts to write, when to publish them and which ten people to engage with, drawn from what happened to you.

3,760 stars on the repository MIT LicenseJakeschincariol/linkedin-agent-skill · skills/li-plan
/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-plan costs

62tokens idle
895tokens 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
  • Structure17/25
  • 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-plan is the weekly planning skill of the LinkedIn pack. It reads your voice profile and post log, asks what you sell, your themes, what happened this week and who you want to be visible to, and builds a schedule of about four posts.

Each slot gets a post type, a specific angle from your week and a hook formula number. It adds posting times and a list of ten people to engage with, split into reach, peers and buyers, and saves the plan to a file the other skills read.

What You Get

  • A week schedule of about four posts with type, angle and hook formula for each slot
  • Posting times anchored to your audience’s timezone, with the working default of Tuesday to Thursday mornings
  • A list of ten people to engage with: five for reach, three peers and two buyers
  • A plan file at ~/.claude/linkedin/plan.md that the other skills in the pack can read

Common Use Cases

  • Planning next week on the same day every week
  • Turning a client call or a mistake from this week into post angles
  • Building a list of people to comment on before you post
  • Using your audit results to change next week’s mix

What Makes It Unique

It plans angles and leaves topics behind: a specific lost proposal is a plan item, while the word AI is not. It recommends four posts over seven, avoids repeating a theme from the last fortnight by reading your log, and says that the first line matters more than the posting hour. It sits above the other skills as the place that decides what they execute.

Under The Hood

The skill is instructions only, with no scripts. It reads voice.md and log.md from your home folder under .claude/linkedin when they exist, asks you questions when they do not, and writes plan.md in the same folder, so it reads and writes local files. It does not fetch web pages, call APIs, schedule or publish anything on LinkedIn.

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