agentleFS
Sign inStart free
HemanthMChakravarthyHemanthMChakravarthy/linkedin-agent-skills/skills/li-plan/SKILL.md

li-plan

Skill2 starsChanged 43 days agoMITView on GitHub

Plan the user's LinkedIn week: what to post, when to post it, and the ten people to engage with. Use when the user asks for a content plan, "plan my week", "what should I post", or wants a posting calendar. Writes a plan file; every post is still drafted by li-post and approved before publishing.

8 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask three questions in one batch, or infer from history if this is a repeat run:

    line 19
  2. Distinctive:

    If a previous plan exists, read it first and note what actually got posted vs.

    line 24
  3. Very specific:

    Write to ~/.agents/linkedin/plan.md (fall back to ~/.claude/linkedin/ or ~/.copilot/linkedin/ if that is where the user's files already …

    line 29
  4. Distinctive:

    Content pillars: Every post serves exactly one of 3-4 pillars you define with the user (e.g.

    line 42
  5. Distinctive:

    Not a commitment device. If the user posts 1 of 3, the next plan says 2, not 3 with guilt.

    line 65
  6. Distinctive:

    Not automation. Nothing here posts, schedules, or sends.

    line 67
  7. Distinctive:

    Not forever. Re-plan weekly.

    line 68

“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

li-plan

The week, on one page: what to post, when, and who to engage with. Planning is separated from writing on purpose: this skill decides the calendar, li-post writes the posts, the user approves everything.

Before you plan

  1. Load the voice profile (li-voice if missing).
  2. Ask three questions in one batch, or infer from history if this is a repeat run:
    • How many posts this week? (Default: 3. More than 5 needs a reason.)
    • Any dated events? (Launch, talk, milestone with a real date.)
    • Who are you trying to reach right now? (One audience, not three.)
  3. If a previous plan exists, read it first and note what actually got posted vs. planned. The plan adapts to reality.

The plan

Write to ~/.agents/linkedin/plan.md (fall back to ~/.claude/linkedin/ or ~/.copilot/linkedin/ if that is where the user's files already live). One week per file, dated.

Posting slots. 2-4 slots, each with:

  • Day and time (weekday mornings in the user's timezone outperform; never schedule more than one post per day).
  • The idea in one sentence, and which content pillar it serves.
  • The hook family to try first (from li-post's hooks.json).
  • Format: text post, carousel (li-carousel), or repurposed asset (li-repurpose).

Content pillars. Every post serves exactly one of 3-4 pillars you define with the user (e.g. "field notes", "frameworks", "contrarian takes", "proof"). If a pillar has not produced a post in two weeks, say so.

The ten. Ten specific people to engage with this week: 5 in the target audience, 3 peers, 2 aspirational follows. For each: name, why them, and one concrete action (comment on their latest post via li-comment, reply to a thread, share with a note). Never generic "engage more".

The cadence rule. Commenting (via li-comment) on 3-5 posts daily beats one extra weekly post. The plan says this explicitly every week until the user internalizes it.

The loop

  1. Draft the plan file and show it.
  2. On approval, save it. On "change X", change X and re-show only the changed part.
  3. Each post, when its slot comes, is drafted fresh by li-post. The plan never contains finished post copy; plans go stale, slots do not.

What the plan is not

  • Not a commitment device. If the user posts 1 of 3, the next plan says 2, not 3 with guilt.
  • Not automation. Nothing here posts, schedules, or sends. The user does.
  • Not forever. Re-plan weekly. A plan older than 10 days is a wish.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free