Jakeschincariol/linkedin-agent-skill

# li-audit

The only honest source of what works for an account is that account. Every
rule in every LinkedIn guide, including the ones in this pack, is a prior. The
user's own last 30 posts are the evidence.

## Input

Ask for whichever the user has:

- The post analytics export (LinkedIn: Analytics -> Content -> Export). CSV.
- Or a screenshot per post with impressions, reactions, comments, reposts.
- Or just the posts and their reaction counts, which is enough for a first
  pass.

# li-carousel

Document posts are the highest-dwell format on LinkedIn, because a swipe is
counted and a scroll is not. The format rewards one idea broken into steps.
It punishes a text post cut into pieces.

## When to use it instead of a text post

Use a carousel when the idea has **sequence** - steps, a countdown, a
before/after progression, a framework with parts. Use a text post when the
idea is one claim. Splitting one claim across eight slides is the most common
way carousels fail, and if that is what the user has, say so and hand them to
`/li-post`.

# li-comment

Commenting is the highest-leverage thing on LinkedIn and the easiest to do
badly. A comment on a post with 400 reactions gets seen by more people than
most of your own posts. A generic one gets seen by nobody and costs you
credibility with the author.

## Input

The user pastes the post text (and the author's name and role if they have
it). If they paste a screenshot, read it. If they give you a URL you cannot
open, ask them to paste the text - do not guess what the post said, and do not
use browser automation to scrape the feed.

# li-dm

The invite note is 200 characters. The first DM decides whether there is a
second one. Neither is a pitch.

## Before writing, get the specifics

Ask for, in one batched question:

1. **Who** - name, role, company.
2. **The hook** - the actual reason to reach out now. A post they wrote, a
   thing their company shipped, a mutual connection, a talk they gave. Not
   "they fit my ICP".
3. **What the user wants** - a conversation, a referral, a job, a sale. Be

# li-human

Two tools live in this folder and they both actually run. Use them. Do not
eyeball this.

```bash
python3 humanize.py draft.txt --report        # clean it, show what changed
python3 detect.py draft.txt                    # score it, five checks
python3 detect.py before.txt after.txt         # prove the delta
```

Both read `slop.json`, which is the lexicon: 100+ stock words and phrases with
plain-English replacements, 17 invisible character classes, 11 typographic
substitutions, and 11 structural tells. It is meant to be edited. If the user

# li-inbox

Most LinkedIn inboxes are 80% noise, and the cost of that noise is that the
20% goes unanswered for a week. This skill separates them, then writes only
what is worth writing.

## Input

The user pastes the messages. Screenshots are fine. Do not log into their
account or read their inbox with a browser tool.

## Sort into five

| bucket | signal | action |

# li-plan

The control room. Everything else in this pack executes; this decides what
gets executed. Run it once a week, on the same day.

## Input

If `~/.claude/linkedin/voice.md` and `log.md` exist, read them - the plan
should not repeat a theme from the last fortnight. If they do not exist, ask
for four things and write them down:

1. What the user sells, and to whom.
2. The three or four themes they want to be known for.
3. What actually happened this week - a client call, a number, a mistake, a

# li-post

Turns one raw idea into a LinkedIn post that sounds like the person who
posted it.

## Before you write

1. Read `~/.claude/linkedin/voice.md` if it exists. That file is the user's
   voice profile: how they talk, what they never say, who they are talking to.
   If it does not exist, ask for **three of their own past posts**, infer the
   voice from those, and write the file. Do not skip this and do not invent a
   voice. A post in the wrong voice is worse than no post.
2. Read `hooks.json` in this folder. All 21 formulas, with templates, filled
   examples, what each is for, and how each one usually gets ruined.

# li-profile

A profile is not a resume. A resume answers "what have you done". A profile
answers "should I message this person", and it answers it in about four
seconds, from the headline and the first two lines of the about.

## Input

Ask the user to paste: headline, about section, current role and the last two
experience entries, plus whether they have a banner and featured section. A
screenshot of the top card is enough for the first pass. Do not log into
LinkedIn on their behalf.

## Score it

# li-reply

The reply thread under your own post is where reach is actually decided. Every
reply is a second engagement event on the post, and the first hour of replies
does most of the work. But the value is not equal across comments, so this
skill sorts before it writes.

## Input

The user pastes the comments, ideally with names and roles. Screenshots are
fine. Do not scrape the thread with a browser tool.

## Triage first

# li-repurpose

One good long asset contains four to six posts. Most people extract one and
throw the rest away.

## Input

A transcript, an article, a newsletter, a script, a call summary. If the user
gives a YouTube URL and there is a transcript tool available in the session,
use it; otherwise ask them to paste the text. Read the whole thing before
extracting anything.

## Extract, do not summarise