Li plan skill

Build the week on LinkedIn - what to post, when to post it, and who to engage with.

by Jakeschincariol·MIT license·★ 1,856 Stars on the repo·GitHub ↗

Use now

Inside this skill

SKILL.md · the author's own words
# 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
   thing they built, an argument they had. This is where posts come from.
4. Ten to twenty people or companies worth being visible to.

Word-for-word excerpt, not a result. Read the full SKILL.md ↓

Files of Li plan

Jakeschincariol/main1 file shown
SKILL.md
Show the full text95 lines
li-plan/SKILL.md95 lines · 3.5 KB

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 thing they built, an argument they had. This is where posts come from.
  4. Ten to twenty people or companies worth being visible to.

What to post

Four posts a week beats seven. Consistency is a floor, not a target, and the fifth post of a week is almost always the weak one that drags the average.

Mix across the week, never two of the same type back to back:

type share job
Proof 1 per week something that happened, with a number
Opinion 1 per week a position that could lose you followers
Teach 1 per week one thing the reader can do today
Story 1 per fortnight a scene with dialogue and a cost
Offer 1 per fortnight what you sell, said plainly, no apology

For each slot give: the theme, the specific angle drawn from what actually happened this week, and the hook formula number from li-post/hooks.json that fits it. Not a topic - an angle. "AI" is not a plan. "The proposal we lost because our AI draft had an em dash in it" is a post.

When to post

Post when the user's audience is at a desk. For a B2B audience in one timezone, Tuesday to Thursday, 7:30-9:30am local, is the working default, with Monday afternoon and Friday morning as the second tier. Weekends are for personal-story posts or nothing.

But state this plainly: the day and hour matter far less than whether the first line is good. If the user is optimising posting times before their hooks work, they are polishing the wrong thing, and you should say so.

Anchor the times to their audience's timezone, not the user's, if those differ.

Who to engage with

Build a list of 10, split three ways:

  • 5 reach - people with an audience the user wants, whose posts they can genuinely add to. Comment before they have 20 comments or nobody sees it.
  • 3 peers - same level, same field. This is the group that reciprocates.
  • 2 buyers - people who could actually buy. Comment on their posts for weeks before any DM, and never pitch in a comment.

20 minutes a day, before posting, not after. Comments on other people's posts are what makes the user's own post land.

Output

WEEK OF SEP 8

MON  engage only  (20 min, list below)
TUE  8:15am  PROOF    #17 Time Anchor   - the 5hr -> 20min proposal rebuild
WED  engage only
THU  8:00am  OPINION  #1  Contrarian    - why we killed the discovery call
FRI  8:30am  TEACH    #21 Direct Value  - the 4-line reopen email, given away
SAT  -
SUN  4:00pm  STORY    #9  Cold Open     - the "going with someone cheaper" email

ENGAGE  (5 reach / 3 peers / 2 buyers)
  ...

Say "write Tuesday" and I will draft it.

Write the plan to ~/.claude/linkedin/plan.md so the other skills can read it. Nothing is scheduled or posted anywhere - this is a plan, and the user runs it.

1---
2name: li-plan
3description: >-
4 Build the week on LinkedIn - what to post, when to post it, and who to engage
5 with. Use when the user says "plan my week", "what should I post", "content
6 calendar", "I have nothing to post about", or wants a posting schedule and an
7 engagement list.
8---
9 
10# li-plan
11 
12The control room. Everything else in this pack executes; this decides what
13gets executed. Run it once a week, on the same day.
14 
15## Input
16 
17If `~/.claude/linkedin/voice.md` and `log.md` exist, read them - the plan
18should not repeat a theme from the last fortnight. If they do not exist, ask
19for four things and write them down:
20 
211. What the user sells, and to whom.
222. The three or four themes they want to be known for.
233. What actually happened this week - a client call, a number, a mistake, a
24 thing they built, an argument they had. This is where posts come from.
254. Ten to twenty people or companies worth being visible to.
26 
27## What to post
28 
29Four posts a week beats seven. Consistency is a floor, not a target, and the
30fifth post of a week is almost always the weak one that drags the average.
31 
32Mix across the week, never two of the same type back to back:
33 
34| type | share | job |
35| --- | --- | --- |
36| **Proof** | 1 per week | something that happened, with a number |
37| **Opinion** | 1 per week | a position that could lose you followers |
38| **Teach** | 1 per week | one thing the reader can do today |
39| **Story** | 1 per fortnight | a scene with dialogue and a cost |
40| **Offer** | 1 per fortnight | what you sell, said plainly, no apology |
41 
42For each slot give: the theme, the specific angle drawn from what actually
43happened this week, and the hook formula number from `li-post/hooks.json` that
44fits it. Not a topic - an angle. "AI" is not a plan. "The proposal we lost
45because our AI draft had an em dash in it" is a post.
46 
47## When to post
48 
49Post when the user's audience is at a desk. For a B2B audience in one
50timezone, Tuesday to Thursday, 7:30-9:30am local, is the working default, with
51Monday afternoon and Friday morning as the second tier. Weekends are for
52personal-story posts or nothing.
53 
54But state this plainly: **the day and hour matter far less than whether the
55first line is good.** If the user is optimising posting times before their
56hooks work, they are polishing the wrong thing, and you should say so.
57 
58Anchor the times to their audience's timezone, not the user's, if those
59differ.
60 
61## Who to engage with
62 
63Build a list of 10, split three ways:
64 
65- **5 reach** - people with an audience the user wants, whose posts they can
66 genuinely add to. Comment before they have 20 comments or nobody sees it.
67- **3 peers** - same level, same field. This is the group that reciprocates.
68- **2 buyers** - people who could actually buy. Comment on their posts for
69 weeks before any DM, and never pitch in a comment.
70 
7120 minutes a day, before posting, not after. Comments on other people's posts
72are what makes the user's own post land.
73 
74## Output
75 
76```
77WEEK OF SEP 8
78 
79MON engage only (20 min, list below)
80TUE 8:15am PROOF #17 Time Anchor - the 5hr -> 20min proposal rebuild
81WED engage only
82THU 8:00am OPINION #1 Contrarian - why we killed the discovery call
83FRI 8:30am TEACH #21 Direct Value - the 4-line reopen email, given away
84SAT -
85SUN 4:00pm STORY #9 Cold Open - the "going with someone cheaper" email
86 
87ENGAGE (5 reach / 3 peers / 2 buyers)
88 ...
89 
90Say "write Tuesday" and I will draft it.
91```
92 
93Write the plan to `~/.claude/linkedin/plan.md` so the other skills can read it.
94Nothing is scheduled or posted anywhere - this is a plan, and the user runs it.
95 

Discussion