li-engage
Skill1 starsChanged 5 days agoMITView on GitHub
Keep the user's LinkedIn engagement round honest - log who they commented on, catch drift onto the same three people, track the reach / peer / buyer mix from the weekly plan, and surface the people on their list they have gone quiet on. Use when the user says "who should I engage with today", "who have I been commenting on", "log this comment", "am I neglecting anyone", or runs their daily engagement round.
In this repository16 other files it gives its agents.
- li-auditSkill
- li-carouselSkill
- li-commentSkill
- li-dmSkill
- li-humanSkill
- li-inboxSkill
- li-jobsearchSkill
- li-newsletterSkill
- li-planSkill
- li-postSkill
- li-preflightSkill
- li-profileSkill
- li-publishSkill
- li-replySkill
- li-repurposeSkill
- li-voiceSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 32
Write the ten from /li-plan into ~/.claude/linkedin/roster.txt, one per line, name,tier:
- Very specific: line 47
After the user posts a comment by hand, log it with targets.py add.
- Distinctive: line 65
Never comment, react or connect on the user's behalf, and never use a browser tool to do it.
- Distinctive: line 68
Never log an interaction the user did not make.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
li-engage
/li-plan builds a list of ten people: 5 reach, 3 peers, 2 buyers. Two weeks
later the user is commenting on the same three people every morning and the
buyers have not heard from them since day four. Neither problem is visible
from inside the feed. This keeps the record that makes both visible.
One tool lives in this folder and it runs:
python3 targets.py add "Sarah Chen" --tier reach --note "added the churn number"
python3 targets.py report # the last 7 days
python3 targets.py due --roster roster.txt # who on the list has gone quietThe ledger is a CSV at ~/.claude/linkedin/engage.csv. It never opens
LinkedIn and never posts.
The roster
Write the ten from /li-plan into ~/.claude/linkedin/roster.txt, one per
line, name,tier:
Sarah Chen,reach
Marcus Webb,peer
Dana Ruiz,buyerThe daily round
targets.py due --roster ~/.claude/linkedin/roster.txt. Start at the top: the most overdue first.- The user pastes those people's latest posts. Draft each comment with
/li-comment. - After the user posts a comment by hand, log it with
targets.py add. One line, ten seconds.
The weekly read
targets.py report --days 7 prints the count per person, the share the top
three took, and the tier mix against the 50 / 30 / 20 target. It warns when:
- three people took over half of the round. It is visible, to them and to everyone reading the comments.
- a tier fell below half its target. Usually buyers, because commenting on buyers feels like selling. It is not, if the comment is good.
Hand the report to /li-plan so next week's list replaces the people who
never engage back.
Never
- Never comment, react or connect on the user's behalf, and never use a browser tool to do it. Automated engagement violates LinkedIn's User Agreement and gets accounts restricted.
- Never log an interaction the user did not make.
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
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.

