linkedin-warm-tracker
Skill9 starsChanged 4 months agoMITView on GitHub
Maintain a one-row-per-person state machine that outputs each person's single next action and due date, sorted by what is due today. Use to run the day's warming and outreach follow-ups so nobody slips through.
In this repository28 other files it gives its agents.
- linkedin-booking-closerSkill
- linkedin-carousel-writerSkill
- linkedin-cold-reviverSkill
- linkedin-comment-engineSkill
- linkedin-comment-warmerSkill
- linkedin-connection-noteSkill
- linkedin-content-calendarSkill
- linkedin-engage-planSkill
- linkedin-engager-analyticsSkill
- linkedin-first-dmSkill
- linkedin-followup-adapterSkill
- linkedin-hook-labSkill
- linkedin-humanizerSkill
- linkedin-icp-definerSkill
- linkedin-objection-handlerSkill
- linkedin-onboardSkill
- linkedin-outreachSkill
- linkedin-post-autopsySkill
- linkedin-post-writerSkill
- linkedin-profile-auditorSkill
- linkedin-reply-triagerSkill
- linkedin-repurposerSkill
- linkedin-sell-by-chatSkill
- linkedin-signal-stackSkill
- linkedin-story-minerSkill
- linkedin-strategistSkill
- linkedin-voice-profilerSkill
- linkedin-warm-list-builderSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
Read their stage: new / warming / connect-sent / accepted / in-conversation / qualifying / booked / cold.
- Distinctive: line 18
Read their last touch date and last reply state (replied, no reply yet, went quiet).
- Distinctive: line 29
When the action is to send, sending happens only through the connected CLI/MCP layer on the user's own session or provider key, drafts are …
- Distinctive: line 30
No em-dashes. No guaranteed-result promises.
≈ “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
LinkedIn Warm Tracker
The day-driver for warming and outreach. One row per person, one next action each, nothing leaks.
Inputs
- The current list of people in play with their last touch and last reply state (paste the list or give a path): $ARGUMENTS
- The brief (persona, offer, pains) loads automatically.
Do this
For each person:
- Read their stage: new / warming / connect-sent / accepted / in-conversation / qualifying / booked / cold.
- Read their last touch date and last reply state (replied, no reply yet, went quiet).
- Compute the single NEXT ACTION for that stage. Examples: warming = engage on a recent post; connect-sent (no accept, 4+ days) = withdraw or wait; accepted = send first DM; in-conversation = reply with the next angle; qualifying = book the call; went quiet (7+ days) = one soft re-open then mark cold.
- Compute the DUE date from the last touch plus the stage cadence. Anything overdue is due today.
- Sort the table by due date, soonest first, and within today put the warmest stage (qualifying, in-conversation) at the top.
Output
A table with columns: person, stage, last touch, NEXT ACTION, due. Sorted by due date. Below it, a one-line count of how many rows are due today. End with the single warmest row to action first.
Rules
- One row per person. Every person always gets a next action, even if that action is "mark cold". Nothing leaks.
- This drives the day. It does not send anything. Drafting a message is /linkedin-first-dm; running /linkedin-humanizer on the draft; hot replies go to /linkedin-reply-triager.
- When the action is to send, sending happens only through the connected CLI/MCP layer on the user's own session or provider key, drafts are shown and approved first, and the 20 actions/day cap applies to new accounts.
- No em-dashes. No guaranteed-result promises.
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.