linkedin-signal-stack
Skill9 starsChanged 4 months agoMITView on GitHub
Pull five-plus real, checkable signals on one target and stack them into a 3-line signal brief a message can be built on. Use before writing any outreach so the message reads like 30 minutes of homework.
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-story-minerSkill
- linkedin-strategistSkill
- linkedin-voice-profilerSkill
- linkedin-warm-list-builderSkill
- linkedin-warm-trackerSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 22
Verify each one. If a signal cannot be checked against a real, dated source, leave it out.
- Distinctive: line 30
Only real, checkable signals.
- Distinctive: line 33
No em-dashes. No filler. Operator-grade signals only.
≈ “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 Signal Stack
The lift in outreach is not the message, it is the signal stack underneath it. This skill does the homework: five-plus real signals per target, distilled to the one sharpest thing to open on.
Inputs
- A target (profile and/or company) to research: $ARGUMENTS
- The brief (ICP, voice, offer, pains) loads automatically, so the signals are filtered for what matters to this operator.
Do this
- Gather signals that matter on this one target. Aim for five or more from across:
- Recent funding, raise, or revenue milestone.
- An exec move or a new hire (especially in growth, sales, or rev ops).
- A phrase or priority lifted straight from a current job description they have open.
- Their last post (the hook, the claim, the question they raised).
- Any company news from the last 14 days (launch, press, partnership, hiring spike).
- Verify each one. If a signal cannot be checked against a real, dated source, leave it out. No guessing, no inference dressed as fact.
- Stack them into a 3-line signal brief: what is going on, why it is happening now, and the angle it opens.
- Pick the single sharpest signal: the one a peer would notice and the target would feel seen by.
Output
A signal brief per target, labelled clearly: the five-plus verified signals (each with its source), then the 3-line brief, then "Open on:" with the single sharpest signal. Hand this to a message-writing skill like /linkedin-first-dm or /linkedin-connection-note.
Rules
- Only real, checkable signals. Every one carries its source. If it cannot be verified, it does not go in.
- Drafts research only. Pulling signals live (profiles, posts, company pages) needs the connected CLI/MCP layer wired to the operator's own session or a provider key; nothing is scraped by default.
- The operator approves what gets used. This skill never sends.
- No em-dashes. No filler. Operator-grade signals only.
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.

