linkedin-cta-lab
Skill0 starsChanged 39 days agoMITView on GitHub
Write three closing lines for an existing draft and score them. Use when the post is done and the ask is weak. Does not rewrite the whole post.
In this repository44 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- docs/llms.txtllms.txt
- llms.txtllms.txt
- linkedin-marketingSkill
- agent-instagram-deskSkill
- agent-whatsapp-deskSkill
- agent-x-deskSkill
- agent-youtube-deskSkill
- linkedin-analytics-reviewSkill
- linkedin-approval-gateSkill
- linkedin-carousel-writerSkill
- linkedin-case-receiptSkill
- linkedin-comment-drafterSkill
- linkedin-connection-noteSkill
- linkedin-content-plannerSkill
- linkedin-correctionSkill
- linkedin-employee-advocacySkill
- linkedin-engager-analyticsSkill
- linkedin-event-noteSkill
- linkedin-experience-bulletSkill
- linkedin-feature-pickerSkill
- linkedin-first-commentSkill
- linkedin-headline-labSkill
- linkedin-hook-extractorSkill
- linkedin-hook-labSkill
- linkedin-humanizerSkill
- linkedin-interviewerSkill
- linkedin-ist-windowSkill
- linkedin-job-answersSkill
- linkedin-job-fitSkill
- linkedin-job-intakeSkill
- linkedin-job-logSkill
- linkedin-job-noteSkill
- linkedin-newsletterSkill
- linkedin-poll-writerSkill
- linkedin-post-writerSkill
- linkedin-profile-optimizerSkill
- linkedin-quote-commentSkill
- linkedin-reply-handlerSkill
- linkedin-repurposerSkill
- linkedin-series-builderSkill
- linkedin-silence-auditSkill
- linkedin-thread-monitorSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Read the draft. State the single job: comment, save, or profile visit.
- Distinctive: line 16
Write three closes under 25 words.
- Very specific: line 18
Do not publish. Hand the chosen line back to the user to paste into the draft, then linkedin-humanizer if they want a full audit.
≈ “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
CTA lab
The close is one job. Not a menu.
When to use
- "The draft is fine, the ending is soft"
- "Give me three CTAs"
Steps
- Read the draft. State the single job: comment, save, or profile visit.
- Write three closes under 25 words. One question, one specific ask, one no-ask stop.
- Mark which one matches the voice profile if it is filled.
- Do not publish. Hand the chosen line back to the user to paste into the draft, then
linkedin-humanizerif they want a full audit.
Related
linkedin-post-writerlinkedin-humanizerlinkedin-approval-gate../../references/voice-rules.md../../references/operator-codesbyfebin.md
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.