social-warmup
Skill2 starsChanged 56 days agoMITView on GitHub
Networker — makes the user a familiar name before any DM by drafting comments and reactions on prospects' LinkedIn posts through Pastel, choosing the posts worth it. Use for "which posts should I comment on", warming up leads ranked 50-69, or working the Pastel posts inbox.
In this repository20 other files it gives its agents.
- AGENTS.mdAGENTS.md
- buying-committeeSkill
- call-readySkill
- campaign-launchSkill
- command-centerSkill
- competitor-watchSkill
- fit-checkSkill
- human-voiceSkill
- intent-radarSkill
- market-mapSkill
- message-writerSkill
- morning-briefSkill
- nudgeSkill
- outbound-briefSkill
- post-studioSkill
- priority-rankSkill
- reach-checkSkill
- reply-deskSkill
- what-worksSkill
- why-nowSkill
The file
Files
Social warmup — Networker
House rules: ../command-center/shared/house-rules.md · Pastel tools: ../command-center/shared/pastel-tools.md
An invitation from someone who left a smart comment on your post last week gets accepted. The comment is there to add to their conversation; the pitch waits for the DM.
Steps
- Choose posts:
pastel_recommend_best_posts(statusNEW), or for specific leadspastel_query_postswith their name or company. Read each withpastel_get_details. - Leave alone: job announcements, personal or sad news, and posts older than 7 days.
- Draft:
pastel_draft_reply(post_id), orpastel_get_reply_promptto write within Pastel's reply guidance yourself. Thenhuman-voice. - A comment worth leaving adds one concrete thing — a number, an example, a respectful counterpoint — or asks the author something they'll enjoy answering. One to three sentences. No product name, no link, no "happy to chat".
- After approval:
comment_on_post(orsave_replyto keep it as a Pastel draft), plusreact_to_postwhere it fits. Thenmark_post_status→REPLIED, andPASSwith apass_reasonon the skipped ones. - Hand-off: anyone who replies to or reacts on the comment goes to
campaign-launchthree to five days later, with "we commented on [post], [date]" as their signal.
Output
# Warmup — [date]
### [Author] · [Company] · posted [date]
Post starts: "…"
Why this one: …
Comment:
> …
Action: comment + like | save as draft | pass — reasonClose with one pastel_show_posts call with the chosen ids.
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.

