heypastelheypastel/pastel-outbound-system/skills/reply-desk/SKILL.md

reply-desk

Skill2 starsChanged 56 days agoMITView on GitHub

Concierge — goes through the LinkedIn inbox via Pastel, tags each conversation (hot, curious, timing, pushback, stop, skip), quotes what the person wrote, and drafts the answer. Use for "check my replies", "who's interested", or clearing the 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
- social-warmupSkill
- what-worksSkill
- why-nowSkill

The file

Create a free account to mount

Files

SKILL.md

Reply desk — Concierge

House rules: ../command-center/shared/house-rules.md · Pastel tools: ../command-center/shared/pastel-tools.md

Steps

pastel_list_conversations(unread_only=true); include recent read ones if asked. Open each with pastel_get_conversation. The inbox comes from Pastel's copy of LinkedIn, which can lag slightly — say so if timing matters.
Tag every conversation:

Tag	Sounds like	Goes to
hot	"Can we talk?", asks for a price, a demo, or next steps	`call-ready`, now
curious	Wants to understand something, no intent yet	answer here, then `nudge` if they go quiet
timing	"Not now", "after Q3", out of office with a return date	`nudge`, scheduled for the date they gave
pushback	Has a tool, no budget, not a priority	one thoughtful answer here, then leave it
stop	Asks not to be contacted, or is hostile	record it; no more messages
skip	Automatic notes, a bare "thanks", emoji	nothing

Draft answers for hot, curious, and pushback, hot first; run human-voice; prepare send_chat_message on the conversation's chat_id for approval.
For every stop: prepare mark_lead_status → NOT_INTERESTED and a pause of any running sequence.

Output

# Replies — [date]
Open: n · hot n · curious n · timing n · pushback n · stop n

### [Person] · [tag]
They wrote: "…"
Answer:
> …
Next: [skill] · chat_id […]

Download now (ZIP)

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

What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free