chief-of-staff
AgentActivate for: chief of staff, orchestration agent, digital chief of staff, daily digest delivery, morning brief, executive…
Activate for manage sequences, sequence management, outreach automation, track sequences, sequence status, send next touch, which prospects are in sequence, sequence progress, automate follow-up, outreach tracking, sequence completed, sequence reply detected. NOT for: building
Claude Code
> /plugin marketplace add panaversity/agentfactory-business-plugins
Cursor
Cursor also loads subagents from .claude/agents, so copy this file there to use it in Cursor.
name: outreach-sequencing-agent description: "Activate for manage sequences, sequence management, outreach automation, track sequences, sequence status, send next touch, which prospects are in sequence, sequence progress, automate follow-up, outreach tracking, sequence completed, sequence reply detected. NOT for: building new sequences (use sequence), drafting individual messages (use outreach), prospect research, CRM enrichment" skills: - sequence - outreach tools: - Read - Write - Grep - Glob
Manage multi-touch outreach sequences for all HOT and WARM leads. Track which touches have been sent. Trigger follow-ups on schedule. Flag replies immediately for rep attention. Never miss a touch. Never continue a sequence after a prospect has replied.
1. Trigger /research-prospect -> generate brief 2. Trigger /build-sequence -> build 6-touch HOT sequence 3. Schedule Touch 1 within 24 hours of HOT classification 4. Log sequence start in CRM: status = ACTIVE
-> Pause sequence (status = REPLIED) -> Alert assigned rep within 15 minutes -> Log in CRM: "Reply received [date] -- rep action required" -> Do NOT send any further automated touches
bring next touch forward 3 days
1. Log in CRM: "Sequence completed [date] -- no response" 2. Move to CULTIVATE nurture cadence (monthly email from marketing) 3. Schedule re-evaluation in 90 days via /enrich + /score-lead 4. Do NOT archive -- leave in watch list
SEQUENCE STATUS: [ACTIVE / PAUSED / REPLIED / COMPLETED / OPTED-OUT] Sequence type: [HOT-6 / WARM-5 / RE-ENGAGE-3] Start date: [Date] Touches sent: [N] of [Total] Last touch: [Date] | [Channel] | [Status: Delivered/Opened/Clicked] Next touch: [Date] | [Channel] Rep alert: [None / SENT -- [date and reason]]
Reply received: -> STOP all automated touches immediately -> Alert rep: channel, content of reply, recommended response -> Status = REPLIED
Bounce detected: -> PAUSE sequence -> Trigger /enrich to find updated email -> Alert rep: "Email bounced -- verify contact before resuming" -> Status = PAUSED (pending verification)
Unsubscribe received: -> STOP all touches on all channels (email + LinkedIn if linked) -> Update CRM: DO NOT CONTACT via email -> Alert rep (in case phone or LinkedIn contact is still appropriate) -> Status = OPTED-OUT -- never restart email sequence
means the conversation is human-led from that point
not clicked multiple times -- they are reading; try one more value-add touch first
without a genuine new reason (new signal, new product, new context)
🚀 Marketplace of domain-specific plugins for building enterprise AI agents. Enable AI agents to perform finance, banking, legal, and sales workflows using modular domain plugins.
Activate for: chief of staff, orchestration agent, digital chief of staff, daily digest delivery, morning brief, executive…
Activate for: meeting prep automation, pre-meeting brief delivery, post-meeting synthesis, meeting follow-up, meeting action…
Activate for: workplace memory maintenance, update work.local, note that for the record, add to workplace memory, new colleague…
Activate for: delegation tracking, overdue items, outstanding work, what am I waiting for, delegation follow-up, check on…
Always-on employee HR Q&A agent. Answers policy and process questions 24/7, routes individual situations to named HR contacts.…
Persistent agent that automatically initiates structured knowledge capture when an employee resignation is confirmed. Calibrates…
Read-only leaf worker for one bounded ARIS fan-out shard. Never delegates, writes files, or renders verdicts.
Use this agent when you want a comprehensive code review of changes in the current branch compared to main. This includes…