agentleFS
guerrilla2799guerrilla2799/sdr-copilot/skills/work-inbound/SKILL.md

work-inbound

Skill1 starsChanged 4 months agoMITView on GitHub

Turn the last 24 hours of inbound leads into a prioritized call-order list with context and openers — speed-to-lead for form fills, trial signups, and campaign registrations. Use when the rep says "work my inbound", "new leads", "who came in today/overnight", or "process these leads" (with a pasted list).

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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
  1. Very specific:

    Read ${CLAUDE_PLUGIN_ROOT}/references/icp.md and references/guardrails.md if not already in context.

    line 12
  2. Distinctive:

    If the HubSpot connector can't run that query (or isn't connected), say so and ask the rep to paste the lead list/export — the rest of the …

    line 18

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Work Inbound

Much of your pipeline may be inbound, and inbound decays by the hour — a signup called today is a conversation, called Thursday is a voicemail. This skill turns the overnight batch into a call order, not a reading list. Target runtime: faster than signal-watch; this is the FIRST thing to run each morning, before the cold-outbound sweep.

Before you work

Read ${CLAUDE_PLUGIN_ROOT}/references/icp.md and references/guardrails.md if not already in context.

Step 1 — Pull the leads

Query HubSpot for contacts/leads created or reactivated in the last 24 hours (Mondays: last 72). Capture per lead: name, title, company, source/conversion event (form, trial signup, content download, campaign registration), and any message they left in a form field — a free-text field is gold, quote it back in the opener.

If the HubSpot connector can't run that query (or isn't connected), say so and ask the rep to paste the lead list/export — the rest of the skill works the same. Never silently skip the pull.

Step 2 — Triage each lead

CRM check first (guardrail #1, still applies to inbound):

  • Existing customer → not your lead. Route to the account owner/CS with a one-line note ("[name] at [customer] filled the [form] — expansion signal?").
  • Open deal / active demo on the account → pass to the deal owner as intel, don't touch.
  • Everyone else → yours.

Then score fit (10-point rubric, from what's visible + one quick Exa/web check for anything scoring near a tier boundary — cap research at ~1 search per lead, this is triage not account-brief):

  • Tier 3 / score <5 → do not call (guardrail #6). Note them as "self-serve — no touch" so the discipline is visible.

Then weight intent by source. Fit × intent sets the call order:

IntentSourcesHandling
🔥 Hand-raiseDemo request, contact-sales form, pricing page formCall within the hour. No research beyond the triage pass — speed beats polish here.
HighTrial / free signup (if the product has one)Call same-day. Champion types often prefer to self-serve — the call offers help, not a pitch ("saw you got set up — anything not showing up the way you expected?").
MediumContent download / gated assetSame-day email + call if Tier 1. Reference the specific asset.
SoftCampaign registration (webinar/event/content series, if one is live)⚠️ A webinar reg is NOT a sales hand-raise — hard-pitching registrants poisons the series. Tier 1 registrants get ONE light touch: personal note, one genuine question about their setup, zero meeting ask ("what got you interested in the session?"). Everyone else waits for the post-session follow-up flow (your marketing lead owns that).

Step 3 — Openers

For each lead you will actually call/email: persona guess (Champion/Practitioner/Economic Buyer), a 2-sentence context line, and a call opener that names their conversion event specifically ("you grabbed the [asset] yesterday — calling to ask what you were hunting for in it"). Inbound openers reference what THEY did; never open an inbound call with a cold-outbound trigger line.

Output format

# Inbound · [date] · [N] new leads

## Call now (hand-raises + hot trials)
1. **[Name, Title, Company]** — [source, when] — score [X]/10 · [persona]
   Context: [2 sentences]
   Opener: "[...]"
   [phone/email/LinkedIn from HubSpot]

## Today (worked in order)
[same format]

## One light touch (campaign Tier 1 regs)
[name — company — the no-pitch note draft]

## Routed away
[lead → customer/active-deal → who it went to]

## No touch (Tier 3 / <5)
[name — company — why]

End with: log every connect/conversation in HubSpot as it happens (guardrail #5), and "say brief me on [company] before any call where you feel thin, or write an email to [name] for the follow-up."

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.