agentleFS
samsational-codesamsational-code/business-skills/conference-prep-planner/SKILL.md

conference-prep-planner

Skill0 starsChanged 2 months agoMITView on GitHub

Turn a conference attendee, speaker, sponsor, or exhibitor list plus the user's goals into a working event plan — a tiered, prioritized target list with evidence-based why-them one-liners, pre-conference outreach drafts, per-day scheduling logic, talking points per target, and a post-event follow-up tracker. Built for anyone attending an event with a purpose: sales and business development, partnerships, recruiting, fundraising, investor relations, job hunting, academic or clinical networking, and founders at trade shows, industry conferences, developer conferences, medical congresses, career fairs, or user summits. Trigger on "prep me for [conference]," "here's the attendee list for [event]," "who should I meet at [conference]," "build my conference target list," "conference game plan," "outreach for [event]," "I'm going to [conference] next month," or when a user shares a speaker/attendee/exhibitor list and a goal. Do NOT use for deep prep on one specific person — use the professional-profile-brief skill. Do NOT use for researching one target organization in depth — use the company-first-pass or private-company-tear-sheet skill.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Missing-input behavior: If the list or the goal is missing, ask once for whichever is absent — without a goal, prioritization is fake.

    line 47
  2. Distinctive:

    No invented event details: don't make up session times, party invites, or venue logistics not in the provided agenda.

    line 115
  3. Distinctive:

    Every Tier 1–2 target has an evidence-based why-them line?

    line 122

≈ “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

Conference Prep Planner

Convert a conference attendee list, speaker roster, exhibitor directory, or event-app export plus the user's goals into an executable plan: who to pursue (tiered, with a one-line reason each), what to send them before the event, how to sequence the days, what to say in each conversation, and a tracker that makes the follow-up actually happen. The plan is built around a truth every experienced networker knows: conferences are won in the two weeks before and the week after, not at the booth.

Why this skill exists

A sales lead lands at a 3,000-person industry trade show with 48 hours and a vague intention to "see who's around." A recruiter shows up at a developer conference hoping the right engineers wander past. A founder attends a partner summit with no list. In each case the attendee list was available three weeks earlier; nobody triaged it. The result is serendipity-dependent networking: coffee with people they already know, two random hallway meetings, and a stack of badge-scan contacts nobody follows up with. Triaging 800 names against a goal, drafting 25 outreach notes, and building a follow-up tracker is a solid two days of work — which is why it doesn't happen. This skill compresses it to an afternoon.

Inputs

Required:

  • The attendee, speaker, sponsor, or exhibitor list (pasted, file, or export from the event app) — names with organizations at minimum
  • The user's goal, concretely: booking demos with hospital IT directors; recruiting senior backend engineers; finding distribution partners in three new regions; meeting seed investors for a first round; landing a product-management role at a mid-size software company; meeting acquirers for a business unit

Optional but high-value:

  • Conference name and dates, session agenda, the user's existing commitments (panels, booth shifts, dinners)
  • The user's existing relationships on the list ("know well / met once / cold")
  • A one-liner about the user's organization, product, or self for outreach drafts
  • Number of days attending and realistic meeting capacity per day

Missing-input behavior: If the list or the goal is missing, ask once for whichever is absent — without a goal, prioritization is fake. Otherwise proceed with labeled assumptions (default: 2 conference days, 8 meeting slots/day, standard 25-minute coffee meetings).

How it works

  1. Score the list against the goal. Every name gets a relevance read based on what's actually known (title, organization, organization type). Where the list gives only name + organization, use your AI's web search to enrich the top candidates — role, focus area, recent news — rather than enriching all 800.
  2. Tier the targets:
    • Tier 1 (5–10): direct goal fit; pursue with pre-booked meetings; walk away disappointed if missed
    • Tier 2 (10–25): strong fit; pre-conference outreach, opportunistic scheduling
    • Tier 3 (open-ended): worth a hello if encountered; no outreach investment
    • Each target gets a why-them one-liner grounded in evidence ("VP Engineering at a 400-person logistics software company, speaking Tuesday on platform migration") — not "could be interesting."
  3. Draft pre-conference outreach for Tiers 1–2: short, specific, sendable. Each note references something true about the target, states the ask plainly (20 minutes, specific day), and avoids the "would love to connect" void. Cold and warm variants where relationship status is known. Output as text to copy-paste — or into your email tool if one is connected.
  4. Build the per-day schedule logic (not a fantasy calendar): which targets to anchor each day around, when to be at which sessions (a Tier 1 target's talk is a scheduling anchor and a conversation opener), where the user's own commitments create adjacency opportunities, and explicit white space — back-to-back-packed conference schedules collapse by 2pm Day 1.
  5. Write talking points per Tier 1 target: an opener tied to them, two substantive threads, the soft ask, and the thing not to lead with (don't pitch in sentence one to a decision-maker who gets pitched forty times a day; don't open with "are you hiring?" to a hiring manager at their own company's booth).
  6. Produce the follow-up tracker — a table the user fills during/after the event, with pre-drafted follow-up note skeletons keyed to meeting outcome (met / missed-but-targeted / new contact).

Output format

# Conference Plan — [Event], [Dates]
Goal: [user's goal] | List size: [n] | Tiered: [n1]/[n2]/[n3]
Assumptions: [days attending, slots/day, anything defaulted]

## Tier 1 Targets
| Name | Organization / Role | Why Them (one line) | Status | Pre-Book? |
|---|---|---|---|---|

## Tier 2 Targets
Same table, compressed.

## Pre-Conference Outreach (send ~2 weeks out)
### [Target name] — [cold/warm]
Subject: …
[3–5 sentence note with a specific ask and day]
(repeat for each Tier 1–2 target)

## Day-by-Day Logic
### Day 1
Anchor meetings, session positioning, adjacency plays, protected white space.
(repeat per day)

## Talking Points — Tier 1
### [Target name]
Opener: … | Threads: 1)… 2)… | Soft ask: … | Don't lead with: …

## Follow-Up Tracker (fill in as you go)
| Name | Tier | Met? | Key Notes | Promised | Follow-Up Owed | Sent? |
|---|---|---|---|---|---|---|

## Follow-Up Note Skeletons
Met / Missed / New-contact variants, ready to personalize within 48h post-event.

Outreach drafting notes

What makes a pre-conference note get answered (and what kills it):

  • Subject lines name the event and the ask: "[Event] — 20 min Tuesday?" beats "Connecting at the conference"
  • First sentence is about them, and specifically them — their talk, their recent launch or hire, their organization's stated focus. If the only available opener is generic, say something honest and short instead of faking specificity.
  • One ask, one timeframe: "20 minutes Tuesday morning near the main stage" — concrete asks get calendar responses; "grab time" gets silence.
  • Two sentences of who-you-are maximum. The meeting is the pitch; the email is not.
  • No attachments on first contact. Deck, resume, or brochure requests come after a yes — and in regulated industries (financial services, healthcare, pharmaceuticals, government contracting), sending marketing materials cold may itself trigger review requirements; route materials through the organization's approved process.
  • The bump: plan one short follow-up 3–4 days later for non-responders ("Floating this back up — Wednesday also works"). Draft it with the original.
  • Send ~2 weeks out: calendars are forming but not full. Day-before outreach only works for Tier 3 hellos.

Guardrails

  • Why-them lines must be evidenced. From the list, from enrichment search (with the source implicit in the claim), or from the user's input. Never invent a target's title, remit, or interests — if enrichment found nothing, the line says what's actually known ("Director at [organization]; organization works in [space] per their site").
  • Never fabricate a relationship or prior interaction in outreach drafts. Cold notes are honestly cold.
  • No invented event details: don't make up session times, party invites, or venue logistics not in the provided agenda.
  • Outreach drafts contain no performance, outcome, or results claims unless the user supplied the exact language — outreach is marketing material and common claim-substantiation principles apply; flag any draft where the user's one-liner includes results figures, and remind the user that regulated industries may require review before sending.
  • People research stays public and professional.
  • Be honest about capacity: if Tier 1+2 exceeds realistic meeting slots, say so and force-rank rather than pretending 40 meetings fit in two days.

Quality checks

  • Every Tier 1–2 target has an evidence-based why-them line?
  • Outreach notes specific enough that the target can say yes to a time and place?
  • Schedule includes anchors, adjacencies, and protected white space?
  • Talking points reference something true per target, not generic openers?
  • Tracker usable on a phone between meetings (simple columns, no essay fields)?
  • Capacity math honest?

Example prompts

"Attached is the attendee export from the national healthcare IT conference — I'm there Tuesday and Wednesday. Goal: first meetings with CIOs and IT directors at 200–800 bed hospitals for our patient-intake platform (I can share the one-liner). I know maybe ten people on this list well. Build me the plan — tiers, outreach I can send Thursday, and the follow-up tracker."

"Developer conference speaker list pasted below. I'm the recruiting lead for a 60-person infrastructure startup; goal is conversations with senior backend engineers and engineering managers who might be open to a move. Three days, and I'm running a booth shift Wednesday afternoon — build the plan around that."

"Smaller event: 80-person regional manufacturing supplier summit, attendee list attached. Goal is two specific distribution partnerships in the Southeast. Skip the tiers, give me outreach and talking points for the eight names that matter."

"I'm job hunting. Here's the sponsor and speaker list for a product-management conference. Goal: meet hiring managers at mid-size B2B software companies. Two days. I know nobody."

Works well with

Deep-prep individual Tier 1 targets with professional-profile-brief (people) or company-first-pass / private-company-tear-sheet (organizations); after the event, call-transcript-followup and relationship-status-summarizer keep the tracker honest.

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.