event-followup
Skill2 starsChanged 3 months agoMITView on GitHub
Use at T-3 weeks, before the event, or when the user says "follow up after the event", "post-event emails", "thank you note", "we met these people, now what", "the leads from the show". Writes the tiered follow-up sequences before the event so the first tier ships inside 24 hours. Writes workspace/events/<event>/followup/. Owns the outreach to people you met. Not the public recap or social, which is `event-content`.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- calven-ai/marketing-as-codetheir own version, first seen Oct 7, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- calven-ai/marketing-as-code★ 10same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository23 other files it gives its agents.
- artifact-evalSkill
- audience-machineSkill
- conference-activationSkill
- event-and-scale-osSkill
- event-budgetSkill
- event-contentSkill
- event-logisticsSkill
- event-measurementSkill
- event-program-setupSkill
- event-retrospectiveSkill
- event-selectionSkill
- executive-dinnerSkill
- invite-motionSkill
- meeting-engineSkill
- owned-eventSkill
- roundtable-and-salonSkill
- run-of-showSkill
- speaking-and-stageSkill
- sponsorship-negotiationSkill
- staffing-and-briefingSkill
- venue-selectionSkill
- virtual-eventsSkill
- writing-qualitySkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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
- Distinctive: line 53
Follow-up quality is decided during the event, not after.
- Distinctive: line 58
If anything was promised in a conversation, that is the follow-up.
- Distinctive: line 82
Tiered by what actually happened: Never one blast
- Distinctive: line 86
Same-day notes: Follow-up quality is decided during the event
≈ “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.
Files
Event Followup
Written before the event. Sent inside 24 hours. Every team that plans to write follow-up afterward sends it days late, and days late turns a warm conversation into a cold email.
When to use
- T-3 weeks. This is the correct time to run this skill
- Immediately after an event where nothing was prepared, when speed still matters
- A recurring event program where follow-up should be systematized
Inputs
- Reads:
workspace/events/<event>/meetings.csv, the staffing assignments, the format plan - Needs from user: who sends what, and what was promised to whom (filled in on the day)
Workflow
1. Tier the follow-up by what actually happened
The single most important design decision. One templated blast to everyone scanned is worse than nothing, because it tells the people you actually talked to that they were a row in a spreadsheet.
| Tier | Who | What they get | When |
| 1 | Meeting held | Personal note from the person who was in it, referencing what was actually discussed, delivering anything promised, proposing the specific next step with a date | Inside 24 hours |
| 2 | Real conversation, no formal meeting | Personalized note from the person who had it, one specific reference, a light next step | Inside 48 hours |
| 3 | Attended, no meaningful conversation | A useful piece of content from the event. No "great to meet you" | Within a week |
| 4 | Scanned, no conversation | Nurture. Not a "great to meet you" email that both people know is false | Weekly batch |
| 5 | Registered, did not attend | Different message entirely. The material, no guilt, an offer to catch up | Inside 24 hours |
| 6 | Invited, declined | Nothing immediately. Note it, and invite them to the next one | Next cycle |
Tier 5 is the one everybody forgets. A no-show is frequently a person who genuinely wanted to come, and a warm, guilt-free note with the material outperforms most first touches.
2. Write the templates before the event
For each tier: the structure, the sender, the timing, and the placeholders for what can only be known afterward. Then afterward the only work is filling the blanks, which is the only part that has to happen afterward.
Tier 1 structure:
<Name>, good to meet you <yesterday / at the dinner>.
<One specific thing they said, in their words. This is the whole email.>
<The thing you promised, attached or linked. Delivered, not "I'll send it over.">
<The specific next step, with a proposed date.>Three to five sentences. No recap of your product. No deck unless one was requested. The specific reference in sentence two is what makes it a real email, and a generic version of it is worse than not sending.
3. Capture on the day so the specifics exist
Follow-up quality is decided during the event, not after. Every conversation gets a same-day note with what was discussed, what was promised, and the next step. Notes written three days later produce generic follow-up, and it shows.
Give every team member the note format in advance so it takes thirty seconds on a phone.
4. Deliver what was promised, first
If anything was promised in a conversation, that is the follow-up. An introduction, a document, an answer, a pricing question. Deliver it before anything else, and do not attach a next step to it if it was a favor.
5. Route the attendee list properly
The full attendee list, if you receive one, is not follow-up material. It is list-building material. Enrich it, score it against the ICP, and route it into the target list so the next event starts warmer. Do not email it as though those people met you.
6. Sequence the second and third touches
Most event pipeline comes from the second and third touch, not the first.
- T+1 week: the content from the event, from marketing, to everyone in tiers 1 through 3
- T+2 weeks: a personal check-in from the owner to tier 1 and 2 non-responders
- T+4 weeks: a genuinely useful, non-event reason to reconnect
- Then into normal nurture
7. Track it, by name
Per person: tier, owner, sent date, replied, next step, and the date. An event that produced twenty conversations and no tracked follow-up produced nothing.
8. Quality gate
Everything runs through writing-quality. Event follow-up is unusually prone to inflated warmth: "it was incredible to connect", "the energy in the room was amazing." A specific detail does that work better and reads as human.
Output
- Writes:
workspace/events/<event>/followup/with a template per tier, the note-capture format, the sequence calendar, and the tracking sheet - Prints: the tier table with owners and timing, the templates, and the capture format for the team
Rules & quality bar
- Written before the event. This is the point of the skill
- Tiered by what actually happened. Never one blast
- Tier 1 inside 24 hours
- The specific reference is mandatory. A generic tier 1 note is worse than none
- Deliver what was promised first
- Same-day notes. Follow-up quality is decided during the event
- No-shows get a real, guilt-free message
- The attendee list is list building, not follow-up
- Everything runs through
writing-quality
Related skills
- Reads:
meeting-engine,staffing-and-briefing,run-of-show - Pairs with:
event-content(different audience, same deadline) - Feeds:
event-measurement
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.

