agentleFS
guerrilla2799guerrilla2799/event-and-scale-os/skills/event-content/SKILL.md

event-content

Skill2 starsChanged 3 months agoMITView on GitHub

Use before any event, or when the user says "recap post", "event content", "social for the event", "what do we publish", "photographer brief", "post-event blog". Builds the content machine before the event so it ships within 24 hours instead of five days late. Writes workspace/events/<event>/content/. Owns what you publish. Not the outreach to people you met, which is `event-followup`.

1 other project uses a version of this.

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, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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. Distinctive:

    After an event, when nothing was prepared and speed still matters

    line 13
  2. Distinctive:

    All of it, in skeleton, with placeholders for what you cannot know yet:

    line 34
  3. Very specific:

    Every published piece runs through writing-quality.

    line 71

≈ “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

Event Content

Everything you will publish about the event, written before the event. Teams that plan to write it afterward send it five days late, and five days late is a different asset entirely.

When to use

  • T-3 weeks on any event worth talking about
  • After an event, when nothing was prepared and speed still matters
  • A roundtable or panel that generated genuinely good material

Inputs

  • Reads: workspace/events/<event>/ (the plan, the program, the speakers), workspace/program/charter.md
  • Needs from user: who publishes in which voice, whether the event is on or off the record, and what capture is available

Workflow

1. Build the pre-event set

AssetWhenVoice
Announcement, if publicT-4Company
Speaker announcementT-3Speaker, plus company amplification
A written piece on the topicT-2Speaker. Gives the invitation something to point at
"See you there" postT-1 weekIndividual, from everyone attending
Day-before postT-1 dayIndividual

For a private dinner, skip almost all of this. Publicizing a private room damages the thing that makes it work.

2. Write the post-event set before the event

All of it, in skeleton, with placeholders for what you cannot know yet:

AssetShip byNotes
Thank-you note to attendeesT+1 dayTemplated, personalized per recipient
No-show follow-upT+1 dayDifferent message. Offer the material, no guilt
Individual social postsT+1 dayOne per attendee from your team, in their own voice
Company recap postT+2 daysSkeleton written in advance, filled with what happened
Recap article or blogT+3 to 5 daysThe substantial one, drafted in outline beforehand
Clips, if recordedT+1 week
A longer piece from the best idea in the roomT+2 weeksFrequently the highest-value asset of all

The only work left afterward is personalization and filling the blanks, which is the only part that genuinely has to happen afterward.

3. Brief the photographer with a shot list

Without a list you get a hundred photos of people eating and none of the five you needed.

  • The room full and looking busy, from the back
  • Your speaker mid-gesture at the lectern or in conversation
  • Two or three candid conversation shots, three-quarter angle
  • The venue looking good before guests arrive
  • One clean group shot if the format allows it
  • Detail shots: the table set, the signage, the branding

Agree the permission rules first. Under Chatham House Rule or any off-the-record framing, publishing attendee faces or names is a breach, and it will cost you the next room. Ask in the room if you want a specific photo published.

4. Capture the substance, not just the pictures

The most valuable output of a good roundtable or panel is what was said. Assign a notetaker who is not the moderator or a speaker, and capture themes and quotable formulations rather than a transcript.

Get attribution permission on the spot. Asking in the room is easy. Asking three weeks later is awkward and usually gets a no.

5. Write recaps that are worth reading

A recap that lists who spoke and thanks everyone is a press release nobody reads. A recap worth reading takes the single most interesting thing said in the room and makes an argument out of it.

The test: would this be worth reading by someone who was not there and has no interest in your company? If not, rewrite it around the idea rather than the event.

6. Route everything through the quality gate

Every published piece runs through writing-quality. Event recaps are unusually prone to the tells: inflated significance, three-part lists, and words like "incredible" and "energy" doing the work that a specific detail should be doing.

Output

  • Writes: workspace/events/<event>/content/ with pre and post assets, the shot list, the capture plan, and the publishing calendar
  • Prints: the calendar with owners, which assets are drafted, and the permission rules

Rules & quality bar

  • The post-event set is written before the event
  • Photographer briefed with a written shot list
  • Chatham House Rule honored in every published asset, including social
  • Attribution permission asked in the room
  • A recap is an argument, not a thank-you list
  • Private dinners are not publicized. Publicity damages the format
  • Everything runs through writing-quality
  • No invented quotes. Attributed words are verbatim or they are paraphrase without quote marks

Related skills

  • Reads: the format skills, speaking-and-stage
  • Pairs with: event-followup (different audience, same deadline)
  • Gated by: writing-quality, optionally artifact-eval

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.