agentleFS
scrollmarkscrollmark/social-skills/skills/read-the-room/SKILL.md

read-the-room

Skill19 starsChanged 30 days agoMITView on GitHub

Use when interpreting social media content — comments, captions, replies, DMs — and you need to understand tone, subtext, or cultural context beyond the literal words.

3 other projects use 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. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 3

    Distinctive

    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:

    Before interpreting any social media text, identify the register.

    line 8
  2. Distinctive:

    Before taking any strong statement at face value, ask: is this a meme format, copypasta, or cultural reference?

    line 32
  3. Distinctive:

    If you're unsure whether something is a reference, say so rather than interpreting it literally.

    line 38

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “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

Read the Room

Before interpreting any social media text, identify the register. Everything else follows from this.

The Four Registers

  • Sincere: earnest, personal, means what it says. "This genuinely changed my life" with a long personal story.
  • Ironic: says one thing, means another. Exaggeration, emoji mismatch, deadpan delivery. "wow so original 🙄"
  • Performative: audience-aware, playing to the crowd. Engagement bait, hot takes crafted for reaction, "unpopular opinion" that's actually popular.
  • Parasocial: addressing a creator like a close friend. "SO proud of you!!" from a stranger. Not insincere — just a different relationship than it appears.

Get the register wrong and you'll misread everything downstream. When in doubt, check for irony first — it's the most commonly missed.

Emoji as Grammar

Emoji modify meaning the way adverbs modify verbs. They don't decorate — they redirect.

  • 💀 after a statement = "this is hilarious." Not death.
  • 😭 is almost always laughter or overwhelm, rarely actual sadness (context: is the post funny or tragic?)
  • ✨ around a phrase is either sincere emphasis or sarcastic. "✨productivity✨" about doomscrolling = sarcastic.
  • 🫠 = "I'm overwhelmed and coping with humor"

A single emoji can flip the meaning of an entire sentence. "Love that for you" is supportive. "Love that for you 🙃" is not.

The Reference Check

Before taking any strong statement at face value, ask: is this a meme format, copypasta, or cultural reference? Signals:

  • Unusual formality or dramatic language that feels templated
  • Very specific phrasing you've seen variations of
  • Excessive emotion that seems performed rather than felt

If you're unsure whether something is a reference, say so rather than interpreting it literally.

Comment Sentiment Layers

Surface words ≠ actual sentiment. Common inversions:

  • "Nobody asked" — can be playful ribbing between regulars
  • "Obsessed" — always positive
  • "This is so bad" under a comedy video — means it's good
  • "Unfollow" as a comment — often a joke about how good the content is
  • "I'm calling the police" — the content is outrageously good/funny

Context matters: who's talking to whom, what's the post about, what platform is this on.

When to Load References

If you encounter unfamiliar slang or emoji usage, read references/slang-and-signals.md from this skill's own directory. For platform-specific comment culture, read references/platforms/{platform}.md from this skill's own directory. If the references can't be loaded, work with the patterns above and note the gap to the user.

Anti-patterns

  • Treating all text as literal
  • Ignoring emoji or treating them as decoration
  • Assuming negative words = negative sentiment without checking register
  • Ignoring who is speaking to whom (context collapse)

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.