mcpField
R
read-the-room

read-the-room

github.com/scrollmarkMarketing & growth1658 installsUpdated 1d ago
Repository

About read-the-room

Read the Room is a skill for agents interpreting social media text. It starts by identifying register, then uses emoji, cultural references, and conversational context to assess meaning and sentiment, with reference files for unfamiliar slang or platform norms.

Key features

  1. 01Identify four text registers
  2. 02Use emoji to interpret tone
  3. 03Check memes and cultural references
  4. 04Assess layered comment sentiment
  5. 05Load slang and platform references

Use cases

  1. 01Interpret ironic social posts
  2. 02Understand emoji meaning in comments
  3. 03Analyze platform-specific comment context

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/scrollmark/social-skills --skill read-the-room

After installing, type/read-the-roomin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

references/
slang-and-signals.md
references/platforms/
instagram.md
linkedin.md
tiktok.md
x.md
youtube.md

Details

From the project README

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)

Comments

Markdown supported