emoji-recommender
Skill0 starsChanged 9 months agoMITView on GitHub
Recommends the 5 best emoji for any description, phrase, concept, mood, or situation — with clear reasoning for each pick. Use this skill whenever the user asks for emoji suggestions, says things like "what emoji should I use for X", "give me emojis that mean Y", "which emoji fits Z", or wants help picking emojis for a caption, bio, message, or vibe. Trigger this even if the user just casually tosses out a phrase and seems to want emoji without explicitly saying so.
In this repository3 other files it gives its agents.
- alt-text-generatorSkill
- apple-store-trackerSkill
- hn-digestSkill
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 13
Read the user's input (could be a word, phrase, feeling, scenario, aesthetic, etc.)
- Distinctive: line 23
Keep reasoning concise and human — like you're texting a friend, not writing a dictionary entry.
- Distinctive: line 29
Diversity: Don't cluster on too-similar emoji.
- Distinctive: line 32
Cultural awareness: Consider how the emoji is actually used on social media / in messaging, not just its official name.
≈ “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
Emoji Recommender
Given a description, phrase, concept, mood, or situation, surface the 5 emoji that best represent it — with a punchy explanation for each.
Core Task
- Read the user's input (could be a word, phrase, feeling, scenario, aesthetic, etc.)
- Think broadly: consider literal meaning, metaphorical associations, cultural usage, emotional tone, and how people actually use the emoji in the wild
- Return exactly 5 emoji candidates, ranked from best fit to honorable mention
Output Format
Present results like this:
[emoji] — [1-sentence reason why it fits]
Keep reasoning concise and human — like you're texting a friend, not writing a dictionary entry. Mention both the literal and vibe-based reasons when relevant.
End with a brief note on which one you'd actually pick if you had to choose just one, and why.
Quality Criteria
- Diversity: Don't cluster on too-similar emoji. Cover different angles (literal, emotional, symbolic, aesthetic).
- Relevance: Prioritize emoji people actually reach for in this context, not just technically accurate ones.
- Insight: The explanations should make the user go "oh yeah, that's exactly it" — not just describe what the emoji looks like.
- Cultural awareness: Consider how the emoji is actually used on social media / in messaging, not just its official name.
Examples
Input: "feeling nostalgic"
- 🌅 — Sunsets = looking back, the bittersweet beauty of something passing
- 📼 — VHS tape vibes, literal throwback aesthetic
- 🥹 — That face you make when something hits different emotionally
- 🍂 — Autumn as a universal metaphor for time passing
- 💭 — Lost in thought, deep in memories
Best pick: 🥹 — it captures the emotional complexity of nostalgia better than anything else
Input: "chaotic coworker energy"
- 🤡 — The classic "this person is a clown" shorthand
- 🌀 — Pure chaos swirl
- 😵 — What you feel after interacting with them
- 🎪 — It's literally a circus
- 💥 — Everything they touch somehow explodes
Best pick: 🎪 — because it implies you're not just dealing with one clown, it's a whole show
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.