RRepoGEO

REPOGEO REPORT · LITE

NomaDamas/KICE_slayer_AI_Korean

Default branch master · commit 399e4856 · scanned 6/15/2026, 3:13:24 PM

GitHub: 531 stars · 34 forks

AI VISIBILITY SCORE
17 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
1 pass · 0 warn · 1 fail
Objective metadata checks
AI knows your name
1 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface NomaDamas/KICE_slayer_AI_Korean, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • hightopics#1
    Add relevant topics to the repository

    Why:

    COPY-PASTE FIX
    llm-benchmarking, korean-language, standardized-tests, suneung, autorag, nlp, large-language-models, education-ai
  • highreadme#2
    Add a concise introductory sentence to the README

    Why:

    COPY-PASTE FIX
    이 프로젝트는 최신 LLM 모델들의 수능 국어 영역 성능을 벤치마킹하고 비교 분석합니다.
  • highlicense#3
    Create a LICENSE file

    Why:

    COPY-PASTE FIX
    LICENSE

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
0 / 2
0% of queries surface NomaDamas/KICE_slayer_AI_Korean
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
KLUE-benchmark/KLUE
Recommended in 3 of 2 queries
COMPETITOR LEADERBOARD
  1. KLUE-benchmark/KLUE · recommended 3×
  2. OpenKo-LLM Leaderboard · recommended 1×
  3. huggingface/evaluate · recommended 1×
  4. KorQuAD 1.0/2.0 · recommended 1×
  5. AI Hub Datasets · recommended 1×
  • CATEGORY QUERY
    How to benchmark large language models for Korean language standardized tests?
    you: not recommended
    AI recommended (in order):
    1. OpenKo-LLM Leaderboard
    2. KLUE (Korean Language Understanding Evaluation) benchmark (KLUE-benchmark/KLUE)
    3. Hugging Face evaluate library (huggingface/evaluate)
    4. KorQuAD 1.0/2.0
    5. KLUE-NLI (KLUE-benchmark/KLUE)
    6. KLUE-MRC (KLUE-benchmark/KLUE)
    7. AI Hub Datasets
    8. EleutherAI/lm-evaluation-harness (EleutherAI/lm-evaluation-harness)
    9. KoBEST (Korean Benchmark for Evaluating Semantic Textual Similarity) (SKT-AI/KoBEST)
    10. OpenAI Evals (openai/evals)

    AI recommended 10 alternatives but never named NomaDamas/KICE_slayer_AI_Korean. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Comparing LLM performance and costs for Korean standardized test preparation?
    you: not recommended
    AI recommended (in order):
    1. GPT-4
    2. Claude 3 Opus
    3. Claude 3 Sonnet
    4. Google Gemini 1.5 Pro
    5. Naver HyperCLOVA X
    6. Kakao KoGPT
    7. Mistral Large
    8. Mixtral 8x7B

    AI recommended 8 alternatives but never named NomaDamas/KICE_slayer_AI_Korean. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    fail

    Suggestion:

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of NomaDamas/KICE_slayer_AI_Korean?
    pass
    AI did not name NomaDamas/KICE_slayer_AI_Korean — likely talking about a different project

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts NomaDamas/KICE_slayer_AI_Korean in production, what risks or prerequisites should they evaluate first?
    pass
    AI named NomaDamas/KICE_slayer_AI_Korean explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo NomaDamas/KICE_slayer_AI_Korean solve, and who is the primary audience?
    pass
    AI did not name NomaDamas/KICE_slayer_AI_Korean — likely talking about a different project

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of NomaDamas/KICE_slayer_AI_Korean. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/NomaDamas/KICE_slayer_AI_Korean.svg)](https://repogeo.com/en/r/NomaDamas/KICE_slayer_AI_Korean)
HTML
<a href="https://repogeo.com/en/r/NomaDamas/KICE_slayer_AI_Korean"><img src="https://repogeo.com/badge/NomaDamas/KICE_slayer_AI_Korean.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

NomaDamas/KICE_slayer_AI_Korean — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite