RRepoGEO

REPOGEO REPORT · LITE

shikras/shikra

Default branch main · commit ff79a4ce · scanned 6/3/2026, 3:13:30 AM

GitHub: 810 stars · 48 forks

AI VISIBILITY SCORE
30 /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
3 / 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 shikras/shikra, 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
  • highabout#1
    Add a concise description, relevant topics, and homepage URL to the About section

    Why:

    CURRENT
    Description: (none)
Topics: (none)
Homepage: (none)
    COPY-PASTE FIX
    Description: "Shikra is a Multimodal Large Language Model (MLLM) designed for referential dialogue, excelling in spatial coordinate inputs and outputs in natural language without additional vocabularies or external models."
Topics: `multimodal-llm`, `referential-dialogue`, `spatial-reasoning`, `large-language-models`, `deep-learning`, `computer-vision`, `mllm`, `llm`, `vision-language-model`, `ai-model`
Homepage: `http://arxiv.org/abs/2306.15195`
  • mediumreadme#2
    Add a clear statement about the project's license in the README

    Why:

    COPY-PASTE FIX
    Add a new section to your README, for example: `## License
This project is licensed under [**Please specify the exact license name(s) here, based on your LICENSE file content**]. Refer to the `LICENSE` file for full details.`
  • lowreadme#3
    Add a 'Quick Start' or 'Usage' section with a simple code example

    Why:

    COPY-PASTE FIX
    Add a new section, e.g., `## Quick Start` or `## Usage`, demonstrating how to run a basic inference or interact with the model using a simple code snippet, building on the 'Install' section.

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 shikras/shikra
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
OpenAI GPT-4V (Vision)
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. OpenAI GPT-4V (Vision) · recommended 1×
  2. Google Gemini (Pro/Ultra) · recommended 1×
  3. Hugging Face Transformers · recommended 1×
  4. BLIP-2 · recommended 1×
  5. LLaVA · recommended 1×
  • CATEGORY QUERY
    How to build a multimodal LLM capable of understanding and generating spatial coordinates?
    you: not recommended
    AI recommended (in order):
    1. OpenAI GPT-4V (Vision)
    2. Google Gemini (Pro/Ultra)
    3. Hugging Face Transformers
    4. BLIP-2
    5. LLaVA
    6. InstructBLIP
    7. ViT
    8. Swin Transformer
    9. Llama 2
    10. Flan-T5
    11. Detectron2
    12. Mask R-CNN
    13. GPT-3.5
    14. OWL-ViT (Open-World Localization for Vision Transformers)
    15. Grounding DINO (Open-Set Object Detection with Text Query)

    AI recommended 15 alternatives but never named shikras/shikra. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Looking for an LLM that handles referential dialogue with natural language spatial inputs.
    you: not recommended
    AI recommended (in order):
    1. GPT-4 (with Vision/Multimodal capabilities)
    2. Claude 3 Opus
    3. Gemini 1.5 Pro
    4. Llama 3 (70B Instruct)
    5. Mistral Large

    AI recommended 5 alternatives but never named shikras/shikra. 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 shikras/shikra?
    pass
    AI named shikras/shikra explicitly

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

  • If a team adopts shikras/shikra in production, what risks or prerequisites should they evaluate first?
    pass
    AI named shikras/shikra 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 shikras/shikra solve, and who is the primary audience?
    pass
    AI named shikras/shikra explicitly

    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 shikras/shikra. 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/shikras/shikra.svg)](https://repogeo.com/en/r/shikras/shikra)
HTML
<a href="https://repogeo.com/en/r/shikras/shikra"><img src="https://repogeo.com/badge/shikras/shikra.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

shikras/shikra — 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
shikras/shikra — RepoGEO report