REPOGEO REPORT · LITE
WisdomShell/codeshell
Default branch main · commit 09d1adc8 · scanned 5/25/2026, 12:02:57 PM
GitHub: 1,628 stars · 118 forks
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 WisdomShell/codeshell, 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
2 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.
- highreadme#1Ensure the primary README.md starts with a clear English introduction
Why:
CURRENT## Introduction CodeShell是北京大学知识计算实验室联合四川天府银行AI团队研发的多语言代码大模型基座.
COPY-PASTE FIXMove the content from `README_EN.md` to be the primary introduction in `README.md`, ensuring the very first content section clearly describes CodeShell. For example, start with: 'CodeShell is a multilingual code large language model base developed by Peking University Knowledge Computing Lab in collaboration with Sichuan Tianfu Bank AI Team. CodeShell has 7 billion parameters, was trained on 500 billion tokens, and has a context window length of 8192. CodeShell achieves the best performance among models of similar scale on authoritative code evaluation benchmarks (HumanEval and MBPP).'
- mediumlicense#2Add a clear statement about the repository's license in the README
Why:
COPY-PASTE FIXAdd a section or line in the README, perhaps under 'Introduction' or a new 'License' section, stating: 'This project is released under the terms specified in the [License.pdf](https://github.com/WisdomShell/codeshell/blob/main/License.pdf) file. Please refer to the PDF for full details on usage and distribution.'
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.
- CATEGORY QUERYWhat are the best open source large language models for code generation?you: not recommended
Show full AI answer
- CATEGORY QUERYWhich code LLMs offer strong benchmark performance and good context window for development?you: not recommended
Show full AI answer
Objective checks
Rule-based audits of metadata signals AI engines weight most.
- Metadata completenesswarn
Suggestion:
- README presencepass
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 WisdomShell/codeshell?passAI named WisdomShell/codeshell explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
- If a team adopts WisdomShell/codeshell in production, what risks or prerequisites should they evaluate first?passAI named WisdomShell/codeshell 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 WisdomShell/codeshell solve, and who is the primary audience?passAI named WisdomShell/codeshell 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 WisdomShell/codeshell. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.
[](https://repogeo.com/en/r/WisdomShell/codeshell)<a href="https://repogeo.com/en/r/WisdomShell/codeshell"><img src="https://repogeo.com/badge/WisdomShell/codeshell.svg" alt="RepoGEO" /></a>Subscribe to Pro for deep diagnoses
WisdomShell/codeshell — 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