sansheng-image
给 Agent 的生图 Skill：读懂内容，挑画风与色系，生成风格统一的封面、插图、小红书、PPT；按需制作动态插图。
A new way for AI to search for data
1GitHub stars
What XERJ indexed
Selected work
“add purpose-based methods and replayable examples”. 13 files, 828 lines in examples, tests, scripts.
Licence
The repository
MIT
Checked by a person at the pinned commit.
The XERJ corpus
MIT, with credit
The author agreed by email on 2026-10-20. Same terms as the repository. Answers name the repo, the commit and the file:line.
in licence reviewnot in the hub yetsuggested use: adapt with attribution
agent-skillsclaude-codecodeximage-generationinfographics
Example questions
- How does sansheng-image implement agent-skills?
- Where does sansheng-image handle “add purpose-based methods and replayable examples”?
- Show the claude-code code in sansheng-image.
The prompt
Paste it into your AI agent. It clones sanshengai/sansheng-image at the pinned commit and indexes it on your machine.
Search the GitHub repository sanshengai/sansheng-image with XERJ (https://hub.xerj.org/corpus/sanshengai--sansheng-image). Run these in a shell, in order, and check each result before the next: 1. xerj --help (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh 2. git clone https://github.com/sanshengai/sansheng-image sansheng-image && git -C sansheng-image checkout 8a5e8c716af1aec1caafd9eae60d0882d5753360 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./sansheng-image --url http://127.0.0.1:9200 --prefix sansheng-image --progress plain 5. xerj autoindex map --url http://127.0.0.1:9200 Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt Licence: MIT. Keep the copyright notice and credit the authors.
Related
叁笙早安 AIAI, prompts and agents corporaxerj-blogpostsDavidLam-oss/wechat-writing-teamcalven-ai/marketing-as-codeandreiverdes/bluedoc
Selected work and consent: the XERJ registry.