docs(skills): include image suffixes in the resource watcher list (#584)

* docs(skills): include image suffixes in the resource watcher list

The default resource_watch_loop has watched image suffixes since #526 and
auto_resource renders them into caption cards, but the skill still listed
only the seven text types. An agent reading the skill would conclude that
images dropped under resource/ are never processed.

* docs(skills): clarify image captioning requirements

---------

Co-authored-by: jinli.yl <jinli.yl@alibaba-inc.com>
This commit is contained in:
Ziyang Guo 2026-10-12 16:36:34 +08:00 • committed by GitHub
parent bf7dc2e512
commit ca4842fe4d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -182,7 +182,8 @@ Use ReMe commands instead of editing memory files directly unless the user expli
## Ingest Resources
Place external documents under `resource/YYYY-MM-DD/` in the selected ReMe workspace. While `reme start` is running, the
default background watcher processes new or changed `md`, `txt`, `json`, `jsonl`, `csv`, `yaml`, and `html` files.
default background watcher processes new or changed `md`, `txt`, `json`, `jsonl`, `csv`, `yaml`, `html`, and image files
(`png`, `jpg`, `jpeg`, `webp`, `gif`, `bmp`, `tiff`, `heic`); images produce caption cards linked to the original file.
To request processing explicitly:
@ -191,6 +192,7 @@ reme auto_resource changes='[{"path":"resource/<YYYY-MM-DD>/<file>","change":"ad
```
`auto_resource` requires LLM credentials.
Image captioning requires a vision-capable AgentScope model; HEIC also requires `reme-ai[image-heif]`.
## Consolidate and Use Proactive Topics