Local RAG implementation for skills discovery when they grow past a certain limit

How to use GitHub

• Please use the 👍 reaction to show that you are interested into the same feature.
• Please don't comment if you have no relevant information to add. It's just extra noise for everyone subscribed to this issue.
• Subscribe to receive notifications on status change and new comments.

Feature request

Which Nextcloud Version are you currently using: 34.0.0

Is your feature request related to a problem? Please describe.
The skills' names and descriptions are extracted and put in the context of the model for the skills discovery by the model. For 20 skills, this could roughy take 5500 tokens, or 2750 tokens on average (see https://github.com/nextcloud/context_agent/issues/170#issuecomment-4945087989).
But skills have many uses from documentation for process automation to document writing adapted from a style, not to mention they are combined with the admin provided skills too. See https://github.com/nextcloud/context_agent/issues/170#issuecomment-4947934711

Describe the solution you'd like
One of the ideas could be to use local RAG to not inject everything but provide skill results to the model based on need.
The other would be to use subagents that will see all the skills (maybe could also be implemented for tools) and respond with the appropriate ones, which the main model can then call directly.

Describe alternatives you've considered

1. Limiting the no. of skills injected
2. Only injecting the skills names instead of names + short descriptions

Additional context
Skills PR: https://github.com/nextcloud/context_agent/pull/206
Discussion: https://github.com/nextcloud/context_agent/issues/170

Start with the skills implementation in pull request #206 and the related discussion in issue #170. Compare local RAG and subagent approaches, then clarify the design, integration points, and measurable criteria for reducing injected skill context before implementation begins.