It hardens a skill through judge-panel refinement rounds, it’s a quality gate that runs after authoring, not an authoring tool.
whattheheckheck 2 hours ago [-]
What if I want a way to open up a latent space prompt without having to type it all out everytime?
theowaway213456 5 hours ago [-]
TL;DR don't have your agent write skills using only its latent knowledge, otherwise you may as well not use a skill in the first place and let it summon that latent knowledge on the fly.
Not sure if this take is correct though. I suspect self-generated skills help the agent avoid having to "decompress" its latent knowledge, which might save tokens? idk, I am not an expert
solarkraft 36 minutes ago [-]
It seems so obvious: How would it know better than it already does?
Yet I’ve seen people succeed with „write me a prompt“ prompts. The model makes something up, often it makes sense.
They are like plans in that way: It’s not exactly novel knowledge, but it at least encodes it somewhere to make the process verifiable beforehand and a bit more repeatable.
I wouldn’t be surprised if it improves performance a little, just like thinking blocks do (every model reasons now).
bigcat12345678 4 hours ago [-]
I now have rules to not let agent write any docs or processes. Pretty much anything LLM auto-generated are of zero reuse value.
Eg. Ask the agent to write a skill then get it to prompt a subagent to use the skill, then iterate until it verifies the task was completed correctly
https://github.com/bjcoombs/ai-native-toolkit/blob/main/skil...
It hardens a skill through judge-panel refinement rounds, it’s a quality gate that runs after authoring, not an authoring tool.
Not sure if this take is correct though. I suspect self-generated skills help the agent avoid having to "decompress" its latent knowledge, which might save tokens? idk, I am not an expert
Yet I’ve seen people succeed with „write me a prompt“ prompts. The model makes something up, often it makes sense.
They are like plans in that way: It’s not exactly novel knowledge, but it at least encodes it somewhere to make the process verifiable beforehand and a bit more repeatable.
I wouldn’t be surprised if it improves performance a little, just like thinking blocks do (every model reasons now).