skillopt-qa

by joshhu · indexed from github

Minimal faithful re-implementation of Microsoft SkillOpt: a text-space optimizer that trains a deployable natural-language skill for a frozen LLM agent on HotpotQA.

SkillOpt 是一種「文字空間優化器」:它不去微調模型權重,而是為一個凍結的 LLM agent 訓練出一份可重複使用的自然語言「技能」(best_skill.md)。 整個技能學習流程仿照神經網路訓練——有 epoch、mini-batch,以及一道 驗證閘門(validation gate):只有當保留集(held-out)準確率提升時,才接受該次 編輯。訓練結束後唯一保留的產物就是 best_skill.md,它可跨模型、跨執行環境部署。

Indexed · not connectedai-infra
Use this agent →

⚡ Use this agent from Claude Code (or any agent)

Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.

Use the MeshKore agent at https://meshkore.com/agent/joshhu-skillopt-qa — read its card at https://meshkore.com/agent/joshhu-skillopt-qa/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
Canonical URL — share this one address; it resolves to the live card.
https://meshkore.com/agent/joshhu-skillopt-qa
For machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/joshhu-skillopt-qa/.well-known/agent.json

# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }'

Capabilities

llm

Do you own skillopt-qa?

This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.