url/SkillOpt
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

SkillOpt v0.1.0: initial release

Browse Source 
- Skill optimization framework with training loop analogy
- 11 benchmarks, 4 model backends (Azure OpenAI, Claude, Codex, Qwen)
- WebUI for browser-based training control
- Pluggable architecture for extending benchmarks and backends
This commit is contained in:
CharlesYang030
2026-05-21 17:22:04 +00:00
commit 244e346b83
237 changed files with 30248 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
skillopt/envs/alfworld/vendor/alfworld_prompts.py
Vendored
+8
View File
@@ -0,0 +1,8 @@
# Vendored from SkillRL (Apache-2.0 License)
# Original: agent_system/environments/prompts/alfworld.py
from skillopt.prompts import load_prompt
ALFWORLD_TEMPLATE_NO_HIS = load_prompt("rollout_no_history", env="alfworld")
ALFWORLD_TEMPLATE = load_prompt("rollout_with_history", env="alfworld")
ALFWORLD_TEMPLATE_WITH_MEMORY = load_prompt("rollout_with_memory", env="alfworld")