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/docvqa/skills/initial.md
+11
View File
@@ -0,0 +1,11 @@
# DocVQA Skill
## Visual Evidence Discipline
- Read the document carefully before answering.
- Prefer the smallest exact text span that answers the question.
- When several nearby strings look similar, choose the one whose surrounding labels or layout best match the question.
## Exact Answer Discipline
- Copy names, numbers, and dates exactly from the document whenever possible.
- Prefer direct extraction over paraphrase.
- Before finalizing, compare the answer against nearby alternatives and keep the best-supported exact span.