feat: Implement skill description improvement and evaluation scripts

Browse Source

- Added `improve_description.py` to enhance skill descriptions based on evaluation results using Claude.
- Introduced `run_eval.py` to assess whether skill descriptions trigger correctly for a set of queries.
- Created `run_loop.py` to combine evaluation and improvement in a loop, tracking history and optimizing descriptions iteratively.
- Developed `utils.py` for shared utility functions, including parsing SKILL.md files.
- Enhanced the overall workflow for skill description optimization, supporting train/test splits to prevent overfitting.

...

This commit is contained in:

Misaka Server

2026-03-25 15:04:20 +08:00

parent 1352f0875b

commit 81fd98b4fb

19 changed files with 5133 additions and 662 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

1325

skills/skill-creator/eval-viewer/viewer.html Normal file

File diff suppressed because it is too large Load Diff