Repository navigation
Raw python scripts in skills #114
Description
It is weird that skill.md contains lots of raw python code. Is it better to embed these python scripts into graphify package, maybe a cli subpackage?
e.g.
Replace NODE_A and NODE_B with the actual concept names from the user. Then explain the path in plain language - what each hop means, why it's significant.
After writing the explanation, save it back:
```python
$(cat .graphify_python) -c "
from graphify.ingest import save_query_result
from pathlib import Path
save_query_result(
question='Path from NODE_A to NODE_B',
answer='ANSWER',
memory_dir=Path('graphify-out/memory'),
query_type='path_query',
source_nodes=PATH_NODES, # list of node labels on the path
)
print('Path result saved to graphify-out/memory/')
"
```can be replaced with:
Replace NODE_A and NODE_B with the actual concept names from the user. Then explain the path in plain language - what each hop means, why it's significant.
After writing the explanation, save it back:
```python
$(cat .graphify_python) -m graphify.cli.ingest save_query_result NODE_A NODE_B
```which is much shorter for LLM to read.
Activity
safishamsi commentedon Apr 9, 2026
Fixed in v0.3.18. All six skill files have had the inline save_query_result Python blocks replaced with a single graphify save-result CLI call. The new graphify save-result subcommand handles saving Q&A results to the memory directory directly, so the skill files are shorter and easier to maintain.
biggates commentedon Apr 10, 2026
save-resultsolves that one problem, but there are still a lot of other raw python scripts in skills. are you going to do all of them? @safishamsiThe following is a full list of possible cli commands, summarized by gpt: