jevgrep 0.2.0 → 0.3.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "jevgrep",
3
- "version": "0.2.0",
3
+ "version": "0.3.0",
4
4
  "description": "Semantic grep: describe the code you want in English, get file:line hits. Powered by TypeSafe Jev. No index, no embeddings, no dependencies.",
5
5
  "keywords": ["grep", "semantic-search", "code-search", "jev", "typesafe", "lint", "cli"],
6
6
  "license": "MIT",
package/skill/SKILL.md CHANGED
@@ -70,6 +70,15 @@ jgrep --diff --staged "changes behavior without a corresponding test change"
70
70
  jgrep --diff --staged "adds an endpoint or handler with no input validation"
71
71
  ```
72
72
 
73
+ ## Tables, not code
74
+
75
+ `jgrep --rows data.csv "<description>"` treats every row as a chunk and prints
76
+ matching rows. With `--questions q.json` (a JSON object of Jev questions:
77
+ `{name: {type: noul|choice|score, instructions, criteria?}}`) it writes the
78
+ table back with one answer column per question (`--out scored.csv` or
79
+ `--json`). Use it to label, triage or filter a list of records instead of
80
+ reading them one by one.
81
+
73
82
  ## Requirements
74
83
 
75
84
  Installed globally as `jgrep`; the key lives in `~/.config/jgrep/env`. If it