skill-harness 0.1.1 → 0.1.2
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/README.md +1 -1
- package/package.json +2 -2
package/README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# skill-harness
|
|
2
2
|
|
|
3
|
-
A portable **test / optimize loop for agent skills**, driven from [pi](https://
|
|
3
|
+
A portable **test / optimize loop for agent skills**, driven from [pi](https://pi.dev).
|
|
4
4
|
Point it at a repo of skills, and for any skill with a `tests/specification.yaml`
|
|
5
5
|
spec it will run each scenario, LLM-judge the transcript, score it against a ship
|
|
6
6
|
bar, and open an interactive review UI so you can measure a `SKILL.md` edit.
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "skill-harness",
|
|
3
|
-
"version": "0.1.
|
|
3
|
+
"version": "0.1.2",
|
|
4
4
|
"description": "Test/optimize loop for agent skills — run spec'd scenarios on pi, LLM-judge, score, review, re-run",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"keywords": ["agent-skills", "skill", "llm", "testing", "eval", "grading", "pi", "ci", "harness"],
|
|
@@ -13,7 +13,7 @@
|
|
|
13
13
|
"README.md"
|
|
14
14
|
],
|
|
15
15
|
"dependencies": {
|
|
16
|
-
"@skill-harness/cli": "0.1.
|
|
16
|
+
"@skill-harness/cli": "0.1.2"
|
|
17
17
|
},
|
|
18
18
|
"repository": {
|
|
19
19
|
"type": "git",
|