@alexanderzzlatkov/skilleval 0.1.0 → 0.1.1

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.
Files changed (2) hide show
  1. package/README.md +13 -1
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -15,6 +15,18 @@ OpenRouter is used for test prompt generation and evaluation judging, and as the
15
15
  - Use paid models instead (remove the `:free` suffix, e.g. `meta-llama/llama-3.3-70b-instruct`)
16
16
  - Provide your own test prompts with `--prompts` to skip the generator model entirely
17
17
 
18
+ ## Installation
19
+
20
+ ```bash
21
+ npm install -g @alexanderzzlatkov/skilleval
22
+ ```
23
+
24
+ Or use directly with `npx`:
25
+
26
+ ```bash
27
+ npx @alexanderzzlatkov/skilleval ./my-skill/SKILL.md
28
+ ```
29
+
18
30
  ## Quick Start
19
31
 
20
32
  ```bash
@@ -22,7 +34,7 @@ OpenRouter is used for test prompt generation and evaluation judging, and as the
22
34
  export OPENROUTER_API_KEY=sk-or-...
23
35
 
24
36
  # Evaluate a local skill
25
- npx skilleval ./my-skill/SKILL.md
37
+ npx @alexanderzzlatkov/skilleval ./my-skill/SKILL.md
26
38
 
27
39
  # Evaluate a skill from a GitHub repo (like skills.sh)
28
40
  npx skilleval owner/repo
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@alexanderzzlatkov/skilleval",
3
- "version": "0.1.0",
3
+ "version": "0.1.1",
4
4
  "description": "Evaluate how well AI models understand Agent Skills (SKILL.md files)",
5
5
  "keywords": [
6
6
  "ai",