@lythos/skill-arena 0.12.0 → 0.13.0

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.
Files changed (2) hide show
  1. package/README.md +8 -8
  2. package/package.json +5 -5
package/README.md CHANGED
@@ -49,20 +49,20 @@ Note: Claude `-p` mode has known issues with web tools in Bun.spawn (deferred to
49
49
  ```bash
50
50
  bun add -d @lythos/skill-arena
51
51
  # or use directly
52
- bunx @lythos/skill-arena@0.12.0 <command>
52
+ bunx @lythos/skill-arena@0.13.0 <command>
53
53
  ```
54
54
 
55
55
  ## Quick Start
56
56
 
57
57
  ```bash
58
58
  # Single: test a deck with one agent
59
- bunx @lythos/skill-arena@0.12.0 single \
59
+ bunx @lythos/skill-arena@0.13.0 single \
60
60
  --deck https://raw.githubusercontent.com/lythos-labs/lythoskill/main/examples/decks/scout.toml \
61
61
  --brief "Generate auth flow diagram"
62
62
 
63
63
  # Vs: compare multiple decks side by side
64
64
  curl -fsSL https://raw.githubusercontent.com/lythos-labs/lythoskill/main/examples/arena/research-compare/arena.toml > arena.toml
65
- bunx @lythos/skill-arena@0.12.0 vs --config ./arena.toml
65
+ bunx @lythos/skill-arena@0.13.0 vs --config ./arena.toml
66
66
  ```
67
67
 
68
68
  ## Commands
@@ -71,23 +71,23 @@ bunx @lythos/skill-arena@0.12.0 vs --config ./arena.toml
71
71
 
72
72
  ```bash
73
73
  # Print execution plan without running
74
- bunx @lythos/skill-arena@0.12.0 vs --config arena.toml --dry-run
74
+ bunx @lythos/skill-arena@0.13.0 vs --config arena.toml --dry-run
75
75
 
76
76
  # Execute with per-side runs_per_side and statistical aggregation
77
- bunx @lythos/skill-arena@0.12.0 vs --config arena.toml
77
+ bunx @lythos/skill-arena@0.13.0 vs --config arena.toml
78
78
  ```
79
79
 
80
80
  ### Scaffold mode (legacy, manual execution)
81
81
 
82
82
  ```
83
- bunx @lythos/skill-arena@0.12.0 scaffold --task "Generate auth flow diagram" \
83
+ bunx @lythos/skill-arena@0.13.0 scaffold --task "Generate auth flow diagram" \
84
84
  --decks https://raw.githubusercontent.com/lythos-labs/lythoskill/main/examples/decks/scout.toml,https://raw.githubusercontent.com/lythos-labs/lythoskill/main/examples/decks/documents.toml
85
85
  ```
86
86
 
87
87
  ### Viz
88
88
 
89
89
  ```bash
90
- bunx @lythos/skill-arena@0.12.0 viz runs/arena-<id>/
90
+ bunx @lythos/skill-arena@0.13.0 viz runs/arena-<id>/
91
91
  ```
92
92
 
93
93
  ## Skill Documentation
@@ -101,7 +101,7 @@ The agent-visible **Skill** layer documentation is here:
101
101
  Part of the [lythoskill](https://github.com/lythos-labs/lythoskill) ecosystem — the thin-skill pattern separates heavy logic (this npm package) from lightweight agent instructions (SKILL.md).
102
102
 
103
103
  ```
104
- Starter (this package) → npm publish → bunx @lythos/skill-arena@0.12.0 ...
104
+ Starter (this package) → npm publish → bunx @lythos/skill-arena@0.13.0 ...
105
105
  Skill (packages/<name>/skill/) → build → SKILL.md + thin scripts
106
106
  Output (skills/<name>/) → git commit → agent-visible skill
107
107
  ```
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@lythos/skill-arena",
3
- "version": "0.12.0",
3
+ "version": "0.13.0",
4
4
  "description": "Skill Arena — benchmark skill effectiveness with controlled-variable comparison",
5
5
  "keywords": [
6
6
  "ai-agent",
@@ -42,13 +42,13 @@
42
42
  "bun": ">=1.0.0"
43
43
  },
44
44
  "dependencies": {
45
- "@lythos/cold-pool": "^0.12.0",
46
- "@lythos/infra": "^0.12.0",
47
- "@lythos/test-utils": "^0.12.0",
45
+ "@lythos/cold-pool": "^0.13.0",
46
+ "@lythos/infra": "^0.13.0",
47
+ "@lythos/test-utils": "^0.13.0",
48
48
  "zod": "^3.24.0",
49
49
  "zod-to-json-schema": "^3.25.2"
50
50
  },
51
51
  "optionalDependencies": {
52
- "@lythos/agent-adapter-claude-sdk": "^0.12.0"
52
+ "@lythos/agent-adapter-claude-sdk": "^0.13.0"
53
53
  }
54
54
  }