@vatio-ai/skills 1.3.0 → 1.4.0
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/.claude-plugin/plugin.json +1 -1
- package/README.md +7 -0
- package/package.json +1 -1
- package/skills/vatio-improve/SKILL.md +6 -2
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "vatio",
|
|
3
3
|
"description": "Build a Vatio agent from your coding agent, then fix what supervisors flag and prove it with evals.",
|
|
4
|
-
"version": "1.
|
|
4
|
+
"version": "1.4.0",
|
|
5
5
|
"author": { "name": "Vatio", "url": "https://vatio.ai" },
|
|
6
6
|
"homepage": "https://vatio.ai/docs",
|
|
7
7
|
"repository": "https://github.com/vatio-ai/skills",
|
package/README.md
CHANGED
|
@@ -23,6 +23,13 @@ It copies both skills into `.agents/skills/` (Codex, Cursor, Gemini CLI,
|
|
|
23
23
|
GitHub Copilot, OpenCode and others) and `.claude/skills/` (Claude Code). Run
|
|
24
24
|
it again to update them.
|
|
25
25
|
|
|
26
|
+
Or with the open [skills](https://skills.sh) CLI, which asks which agents you
|
|
27
|
+
use and installs for those:
|
|
28
|
+
|
|
29
|
+
```
|
|
30
|
+
npx skills add vatio-ai/skills
|
|
31
|
+
```
|
|
32
|
+
|
|
26
33
|
Or in Claude Code, as a plugin:
|
|
27
34
|
|
|
28
35
|
```
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@vatio-ai/skills",
|
|
3
|
-
"version": "1.
|
|
3
|
+
"version": "1.4.0",
|
|
4
4
|
"description": "Agent skills for building and improving a Vatio agent from your coding agent: Claude Code, Codex, Cursor, Gemini CLI, Copilot and any agent that reads SKILL.md",
|
|
5
5
|
"keywords": [
|
|
6
6
|
"vatio",
|
|
@@ -22,10 +22,14 @@ top. Follow those instructions; they take precedence over anything below.
|
|
|
22
22
|
In short:
|
|
23
23
|
|
|
24
24
|
1. Group the flags by cause, and fix each cause where it lives: `vatio.yml`,
|
|
25
|
-
a knowledge entry, a tool, or the backend a tool calls.
|
|
25
|
+
a knowledge entry, a tool, or the backend a tool calls. `vatio tools --env
|
|
26
|
+
live` shows each tool's error rate, timeouts and latency across every
|
|
27
|
+
conversation, and the calls that failed with what the backend answered: a
|
|
28
|
+
failing tool rarely gets flagged, because the agent apologizes and moves
|
|
29
|
+
on. Fix those too.
|
|
26
30
|
2. Work on a git branch. `vatio push` deploys it to the branch's own
|
|
27
31
|
environment, never to live.
|
|
28
|
-
3. Prove it with `vatio eval`: every flag is an eval case, replayed against
|
|
32
|
+
3. Prove it with `vatio eval`: every flag made on live, or before the first publish, is an eval case, replayed against
|
|
29
33
|
the branch and judged. The report counts the open flags apart from the
|
|
30
34
|
regression cases. A fix is done when its flags pass and nothing that
|
|
31
35
|
passed on live now fails.
|