@vatio-ai/skills 1.13.0 → 1.14.0

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 (3) hide show
  1. package/.claude-plugin/plugin.json +1 -1
  2. package/package.json +1 -1
  3. package/skills/vatio-improve/SKILL.md +5 -2
package/.claude-plugin/plugin.json CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "name": "vatio",
3
3
  "description": "The Vatio plugin for Claude Code: build a conversational agent for your app with one prompt, then improve it daily with vatio-improve.",
4
- "version": "1.13.0",
4
+ "version": "1.14.0",
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/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@vatio-ai/skills",
3
- "version": "1.13.0",
3
+ "version": "1.14.0",
4
4
  "description": "The Vatio plugin for Claude Code: build a conversational agent for your app with one prompt, then improve it daily with vatio-improve.",
5
5
  "keywords": [
6
6
  "vatio",
package/skills/vatio-improve/SKILL.md CHANGED
@@ -29,6 +29,10 @@ In short:
29
29
  provider or Vatio failed and Vatio wrote the reply itself. Do not change
30
30
  the agent for those: tell the developer, who can remove the report, and
31
31
  if they keep happening, `vatio feedback`.
32
+ `vatio flags rm ID` removes a report and its test for everyone. It is the
33
+ developer's call: propose it (a report Vatio caused, one that asks for
34
+ something the agent must not do, one whose fix is in but the tests cannot
35
+ reproduce) and run it only when they say so.
32
36
  2. Group the reports by cause, and fix each cause where it lives:
33
37
  `vatio.yml`, a knowledge entry, a tool, or the developer's backend a tool
34
38
  calls. `vatio tools --env live` shows each tool's error rate, timeouts and
@@ -45,8 +49,7 @@ In short:
45
49
  comes with the `vatio chat show CHAT_ID` of its replay. Iterate (fix, push,
46
50
  test) until the reports pass and nothing that passes on live fails. A case
47
51
  marked "not tested (Vatio's side)" says nothing about your fix: run
48
- `vatio test --wait` again. Name reports by id (`F-7K2QX`). A CLI before
49
- 0.81.0 calls it `vatio eval`.
52
+ `vatio test --wait` again. Name reports by id (`F-7K2QX`).
50
53
  5. Show the developer what passes now, and `vatio publish` once they agree:
51
54
  it changes what visitors get. If it is refused, follow its message: it
52
55
  says what to run. Never pass `--force` unless the developer explicitly