@vatio-ai/skills 1.7.0 → 1.11.0

package/.claude-plugin/marketplace.json

@@ -5,7 +5,7 @@
     {
       "name": "vatio",
       "source": "./",
-      "description": "Build a Vatio agent from your coding agent, then fix what supervisors report and prove it with evals."
+      "description": "The Vatio plugin for Claude Code: build a conversational agent for your app with one prompt, then improve it daily with vatio-improve."
     }
   ]
 }

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "vatio",
-  "description": "Build a Vatio agent from your coding agent, then fix what supervisors report and prove it with evals.",
-  "version": "1.7.0",
+  "description": "The Vatio plugin for Claude Code: build a conversational agent for your app with one prompt, then improve it daily with vatio-improve.",
+  "version": "1.11.0",
   "author": { "name": "Vatio", "url": "https://vatio.ai" },
   "homepage": "https://vatio.ai/docs",
   "repository": "https://github.com/vatio-ai/skills",

package/README.md

@@ -1,43 +1,39 @@
-# Vatio skills
+# Vatio: the Claude Code plugin for your app’s agent
 
-Skills for the coding agent working on your [Vatio](https://vatio.ai) agent.
+Already have an app and users? Describe the conversational agent you want in
+Claude Code. `vatio-init` builds it from your project; [Vatio](https://vatio.ai)
+runs it with an inbox, human handoff and evaluation checks. You try the preview
+and approve publication.
+
+After launch, report mistakes in the inbox and make `/vatio:vatio-improve` your
+daily routine. Claude prepares fixes, Vatio tests the reported cases, and you
+approve the update. You do not need to write code yourself; you need access to
+your app’s project in Claude Code.
 
 | Skill | What it does |
 |---|---|
 | `vatio-init` | The first one in a project: looks at what is already there (a `vatio.yml` anywhere in the repository, the app's code) and recommends from it. With no agent yet, builds one: asks the owner what the code does not answer, writes `vatio.yml`, pushes it and hands over a link to try. With one, gets a developer who joined the project up to speed |
-| `vatio-improve` | Takes every reply your supervisors reported in the inbox in one session: reads `vatio flags`, fixes each cause, `vatio push`, proves it with `vatio eval` (in the background in Claude Code) and publishes with `vatio publish` |
+| `vatio-improve` | Takes every reply your supervisors reported in the inbox in one session: reads `vatio flags`, fixes each cause, `vatio push`, proves it with `vatio eval` (in the background in Claude Code) and publishes with `vatio publish` after your approval |
 | `vatio-share-session` | Sends the Claude Code session to the Vatio team when you ask it to, or offers to when the other two finish (send it, not now, or don't ask again), after showing you what goes (images left out, anything that looks like a secret redacted), with your feedback if you want to add some |
 
 The skills are short on purpose. They tell your coding agent when to reach for
 the Vatio CLI; the instructions themselves come from the platform when it runs
 `vatio docs` or `vatio flags`, so they are never out of date.
 
-## Install
-
-Any coding agent, from the root of your project:
-
-```
-npx @vatio-ai/skills
-```
-
-It copies the skills into `.agents/skills/` (Codex, Cursor, Gemini CLI,
-GitHub Copilot, OpenCode and others) and `.claude/skills/` (Claude Code). Run
-it again to update them.
-
-Or with the open [skills](https://skills.sh) CLI, which asks which agents you
-use and installs for those:
+## Install in Claude Code
 
-```
-npx skills add vatio-ai/skills
-```
+In your app’s project, run these commands one at a time and follow the
+installation panel:
 
-Or in Claude Code, as a plugin:
-
-```
+```text
 /plugin marketplace add vatio-ai/skills
 /plugin install vatio@vatio
 ```
 
+Then ask: “Use vatio-init to build a support agent for this app. Connect it to
+our existing users and features, define its permissions and human handoff,
+and give me a preview to try before publishing.”
+
 Claude Code does not update plugins from other people's marketplaces on its own:
 turn it on once in `/plugin` → **Marketplaces** → **vatio** → **Enable
 auto-update**, or run `claude plugin update vatio@vatio`.
@@ -63,3 +59,16 @@ Vatio, so a pull request cannot be merged here: open an issue describing the
 change instead.
 
 MIT licensed.
+
+## Other coding agents
+
+From the root of your project:
+
+```bash
+npx @vatio-ai/skills
+```
+
+This copies the skills into `.agents/skills/` and `.claude/skills/`.
+Run it again to update them. Any coding agent that reads those skills can
+follow the same procedures. You can also use `npx skills add vatio-ai/skills`
+with the [skills CLI](https://skills.sh).

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@vatio-ai/skills",
-  "version": "1.7.0",
-  "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",
+  "version": "1.11.0",
+  "description": "The Vatio plugin for Claude Code: build a conversational agent for your app with one prompt, then improve it daily with vatio-improve.",
   "keywords": [
     "vatio",
     "agent-skills",

package/skills/vatio-init/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: vatio-init
-description: The first Vatio skill in a project. Looks at what is already there — a vatio.yml anywhere in the repository, the workspace on the platform, the app's own code — and recommends from it, then either builds a customer-facing AI agent (for WhatsApp, Instagram, a website widget or an app) and gets it to the console's Test screen, or gets a developer who joined a project that already has one up to speed. Use when asked to create, set up, start or ship a Vatio agent, a chatbot or a support/sales assistant on Vatio, to get started on or onboard onto a project that uses Vatio, or when the user pastes the prompt from vatio.ai.
+description: The first Vatio skill in a project. Looks at what is already there — a vatio.yml anywhere in the repository, the workspace on the platform, the app's own code — and recommends from it, then either builds a customer-facing AI agent (for WhatsApp, Instagram, a website widget or an app) and gets it to the Test page in the Vatio inbox, or gets a developer who joined a project that already has one up to speed. Use when asked to create, set up, start or ship a Vatio agent, a chatbot or a support/sales assistant on Vatio, to get started on or onboard onto a project that uses Vatio, or when the user pastes the prompt from vatio.ai.
 ---
 
 # Start with Vatio in this project
@@ -45,8 +45,8 @@ you recommend, and ask them to confirm.
      `vatio.yml` (and `tools/` for their APIs).
   3. `vatio diff`, `vatio push`, then try it with `vatio chat`, including a
      conversation that should hand off.
-  4. Give them the link `vatio push` prints after `Try it:` (the console's
-     Test screen, with web chat, WhatsApp and Instagram) with what you
+  4. Give them the link `vatio push` prints after `Try it:` (the inbox's
+     Test page, with web chat, WhatsApp and Instagram) with what you
      tried. Publish with `vatio publish` only when they ask.
 - **A `vatio.yml`: the agent exists.** Never `vatio init` here: it writes a
   starter agent, and pushing that replaces the real one. Work from the
@@ -59,7 +59,7 @@ you recommend, and ask them to confirm.
   - open reports in `vatio flags`: work them with the `vatio-improve` skill;
   - tool calls failing in `vatio tools`: the fix is in the backend they call;
   - `workspace_forbidden`: they are not in the workspace yet, and the owner
-    invites them from **Team** in the console.
+    invites them from **Team** in the inbox.
 - **A workspace slug but no `vatio.yml`.** Ask for the repository it lives
   in: Vatio keeps what was deployed, not the files it came from. Do not
   `vatio init` one instead.

package/skills/vatio-share-session/SKILL.md

@@ -9,8 +9,10 @@ description: Send this coding session to the Vatio team, so they can see where b
 `vatio share-session` sends the Claude Code session you are running in: what
 the user asked, what you read and ran, and what came back. It leaves out
 images, replaces anything that looks like a key, token or password with
-`[REDACTED]`, and the home directory with `~`. Only the Vatio team reads it,
-to see where Vatio got in the way and fix it.
+`[REDACTED]`, email addresses and international phone numbers with `[EMAIL]`
+and `[PHONE]`, and the home directory with `~`. Only the Vatio team reads it,
+to see where Vatio got in the way and fix it; every read is logged, and it is
+deleted 30 days after it arrives (sooner on request to dpo@vatio.ai).
 
 It is sent in one of two ways: the user asked for it, or you offer it because
 `vatio-init` or `vatio-improve` just finished.
@@ -31,7 +33,9 @@ It is sent in one of two ways: the user asked for it, or you offer it because
    ```
 
    Tell them which session it is (the summary it prints), that it is the
-   whole conversation, and that the file is there if they want to read it.
+   whole conversation, what was hidden, how it is treated (only the Vatio
+   team reads it, every read is logged, deleted after 30 days), and that the
+   file is there if they want to read it.
 
 3. Ask whether to send it, once. It is their conversation: never send it on
    your own, even when the task seems to call for it.
@@ -42,7 +46,8 @@ It is sent in one of two ways: the user asked for it, or you offer it because
    to the Vatio team, so they can see where Vatio got in the way and improve
    it?", with these options:
 
-   - **Send it** — "The whole conversation, as shown above."
+   - **Send it** — "The whole conversation, as shown above. Only the Vatio
+     team reads it, and it is deleted after 30 days."
    - **Send it with a comment** — "You say what got in the way, what you
      expected, or anything else for the team."
    - **Not now** — "It won't be offered again for a week."
@@ -78,6 +83,20 @@ It is sent in one of two ways: the user asked for it, or you offer it because
    give them the link it prints). Tell them it was sent and the number it
    printed.
 
+5. If a permission check refuses the command (Claude Code's auto mode can
+   treat it as sending data out), do not retry it or look for another way to
+   send it. Give the user the command to run in their own terminal, with the
+   session id from the summary, and their feedback in quotes at the end if
+   they gave some:
+
+   ```bash
+   npx @vatio-ai/cli@latest share-session --id SESSION_ID --yes
+   ```
+
+   When they say they ran it, check instead of asking:
+   `npx @vatio-ai/cli@latest share-session --list` marks a session that was
+   sent with `(sent #N, when)`. If it is not marked, it did not go.
+
 Only Claude Code sessions can be sent. In any other coding agent, do not offer
 it; when the user asks, write what happened instead:
 `npx @vatio-ai/cli@latest feedback "…"`.