@agent-native/core 0.66.6 → 0.66.8

package/dist/templates/workspace-core/.agents/skills/integration-webhooks/SKILL.md

@@ -213,6 +213,17 @@ The adapter is **only** responsible for:
 It does **not** know about the queue, the processor, retries, or the agent
 loop. Those are handled by the shared webhook handler.
 
+### Slack non-message events
+
+Slack's Events API also sends events that are not agent messages, such as
+`link_shared` for app unfurls. Do not map those into `IncomingMessage` unless
+they should actually run the agent. Handle them as short, provider-specific
+webhook work: verify the Slack signature, return `200 OK` quickly, and call the
+provider API needed for the event (`chat.unfurl` for link previews). If a single
+Slack app must handle both agent chat and app unfurls, put a dispatcher in front
+of the one Slack Events Request URL and route message events to the integration
+webhook flow while routing `link_shared` to the app-specific unfurl handler.
+
 ## Long-Running Agent Work
 
 The processor endpoint runs in a fresh function execution with its own full

package/docs/content/actions.md

@@ -56,6 +56,13 @@ export default defineAction({
 
 Run it from the same folder:
 
+```bash
+pnpm action hello '{"name":"Steve"}'
+```
+
+The CLI accepts a JSON object as the action input, which matches the structured
+tool calls agents already make. Simple flags still work for quick manual runs:
+
 ```bash
 pnpm action hello --name Steve
 ```
@@ -415,10 +422,12 @@ headless, render in chat, or grow into a full screen.
 Every action is runnable via `pnpm action`:
 
 ```bash
-pnpm action reply-to-email --emailId thread-123 --body "Thanks!"
+pnpm action reply-to-email '{"emailId":"thread-123","body":"Thanks!"}'
 ```
 
-Flags are parsed into the shape your schema expects. Useful for agent-dev loops, scripts, and cron.
+JSON input is the preferred shape for agents and complex objects. Flags are
+still parsed into the same schema shape for simple manual runs and existing
+scripts. Useful for agent-dev loops, scripts, and cron.
 
 ## Calling it from another agent (A2A) {#a2a}
 

package/docs/content/local-file-mode.md

@@ -91,6 +91,31 @@ without requiring you to clone or fork the entire Content app.
 small sandboxed widgets that can render in app slots while their source stays in
 the repo.
 
+## Install Content Into A Repo
+
+For an existing docs, blog, or MDX workspace, install the Content local-files
+skill:
+
+```bash
+npx @agent-native/core@latest skills add content --mode local-files --scope project
+```
+
+This copies the `content` skill into the repo's agent skill folders and writes
+or updates `agent-native.json` with Content defaults:
+
+- `mode: "local-files"` at the workspace level
+- `apps.content.mode: "local-files"`
+- content roots for `docs/`, `blog/`, `content/`, and `resources/`
+- `components/` for local MDX components
+- `extensions/` for local extension widgets
+
+The installed skill tells coding agents to use Content actions
+(`list-documents`, `get-document`, `edit-document`, `update-document`,
+`share-local-file-document`, and component-file actions) when a local Content app
+or Agent Native Desktop bridge exposes them. If no bridge is running, the skill
+falls back to safe direct repo edits while preserving frontmatter, imports, JSX,
+and unknown MDX.
+
 ## Configuration
 
 Add `agent-native.json` to the repo or workspace root:

package/docs/content/messaging.md

@@ -58,6 +58,30 @@ Connect your agent to Slack, email, Telegram, or WhatsApp so you can chat with i
 
 7. Send your bot a DM in Slack. It should reply.
 
+### Optional: app unfurls
+
+Slack app unfurls let an app replace Slack's normal link preview with a richer
+preview. Clips uses this for Loom-style playable video previews.
+
+Add these extra bot scopes when your app needs unfurls:
+
+- `links:read` — lets Slack notify the app when registered domains are posted
+- `links:write` — lets the app replace Slack's default preview
+- `links.embed:write` — lets the app embed approved media/player URLs
+
+Then subscribe to the `link_shared` event and register your public app domains
+under **App Unfurl Domains**. For Clips-only playable previews, set the Slack
+Event Subscriptions Request URL to:
+
+```text
+https://your-clips.example.com/api/slack/unfurl
+```
+
+A Slack app has one Events API Request URL. If the same Slack app should handle
+both agent chat events and Clips unfurls, route Slack events through a small
+dispatcher that sends message events to `/_agent-native/integrations/slack/webhook`
+and `link_shared` events to the Clips unfurl handler.
+
 ### Tips
 
 - **Channel mentions** — the bot only responds in channels when it's @-mentioned, to avoid noise.

package/docs/content/skills-guide.md

@@ -202,6 +202,9 @@ offline work, or privacy-sensitive use.
 npx @agent-native/core@latest skills add visual-plan
 npx @agent-native/core@latest skills add assets
 
+# Repo-first Content docs/blog/MDX editing.
+npx @agent-native/core@latest skills add content --mode local-files --scope project
+
 # Vercel/open Skills CLI: exported instructions only, no MCP config.
 npx skills@latest add BuilderIO/agent-native --skill assets
 

package/docs/content/template-clips.md

@@ -31,6 +31,8 @@ Think along the lines of Loom + Granola + Wispr Flow rolled into one app — but
 - **Get an auto-generated title, summary, and chapter markers** for every recording — the agent fills them in and keeps them current.
 - **Search across every transcript** — screen recordings, meetings, and dictations all in one library. "Find the clip where we discussed the rollout plan."
 - **Share clips** with per-clip permissions (public, team, private). Link tracking and threaded comments work too.
+- **Preview public clips in Slack** with a Loom-style playable unfurl after the
+  workspace installs your Clips Slack app.
 - **Paste Clips links into agents** so they can discover the agent-readable context: metadata, transcript segments, recommended frames, and timestamped frame images without receiving the raw video file.
 - **Smart library views.** Group by project, filter by speaker, auto-tag based on content.
 - **Edit the transcript through chat.** "Fix the mis-transcribed word at 1:42." "Pull three quotes for a blog post." The agent edits the transcript and the UI updates live.
@@ -53,6 +55,11 @@ Password-protected clips require the password once; successful responses return
 short-lived tokenized links so downstream agents do not need the plaintext
 password.
 
+Slack previews use the same sharing boundary. The `/api/slack/unfurl` webhook
+only returns a playable Slack `video` block for ready, public clips without a
+password, expiry hit, archive marker, or trash marker. Other clips still get the
+normal share-page title/thumbnail metadata and require opening Clips.
+
 ```an-api title="Agent context entry point"
 {
   "method": "GET",
@@ -137,6 +144,54 @@ Clips is a larger template with a native recorder (it ships a desktop companion
 1. **Video storage (required).** Connect a storage backend through the onboarding wizard. The easiest path is Builder.io (free during beta, one-click). For self-hosted storage, set `S3_ENDPOINT`, `S3_BUCKET`, `S3_ACCESS_KEY_ID`, `S3_SECRET_ACCESS_KEY`, and optionally `S3_REGION` and `S3_PUBLIC_BASE_URL`. Cloudflare R2 and DigitalOcean Spaces use the same env vars with the `R2_*` prefix.
 2. **Google Calendar (optional).** To sync upcoming meetings, connect a Google Calendar account from Settings. The OAuth callback URL in dev is `http://localhost:8094/_agent-native/google/callback`. Set up a Google OAuth client in [Google Cloud Console](https://console.cloud.google.com/) with the Gmail and Google Calendar APIs enabled.
 3. **Screen-capture permissions.** On macOS, grant Screen Recording permission to the browser (or the desktop companion app) in System Settings → Privacy & Security → Screen Recording.
+4. **Slack previews (optional).** Create a Slack app with `links:read`, `links:write`, and `links.embed:write`; subscribe to `link_shared`; add your Clips share domain under **App Unfurl Domains**; and set the Request URL to `https://your-clips.example.com/api/slack/unfurl`. Configure `SLACK_BOT_TOKEN` and `SLACK_SIGNING_SECRET` in the Clips deployment.
+
+### Host your own Clips server
+
+The hosted Clips app at [clips.agent-native.com](https://clips.agent-native.com)
+is just a deployed copy of the Clips template. To run your own server, scaffold
+the template, deploy it like any other agent-native app, then point the desktop
+tray app at your deployment.
+
+1. **Create the app.**
+
+   ```bash
+   npx @agent-native/core@latest create my-clips --standalone --template clips
+   cd my-clips
+   pnpm install
+   ```
+
+2. **Configure production state.** Set a persistent `DATABASE_URL`, the normal
+   production auth/secrets variables from [Deployment](/docs/deployment), and a
+   video storage provider. Builder.io Connect is the easiest storage path; for
+   self-hosted storage, use `S3_*` or `R2_*` variables for an S3-compatible
+   bucket.
+
+3. **Deploy the web app.** For a plain Node deploy:
+
+   ```bash
+   pnpm build
+   node .output/server/index.mjs
+   ```
+
+   You can also use any Nitro target from [Deployment](/docs/deployment), such
+   as Netlify, Vercel, Cloudflare Pages, AWS Lambda, or Deno Deploy. Make sure
+   `BETTER_AUTH_URL` is the public Clips origin, for example
+   `https://clips.example.com`.
+
+4. **Connect the desktop tray app.** Open Clips Desktop settings and set
+   **Clips server URL** to the public base URL of your deployment, for example
+   `https://clips.example.com`. If the app is mounted under a workspace path,
+   include that path, such as `https://example.com/clips`. Click **Connect**,
+   then sign in with an account on that Clips server.
+
+5. **Connect optional integrations.** Google Calendar powers the Meetings tab,
+   `GEMINI_API_KEY` or Builder.io Connect powers transcript cleanup and titles,
+   `GROQ_API_KEY` can provide speech-to-text fallback, and Slack credentials
+   enable playable Slack unfurls.
+
+For local development, run the web app with `pnpm dev` and point the desktop
+tray app at `http://localhost:8094`.
 
 ### Key features
 
@@ -148,6 +203,11 @@ Clips is a larger template with a native recorder (it ships a desktop companion
 
 **Agent-readable share links.** Public share links expose transcript and frame APIs so agents can understand recordings without ingesting raw video.
 
+**Slack playable unfurls.** Public share links can render a Slack `video` block
+that points at the existing `/embed/:id` player. This is a workspace Slack app
+install, not a global crawler behavior: normal Open Graph/Twitter metadata is
+the fallback when the app is not installed.
+
 ### Data model
 
 All data lives in SQL via Drizzle ORM. Schema: `templates/clips/server/db/schema.ts`. Recordings, meetings, dictations, calendar accounts, and vocabulary all carry the standard `ownableColumns` and have a matching framework shares table, so they slot into the per-user / per-org sharing model.

package/docs/content/template-content.md

@@ -90,6 +90,21 @@ SQL-backed sharing. See [Local File Mode](/docs/local-file-mode) for the
 standalone repo layout, configuration, custom MDX components, local
 `extensions/` widgets, and production safety guide.
 
+To install the Content local-files skill into an existing repo:
+
+```bash
+npx @agent-native/core@latest skills add content --mode local-files --scope project
+```
+
+The installer copies the `content` skill for your coding agent and writes or
+updates `agent-native.json` with Content roots for `docs/`, `blog/`, `content/`,
+and `resources/`. When a local Content app, Agent Native Desktop, or trusted
+local bridge is running, agents should use Content actions such as
+`list-documents`, `get-document`, `edit-document`, `update-document`, and
+`share-local-file-document` instead of raw filesystem writes. Without that local
+bridge, the installed skill still gives the agent the repo-editing contract for
+safe Markdown/MDX edits.
+
 ## For developers
 
 The rest of this doc is for anyone forking the Content template or extending it.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@agent-native/core",
-  "version": "0.66.6",
+  "version": "0.66.8",
   "type": "module",
   "engines": {
     "node": ">=22"

package/src/templates/headless/AGENTS.md

@@ -45,7 +45,7 @@ features. Prefer this app's own `AGENTS.md` for app-specific rules.
 Run actions from this app root:
 
 ```bash
-pnpm action hello --name Builder
+pnpm action hello '{"name":"Builder"}'
 ```
 
 Run the app-agent loop against those actions:

package/src/templates/headless/DEVELOPING.md

@@ -4,7 +4,7 @@ Install dependencies, then run the hello action:
 
 ```bash
 pnpm install
-pnpm action hello --name Builder
+pnpm action hello '{"name":"Builder"}'
 ```
 
 `actions/run.ts` is only the shared CLI dispatcher that powers

package/src/templates/workspace-core/.agents/skills/integration-webhooks/SKILL.md

@@ -213,6 +213,17 @@ The adapter is **only** responsible for:
 It does **not** know about the queue, the processor, retries, or the agent
 loop. Those are handled by the shared webhook handler.
 
+### Slack non-message events
+
+Slack's Events API also sends events that are not agent messages, such as
+`link_shared` for app unfurls. Do not map those into `IncomingMessage` unless
+they should actually run the agent. Handle them as short, provider-specific
+webhook work: verify the Slack signature, return `200 OK` quickly, and call the
+provider API needed for the event (`chat.unfurl` for link previews). If a single
+Slack app must handle both agent chat and app unfurls, put a dispatcher in front
+of the one Slack Events Request URL and route message events to the integration
+webhook flow while routing `link_shared` to the app-specific unfurl handler.
+
 ## Long-Running Agent Work
 
 The processor endpoint runs in a fresh function execution with its own full