@vellumai/assistant 0.4.56 → 0.5.0

package/src/config/bundled-skills/schedule/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: schedule
-description: Recurring and one-shot scheduling — cron, RRULE, or single fire-at time
+description: Recurring and one-shot scheduling - cron, RRULE, or single fire-at time
 compatibility: "Designed for Vellum personal assistants"
 metadata:
   emoji: "📅"
@@ -26,10 +26,10 @@ Standard 5-field cron syntax: `minute hour day-of-month month day-of-week`
 
 Examples:
 
-- `0 9 * * 1-5` — weekdays at 9:00 AM
-- `30 8 * * *` — every day at 8:30 AM
-- `0 */2 * * *` — every 2 hours
-- `0 9 1 * *` — first of every month at 9:00 AM
+- `0 9 * * 1-5` - weekdays at 9:00 AM
+- `30 8 * * *` - every day at 8:30 AM
+- `0 */2 * * *` - every 2 hours
+- `0 9 1 * *` - first of every month at 9:00 AM
 
 ### RRULE (RFC 5545)
 
@@ -49,25 +49,25 @@ Exclusions (EXDATE, EXRULE) always take precedence over inclusions (RRULE, RDATE
 
 #### Basic examples
 
-- `DTSTART:20250101T090000Z\nRRULE:FREQ=DAILY` — every day at 9:00 AM UTC
-- `DTSTART:20250101T090000Z\nRRULE:FREQ=WEEKLY;BYDAY=MO,WE,FR` — Mon/Wed/Fri at 9:00 AM UTC
-- `DTSTART:20250101T090000Z\nRRULE:FREQ=MONTHLY;BYMONTHDAY=1,15` — 1st and 15th of each month
+- `DTSTART:20250101T090000Z\nRRULE:FREQ=DAILY` - every day at 9:00 AM UTC
+- `DTSTART:20250101T090000Z\nRRULE:FREQ=WEEKLY;BYDAY=MO,WE,FR` - Mon/Wed/Fri at 9:00 AM UTC
+- `DTSTART:20250101T090000Z\nRRULE:FREQ=MONTHLY;BYMONTHDAY=1,15` - 1st and 15th of each month
 
 #### Bounded recurrence
 
-- `DTSTART:20250101T090000Z\nRRULE:FREQ=DAILY;COUNT=30` — daily for 30 occurrences then stop
-- `DTSTART:20250101T090000Z\nRRULE:FREQ=WEEKLY;BYDAY=MO;UNTIL=20250331T235959Z` — every Monday until end of March
+- `DTSTART:20250101T090000Z\nRRULE:FREQ=DAILY;COUNT=30` - daily for 30 occurrences then stop
+- `DTSTART:20250101T090000Z\nRRULE:FREQ=WEEKLY;BYDAY=MO;UNTIL=20250331T235959Z` - every Monday until end of March
 
 #### Set construct examples
 
-- `DTSTART:20250101T090000Z\nRRULE:FREQ=WEEKLY;BYDAY=MO,WE,FR\nEXDATE:20250120T090000Z` — Mon/Wed/Fri except Jan 20
-- `DTSTART:20250101T090000Z\nRRULE:FREQ=DAILY\nEXRULE:FREQ=WEEKLY;BYDAY=SA,SU` — every weekday (daily minus weekends)
-- `DTSTART:20250101T090000Z\nRRULE:FREQ=MONTHLY;BYMONTHDAY=1\nRDATE:20250704T090000Z` — 1st of each month plus July 4th
-- `DTSTART:20250101T090000Z\nRRULE:FREQ=WEEKLY;BYDAY=TU\nRRULE:FREQ=WEEKLY;BYDAY=TH` — union of Tuesdays and Thursdays
+- `DTSTART:20250101T090000Z\nRRULE:FREQ=WEEKLY;BYDAY=MO,WE,FR\nEXDATE:20250120T090000Z` - Mon/Wed/Fri except Jan 20
+- `DTSTART:20250101T090000Z\nRRULE:FREQ=DAILY\nEXRULE:FREQ=WEEKLY;BYDAY=SA,SU` - every weekday (daily minus weekends)
+- `DTSTART:20250101T090000Z\nRRULE:FREQ=MONTHLY;BYMONTHDAY=1\nRDATE:20250704T090000Z` - 1st of each month plus July 4th
+- `DTSTART:20250101T090000Z\nRRULE:FREQ=WEEKLY;BYDAY=TU\nRRULE:FREQ=WEEKLY;BYDAY=TH` - union of Tuesdays and Thursdays
 
 ## One-Shot Schedules (Reminders)
 
-To create a one-time schedule that fires once and is done, pass `fire_at` (an ISO 8601 timestamp) instead of an `expression`. This replaces the old reminder concept — "remind me at 3pm" becomes a one-shot schedule with `fire_at`.
+To create a one-time schedule that fires once and is done, pass `fire_at` (an ISO 8601 timestamp) instead of an `expression`. This replaces the old reminder concept - "remind me at 3pm" becomes a one-shot schedule with `fire_at`.
 
 One-shot schedules:
 - Fire once at the specified time, then are marked as `fired` and disabled.
@@ -82,8 +82,8 @@ Examples:
 
 The `mode` parameter controls what happens when a schedule fires:
 
-- **execute** (default) — sends the schedule's message to a background assistant conversation for autonomous handling. The assistant processes the message as if the user sent it.
-- **notify** — sends a notification to the user via the notification pipeline. No assistant processing occurs.
+- **execute** (default) - sends the schedule's message to a background assistant conversation for autonomous handling. The assistant processes the message as if the user sent it.
+- **notify** - sends a notification to the user via the notification pipeline. No assistant processing occurs.
 
 Use `notify` for simple reminders ("remind me to take medicine at 9am") and `execute` for tasks that need assistant action ("check my calendar at 8am and send me a digest").
 
@@ -91,9 +91,9 @@ Use `notify` for simple reminders ("remind me to take medicine at 9am") and `exe
 
 Control how notify-mode schedules are delivered at trigger time with `routing_intent`:
 
-- **single_channel** — deliver to one best channel
-- **multi_channel** — deliver to a subset of channels
-- **all_channels** (default) — deliver to every available channel
+- **single_channel** - deliver to one best channel
+- **multi_channel** - deliver to a subset of channels
+- **all_channels** (default) - deliver to every available channel
 
 Optionally pass `routing_hints` (a JSON object) to influence routing decisions (e.g. preferred channels, exclusions).
 
@@ -101,7 +101,7 @@ Optionally pass `routing_hints` (a JSON object) to influence routing decisions (
 
 - **Default to `all_channels`** for most notifications. Users usually want to be notified wherever they are.
 - **Use `single_channel`** only when the user explicitly specifies a single channel (e.g. "remind me on Telegram").
-- **Check `user_message_channel`** from the turn context. If the user is currently active on a specific channel, include it as a routing hint:
+- **Check `user_message_channel` (or `channel` when all channels are the same)** from the turn context. If the user is currently active on a specific channel, include it as a routing hint:
   ```
   routing_hints: { preferred_channels: ["vellum"] }
   routing_intent: "all_channels"
@@ -129,20 +129,20 @@ Phrases like "at the 45 minute mark", "at the top of the hour", "at noon", or "2
 
 **Resolution rules (in priority order):**
 
-1. **Conversation-anchored expressions** — if the user mentioned a start time earlier in conversation ("I got here at 9", "meeting started at 2:10"), interpret offset-style phrases ("the 45 minute mark", "20 minutes in") as `start_time + offset`.
+1. **Conversation-anchored expressions** - if the user mentioned a start time earlier in conversation ("I got here at 9", "meeting started at 2:10"), interpret offset-style phrases ("the 45 minute mark", "20 minutes in") as `start_time + offset`.
 
-2. **Clock-position expressions** — when no start time is in context, map directly to a wall-clock time:
+2. **Clock-position expressions** - when no start time is in context, map directly to a wall-clock time:
    - "top of the hour" → next :00
    - "the X minute mark" → current hour's :XX; if already past, advance one hour
    - "noon" / "midnight" → 12:00 PM or 12:00 AM today; if past, tomorrow
 
-3. **Ask only if truly ambiguous** — if neither rule resolves, ask for clarification. Never silently default to "from now."
+3. **Ask only if truly ambiguous** - if neither rule resolves, ask for clarification. Never silently default to "from now."
 - Timezones default to the system timezone if omitted. Use IANA timezone identifiers (e.g. "America/Los_Angeles").
 - Prefer RRULE for complex patterns that cron cannot express (e.g. "every other Tuesday", "last weekday of the month").
 
 ## Capability Preflight
 
-Before confirming a schedule to the user, you MUST verify that you have the capabilities needed to execute the scheduled message autonomously. Scheduled messages run without user interaction — if a required integration is missing, the schedule will fail silently.
+Before confirming a schedule to the user, you MUST verify that you have the capabilities needed to execute the scheduled message autonomously. Scheduled messages run without user interaction - if a required integration is missing, the schedule will fail silently.
 
 When `schedule_create` returns, it includes an integration status summary. Cross-reference the scheduled task's requirements against the available integrations:
 
@@ -153,7 +153,7 @@ When `schedule_create` returns, it includes an integration status summary. Cross
 
 If any required capability is missing:
 
-1. **Do NOT tell the user the schedule is ready** — instead, explain what's missing and why the schedule won't work yet
+1. **Do NOT tell the user the schedule is ready** - instead, explain what's missing and why the schedule won't work yet
 2. Offer to help set up the missing integration first
 3. The schedule is still created (so timing is preserved), but make it clear it won't execute successfully until dependencies are resolved
 

package/src/config/bundled-skills/schedule/TOOLS.json

@@ -3,7 +3,7 @@
   "tools": [
     {
       "name": "schedule_create",
-      "description": "Create a scheduled automation. For recurring: provide expression (cron/RRULE). For one-time: provide fire_at (ISO 8601 timestamp). ONLY use this when the user explicitly wants something to run on a schedule (e.g. \"every day at 9am\", \"remind me tomorrow at 3pm\", \"weekly on Mondays\"). Do NOT use this for \"add to my tasks\" or \"add to my queue\" — use task_list_add for those requests instead.",
+      "description": "Create a scheduled automation. For recurring: provide expression (cron/RRULE). For one-time: provide fire_at (ISO 8601 timestamp). ONLY use this when the user explicitly wants something to run on a schedule (e.g. \"every day at 9am\", \"remind me tomorrow at 3pm\", \"weekly on Mondays\"). Do NOT use this for \"add to my tasks\" or \"add to my queue\" - use task_list_add for those requests instead.",
       "category": "schedule",
       "risk": "medium",
       "input_schema": {
@@ -52,7 +52,7 @@
             "type": "object",
             "description": "Additional routing metadata (e.g. preferred channel identifiers)"
           },
-          "reason": {
+          "activity": {
             "type": "string",
             "description": "Brief non-technical explanation of why this tool is being called"
           }
@@ -78,7 +78,7 @@
             "type": "string",
             "description": "If provided, show detailed info and recent runs for this specific job."
           },
-          "reason": {
+          "activity": {
             "type": "string",
             "description": "Brief non-technical explanation of why this tool is being called"
           }
@@ -139,7 +139,7 @@
             "type": "object",
             "description": "Additional routing metadata (e.g. preferred channel identifiers)"
           },
-          "reason": {
+          "activity": {
             "type": "string",
             "description": "Brief non-technical explanation of why this tool is being called"
           }
@@ -161,7 +161,7 @@
             "type": "string",
             "description": "The ID of the schedule to delete"
           },
-          "reason": {
+          "activity": {
             "type": "string",
             "description": "Brief non-technical explanation of why this tool is being called"
           }

package/src/config/bundled-skills/screen-watch/SKILL.md

@@ -16,9 +16,9 @@ Use `start_screen_watch` when the user wants you to monitor what's happening on
 
 ## Parameters
 
-- **focus_area** (required) — What to focus on observing
-- **duration_minutes** — How long to watch in minutes (1-15, default 5)
-- **interval_seconds** — Seconds between screen captures (5-30, default 10)
+- **focus_area** (required) - What to focus on observing
+- **duration_minutes** - How long to watch in minutes (1-15, default 5)
+- **interval_seconds** - Seconds between screen captures (5-30, default 10)
 
 ## Constraints
 

package/src/config/bundled-skills/screen-watch/TOOLS.json

@@ -21,7 +21,7 @@
             "type": "string",
             "description": "What to focus on observing"
           },
-          "reason": {
+          "activity": {
             "type": "string",
             "description": "Brief non-technical explanation of what you are watching and why, shown to the user as a status update. Use simple language a non-technical person would understand."
           }

package/src/config/bundled-skills/sequences/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: sequences
-description: Create and manage automated email drip sequences with enrollment, scheduling, and analytics
+description: Create and manage automated email drip sequences
 compatibility: "Designed for Vellum personal assistants"
 metadata:
   emoji: "📧"
@@ -34,7 +34,7 @@ You are an email sequence assistant. Use the sequence tools to help users create
 
 ### Analytics
 
-- **Dashboard**: View aggregate metrics across all sequences — total sends, reply rates, completion rates
+- **Dashboard**: View aggregate metrics across all sequences - total sends, reply rates, completion rates
 - **Step Funnel**: Drill into a specific sequence to see per-step send counts, reach, and drop-off
 
 ## Usage Notes

package/src/config/bundled-skills/sequences/TOOLS.json

@@ -55,7 +55,7 @@
             "type": "boolean",
             "description": "Whether to stop the sequence when the contact replies (default true)"
           },
-          "reason": {
+          "activity": {
             "type": "string",
             "description": "Brief non-technical explanation of why this tool is being called"
           }
@@ -78,7 +78,7 @@
             "enum": ["active", "paused", "archived"],
             "description": "Filter by sequence status"
           },
-          "reason": {
+          "activity": {
             "type": "string",
             "description": "Brief non-technical explanation of why this tool is being called"
           }
@@ -99,7 +99,7 @@
             "type": "string",
             "description": "Sequence ID"
           },
-          "reason": {
+          "activity": {
             "type": "string",
             "description": "Brief non-technical explanation of why this tool is being called"
           }
@@ -111,7 +111,7 @@
     },
     {
       "name": "sequence_update",
-      "description": "Update a sequence or manage an enrollment's lifecycle. Two modes: (1) Sequence-level — pass `id` to change name, description, status (active/paused/archived), steps, or exit-on-reply. (2) Enrollment-level — pass `enrollment_id` + `enrollment_action` to pause, resume, or cancel an enrollment. Exactly one mode must be used per call.",
+      "description": "Update a sequence or manage an enrollment's lifecycle. Two modes: (1) Sequence-level - pass `id` to change name, description, status (active/paused/archived), steps, or exit-on-reply. (2) Enrollment-level - pass `enrollment_id` + `enrollment_action` to pause, resume, or cancel an enrollment. Exactly one mode must be used per call.",
       "category": "sequences",
       "risk": "medium",
       "input_schema": {
@@ -177,7 +177,7 @@
             },
             "description": "Replacement steps (replaces all existing steps)"
           },
-          "reason": {
+          "activity": {
             "type": "string",
             "description": "Brief non-technical explanation of why this tool is being called"
           }
@@ -202,7 +202,7 @@
             "type": "string",
             "description": "Sequence ID to delete"
           },
-          "reason": {
+          "activity": {
             "type": "string",
             "description": "Brief non-technical explanation of why this tool is being called"
           }
@@ -242,7 +242,7 @@
             "type": "object",
             "description": "Optional context object with personalization variables for the enrolled contacts"
           },
-          "reason": {
+          "activity": {
             "type": "string",
             "description": "Brief non-technical explanation of why this tool is being called"
           }
@@ -276,7 +276,7 @@
             ],
             "description": "Filter by enrollment status"
           },
-          "reason": {
+          "activity": {
             "type": "string",
             "description": "Brief non-technical explanation of why this tool is being called"
           }
@@ -305,7 +305,7 @@
             "type": "boolean",
             "description": "Set to true to enroll contacts (default false = preview mode)"
           },
-          "reason": {
+          "activity": {
             "type": "string",
             "description": "Brief non-technical explanation of why this tool is being called"
           }
@@ -327,7 +327,7 @@
             "type": "string",
             "description": "Optional sequence ID for detailed step funnel view"
           },
-          "reason": {
+          "activity": {
             "type": "string",
             "description": "Brief non-technical explanation of why this tool is being called"
           }

package/src/config/bundled-skills/sequences/tools/sequence-analytics.ts

@@ -72,7 +72,7 @@ export async function run(
           ),
         );
         lines.push(
-          `  Step ${s.stepIndex + 1}: "${s.subject}" — ${s.sends} sends, ${
+          `  Step ${s.stepIndex + 1}: "${s.subject}" - ${s.sends} sends, ${
             s.enrollmentsReached
           } reached, ${(s.dropOff * 100).toFixed(0)}% drop-off`,
         );
@@ -89,7 +89,7 @@ export async function run(
       const time = new Date(e.createdAt).toISOString();
       const step = e.stepIndex !== undefined ? ` step ${e.stepIndex + 1}` : "";
       lines.push(
-        `  [${time}] ${e.eventType}${step} — enrollment ${e.enrollmentId.slice(
+        `  [${time}] ${e.eventType}${step} - enrollment ${e.enrollmentId.slice(
           0,
           8,
         )}...`,

package/src/config/bundled-skills/sequences/tools/sequence-enroll.ts

@@ -39,11 +39,11 @@ export async function run(
           contactEmail: email,
           context,
         });
-        results.push(`  ${email} — enrolled (ID: ${enrollment.id})`);
+        results.push(`  ${email} - enrolled (ID: ${enrollment.id})`);
         successCount++;
       } catch (e) {
         results.push(
-          `  ${email} — failed: ${e instanceof Error ? e.message : String(e)}`,
+          `  ${email} - failed: ${e instanceof Error ? e.message : String(e)}`,
         );
       }
     }

package/src/config/bundled-skills/sequences/tools/sequence-enrollment-list.ts

@@ -21,7 +21,7 @@ export async function run(
       const nextAt = e.nextStepAt
         ? new Date(e.nextStepAt).toISOString()
         : "n/a";
-      return `- ${e.contactEmail} (ID: ${e.id}) — step ${e.currentStep}, status: ${e.status}, next: ${nextAt}`;
+      return `- ${e.contactEmail} (ID: ${e.id}) - step ${e.currentStep}, status: ${e.status}, next: ${nextAt}`;
     });
     return ok(`${enrollments.length} enrollment(s):\n${lines.join("\n")}`);
   } catch (e) {

package/src/config/bundled-skills/sequences/tools/sequence-get.ts

@@ -41,7 +41,7 @@ export async function run(
       `Steps (${seq.steps.length}):`,
       ...seq.steps.map(
         (s) =>
-          `  ${s.index + 1}. "${s.subjectTemplate}" — delay: ${
+          `  ${s.index + 1}. "${s.subjectTemplate}" - delay: ${
             s.delaySeconds
           }s${s.requireApproval ? " [approval required]" : ""}`,
       ),

package/src/config/bundled-skills/sequences/tools/sequence-import.ts

@@ -31,7 +31,7 @@ export async function run(
       );
     }
 
-    // Preview mode (default) — show what would happen
+    // Preview mode (default) - show what would happen
     if (!autoEnroll) {
       const lines = [
         `Parsed ${parsed.contacts.length} valid contact(s) from file.`,
@@ -72,7 +72,7 @@ export async function run(
       lines.push("");
       lines.push("Skipped:");
       for (const s of result.skipped.slice(0, 10)) {
-        lines.push(`  ${s.email} — ${s.reason}`);
+        lines.push(`  ${s.email} - ${s.reason}`);
       }
     }
 
@@ -80,7 +80,7 @@ export async function run(
       lines.push("");
       lines.push("Failed:");
       for (const f of result.failed.slice(0, 10)) {
-        lines.push(`  ${f.email} — ${f.reason}`);
+        lines.push(`  ${f.email} - ${f.reason}`);
       }
     }
 

package/src/config/bundled-skills/sequences/tools/sequence-list.ts

@@ -21,7 +21,7 @@ export async function run(
 
     const lines = seqs.map((s) => {
       const enrollments = countActiveEnrollments(s.id);
-      return `- ${s.name} (ID: ${s.id}) — ${s.status}, ${s.steps.length} steps, ${enrollments} active enrollments, channel: ${s.channel}`;
+      return `- ${s.name} (ID: ${s.id}) - ${s.status}, ${s.steps.length} steps, ${enrollments} active enrollments, channel: ${s.channel}`;
     });
     return ok(`${seqs.length} sequence(s):\n${lines.join("\n")}`);
   } catch (e) {

package/src/config/bundled-skills/sequences/tools/sequence-update.ts

@@ -58,7 +58,7 @@ export async function run(
             : null;
           if (seq && seq.status !== "active")
             return err(
-              `Cannot resume enrollment — parent sequence "${seq.name}" is ${seq.status}. Resume the sequence first.`,
+              `Cannot resume enrollment - parent sequence "${seq.name}" is ${seq.status}. Resume the sequence first.`,
             );
           resumeEnrollment(enrollmentId);
           return ok(`Enrollment ${enrollmentId} resumed.`);

package/src/config/bundled-skills/settings/TOOLS.json

@@ -17,7 +17,7 @@
           "value": {
             "description": "The new value for the setting (type depends on setting)"
           },
-          "reason": {
+          "activity": {
             "type": "string",
             "description": "Brief non-technical explanation of what you are changing and why, shown to the user as a status update. Use simple language a non-technical person would understand."
           }
@@ -39,7 +39,7 @@
             "enum": ["microphone", "speech_recognition"],
             "description": "The System Settings pane to open"
           },
-          "reason": {
+          "activity": {
             "type": "string",
             "description": "Brief non-technical explanation of what you are opening and why, shown to the user as a status update. Use simple language a non-technical person would understand."
           }
@@ -70,7 +70,7 @@
             ],
             "description": "The settings tab to navigate to"
           },
-          "reason": {
+          "activity": {
             "type": "string",
             "description": "Brief non-technical explanation of what you are navigating to and why, shown to the user as a status update. Use simple language a non-technical person would understand."
           }

package/src/config/bundled-skills/settings/tools/open-system-settings.ts

@@ -36,7 +36,7 @@ export async function run(
 
   const meta = PANES[pane as PaneName];
 
-  // Send open_url to the client — the x-apple.systempreferences: scheme
+  // Send open_url to the client - the x-apple.systempreferences: scheme
   // opens System Settings directly without a browser confirmation dialog.
   if (context.sendToClient) {
     context.sendToClient({

package/src/config/bundled-skills/skill-management/TOOLS.json

@@ -3,7 +3,7 @@
   "tools": [
     {
       "name": "scaffold_managed_skill",
-      "description": "Create or update a managed skill in ~/.vellum/workspace/skills. The skill becomes available for skill_load immediately.",
+      "description": "Create or update a managed skill in ~/.vellum/workspace/skills. The skill becomes available for skill_load immediately. Never persist a skill without explicit user consent. Before persisting, test the snippet: write to a temp file with bash and run with `bun run /tmp/vellum-eval/snippet.ts`. Iterate up to 3 attempts, then ask the user. Clean up temp files after. Do not use file_write for temp files outside the working directory. After a skill is written, the next turn may run in a recreated session due to file-watcher eviction - continue normally.",
       "category": "skills",
       "risk": "high",
       "input_schema": {
@@ -23,7 +23,7 @@
           },
           "body_markdown": {
             "type": "string",
-            "description": "The full skill body in markdown — instructions, prompts, templates, etc."
+            "description": "The full skill body in markdown - instructions, prompts, templates, etc."
           },
           "emoji": {
             "type": "string",
@@ -42,7 +42,7 @@
             "items": { "type": "string" },
             "description": "Optional list of child skill IDs that this skill includes (metadata only, no auto-activation)."
           },
-          "reason": {
+          "activity": {
             "type": "string",
             "description": "Brief non-technical explanation of what you are creating and why, shown to the user as a status update. Use simple language a non-technical person would understand."
           }
@@ -54,7 +54,7 @@
     },
     {
       "name": "delete_managed_skill",
-      "description": "Delete a managed skill from ~/.vellum/workspace/skills and remove it from the SKILLS.md index.",
+      "description": "Delete a managed skill from ~/.vellum/workspace/skills and remove it from the SKILLS.md index. Never delete a skill without explicit user confirmation. After deletion, the next turn may run in a recreated session due to file-watcher eviction - continue normally.",
       "category": "skills",
       "risk": "high",
       "input_schema": {
@@ -68,7 +68,7 @@
             "type": "boolean",
             "description": "Whether to remove the skill from SKILLS.md index (default: true)."
           },
-          "reason": {
+          "activity": {
             "type": "string",
             "description": "Brief non-technical explanation of what you are deleting and why, shown to the user as a status update. Use simple language a non-technical person would understand."
           }

package/src/config/bundled-skills/skills-catalog/SKILL.md

@@ -0,0 +1,84 @@
+---
+name: skills-catalog
+description: Discover bundled skills and search/install community skills from the skills.sh registry
+compatibility: "Designed for Vellum personal assistants"
+metadata:
+  emoji: "\U0001F9E9"
+  vellum:
+    display-name: "Skills Catalog"
+    activation-hints:
+      - "what can you do"
+      - "find a skill"
+      - "install a skill"
+      - "community skills"
+      - "skills.sh"
+      - "search for skills"
+    avoid-when:
+      - "User is asking about a specific bundled skill already visible in the catalog"
+---
+
+You can help the user discover what skills are available and find community skills to extend the assistant's capabilities.
+
+## Bundled skills (first-party)
+
+First-party skills are **bundled** with the assistant - they are compiled in and always available. They do not need to be installed or downloaded. To activate a bundled skill, use the `skill_load` tool:
+
+```
+skill_load skill=<skill-id>
+```
+
+The skill catalog shown in the system prompt lists all bundled skills with their IDs. When a user asks about capabilities, refer to this list to find relevant bundled skills and load them as needed.
+
+## Community skills (skills.sh)
+
+Community skills are published on the skills.sh registry and can be searched, inspected, and installed on demand using the `assistant skills` CLI.
+
+### Searching for community skills
+
+```bash
+assistant skills search "<query>"
+```
+
+Returns matching skills with their slug, source, install counts, and security audit badges. Use this when the user asks for a capability not covered by bundled skills.
+
+### Installing a community skill
+
+**Trust model - check the source owner before installing:**
+
+- **Vellum-owned** (`vellum-ai/*`): First-party skills published by the Vellum team. Install these directly without prompting - they are vetted and trusted.
+- **Third-party** (any other owner): Ask the user for permission first. Present the skill name, source, audit results, and install count. Say something like: "I found a community skill that could help, but it's published by a third party - we haven't vetted it. Want to install it anyway?"
+
+```bash
+assistant skills add <owner>/<repo>@<skill-name>
+```
+
+For example:
+```bash
+assistant skills add vercel-labs/skills@find-skills
+```
+
+Once installed, the skill appears in the workspace skills directory and can be loaded with `skill_load` like any other skill.
+
+## Typical flow
+
+1. **User asks about capabilities** - "Can you order food?" or "What can you do?"
+   - Check the bundled skills list in the system prompt
+   - Present relevant skills to the user
+   - Load any that match with `skill_load`
+
+2. **User wants a capability not covered by bundled skills** - "Can you do X?"
+   - Search with `assistant skills search "<query>"`
+   - Present matching results with descriptions, install counts, and audit badges
+   - Check the source owner to determine trust level (see trust model above)
+   - Install with `assistant skills add <owner>/<repo>@<skill-name>`
+   - Load it with `skill_load`
+
+3. **Skill has dependencies** - if `includes` lists other skill IDs, load those first with `skill_load`
+
+## Notes
+
+- Bundled skills are always available and do not need installation
+- Community skills are installed to the workspace skills directory
+- After installing a community skill, it is auto-enabled and immediately loadable
+- Skills can be enabled or disabled via feature flags without uninstalling them
+- Never install third-party community skills without explicit user confirmation

package/src/config/bundled-skills/slack/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: slack
-description: Scan channels, summarize threads, and manage Slack with privacy guardrails
+description: Scan channels, summarize threads, and manage Slack
 compatibility: "Designed for Vellum personal assistants"
 metadata:
   emoji: "💬"
@@ -68,7 +68,7 @@ When responding to messages from Slack channels, replies are automatically threa
 When you need to **send** content to Slack proactively (e.g. a scheduled digest, a scan summary, or a report):
 
 - Use `messaging_send` with `platform: "slack"` and the target `conversation_id` (Slack channel or DM ID). This posts directly via `chat.postMessage` and preserves the full message content.
-- Do **NOT** use `send_notification` for rich content like digests — the notification router's decision engine rewrites content into short alerts, stripping the actual digest.
+- Do **NOT** use `send_notification` for rich content like digests - the notification router's decision engine rewrites content into short alerts, stripping the actual digest.
 - `send_notification` is appropriate for short alerts and status updates where you want the router to pick the best channel. `messaging_send` is appropriate when you have specific content to deliver to a specific Slack destination.
 - For scheduled tasks (cron/RRULE), always end with a `messaging_send` call so the results actually reach the user. Without it, the output only lives in the conversation log.