@controllerai/cli 0.2.21 → 0.2.23

package/skills-mcp/controllerai-integration-actions/SKILL.md

@@ -16,25 +16,27 @@ Building the agent itself belongs to `controllerai-agents`; a workflow node for
 
 ## How it works
 
-**A ready action is one operation.** The catalog exposes provider integration actions that an agent can call directly, without a workflow; native registry actions appear in the same discovery but are not attachable as direct actions, and every direct attachment needs a connection, so native and provider operations carry different authorization requirements. Use a workflow tool instead when the capability needs several operations, transformation, branching, loops, durable state, a trigger, a custom typed contract, or reuse outside the agent. Never wrap a ready action whose contract already fits in a one-node workflow, and never replace deterministic orchestration with several independent direct actions.
+**A ready action is one operation.** The catalog exposes provider integration actions and native registry actions that an agent can call directly, without a workflow; a native action is attachable when the catalog marks it `agentAttachable`. Most native actions need no connection: they run on the platform's paid rails, bill the user's usage balance per call, and describe the charge in `usagePricingDescription`. A native action that does need authorization uses the platform connection flow (`connection_connect_url`), not Pipedream. Use a workflow tool instead when the capability needs several operations, transformation, branching, loops, durable state, a trigger, a custom typed contract, or reuse outside the agent. Never wrap a ready action whose contract already fits in a one-node workflow, and never replace deterministic orchestration with several independent direct actions.
 
-**Identity is a pair.** An action is the exact integration slug plus its action key, as returned by discovery; a display label is not an identity, and a similar integration with a familiar name is not evidence of the capability. The action binds to a connection whose `integration` matches that slug exactly.
+**Identity is a pair.** An action is the exact integration slug plus its action key, as returned by discovery; a display label is not an identity, and a similar integration with a familiar name is not evidence of the capability. When the catalog says the action needs a connection, it binds to one whose `integration` matches that slug exactly.
 
-**Runtime.** The agent runtime configures the action's dynamic arguments when it invokes the action; nothing is preconfigured at attachment beyond identity, connection, description and approval policy. A direct action runs inline in the conversation and creates no workflow execution: the evidence is the persisted conversation, its action events with arguments and result, and the external effect.
+**Runtime.** The agent runtime configures the action's dynamic arguments when it invokes the action; nothing is preconfigured at attachment beyond identity, any required connection, description and approval policy. A direct action runs inline in the conversation and creates no workflow execution: the evidence is the persisted conversation, its action events with arguments and result, and the external effect.
 
 **Approval policy.** An attached action runs without a human approval step unless `requireConfirmation` is `true`; the default is no approval. When confirmation is on, the runtime pauses with a pending request that the user approves or denies with the exact arguments visible.
 
-**Live bindings.** Publishing snapshots the action identity, description and approval policy into the agent version. The connection and its authorization grant are live security bindings: rebinding redirects the published action immediately, and revocation, breakage or detachment stops it immediately without an agent publish; detachment also removes the draft tool, and a later publish removes it from the published list. Confirmation is strictest-wins: tightening the grant to require confirmation blocks the published action at once until a publish carries the new policy, while relaxing it waits for the publish. Organization members use the published agent, never the draft; direct actions run through the owner's connected account and the organization's shared usage pool whoever calls them.
+**Slack approvals.** Send approval requests to Slack through `slackRoute`. Routes publish with the agent; Test conversations use the draft, live conversations the published version. The route lists who can answer in `slackRoute.approvers`, defaulting to whoever connected Slack. Chat-in-Slack approvers also count; the app's approval card still works.
+
+**Live bindings.** Publishing snapshots the action identity, description and approval policy into the agent version. When an action needs a connection, that connection and its authorization grant are live security bindings: rebinding redirects the published action immediately, and revocation, breakage or detachment stops it immediately without an agent publish. Detachment has the same immediate effect on a connectionless action, always removes the draft tool, and a later publish removes it from the published list. Confirmation is strictest-wins: tightening the grant to require confirmation blocks the published action at once until a publish carries the new policy, while relaxing it waits for the publish. Organization members use the published agent, never the draft; connected actions run through the owner's connected account and the organization's shared usage pool, while connectionless native actions use the platform's paid rails and bill that pool whoever invokes them.
 
 ## Rules
 
-1. **Capture and reuse the exact identities**: integration slug, action key, connection ID, tool ID. Narrow the query or raise the result limit when more matches exist; never derive an identifier from a label.
-2. **A missing connection is a handoff, not a substitution.** Keep the selected integration and action, give the user the authorization route, and stop the attachment there; never swap in `registry_http-http-request` or request provider credentials in chat. A raw endpoint the user mentions is context, not an instruction to hand-roll the call.
+1. **Capture and reuse the exact identities**: integration slug, action key, connection ID when required, tool ID. Narrow the query or raise the result limit when more matches exist; never derive an identifier from a label.
+2. **A required missing connection is a handoff, not a substitution.** Keep the selected integration and action, give the user the platform authorization route, and stop the attachment there; never request provider credentials in chat. Never swap in `registry_http-http-request`: the HTTP node is never agent-attachable, so that substitution is impossible by construction. A raw endpoint the user mentions is context, not an instruction to hand-roll the call.
 3. **Decide the approval policy before attaching.** For an action that sends, posts, spends or deletes, choose `true` or explicitly tell the user it will run unattended; prefer confirmation for permission changes, irreversible writes or an ambiguous destination, and omit it for reads and low-risk reversible operations the user asked to run autonomously. Mention the confirmation choice in the report to the user.
 4. **Attach once.** Read the tool list before and after; the final list holds one intended direct attachment.
-5. **A stored active connection is not proof of authorization.** Only a representative action test proves the provider still accepts it.
+5. **A stored active connection is not proof of authorization.** For an action that needs one, only a representative action test proves the provider still accepts it.
 6. **Verify what the request asked for, where it lives.** Discovery proves metadata; a blocked attachment proves the honest handoff and the independent work; an attachment proves the saved grant; only an authorized runtime test proves the external effect, and for that the action event, its arguments and result, and the external state are the evidence, never a reply that says it ran. Inspect the external state before repeating a failed or uncertain mutation.
-7. **Say whose account runs the action** before organization sharing: the owner's connection and the organization's usage pool, regardless of caller.
+7. **Say whose account and balance run the action** before organization sharing: connected actions use the owner's account; connectionless native actions use the platform's paid rails; calls use the organization's shared usage balance regardless of caller.
 
 ## Recipes
 
@@ -44,31 +46,30 @@ Building the agent itself belongs to `controllerai-agents`; a workflow node for
 - `integration_action_list` — `query`, `integration`, `limit`
 - `integration_action_get` — `integration`, `key`
 
-`integration_search` ranks integrations (`kind` narrows to actions or events); `integration_action_list` ranks actions across one or all integrations; `integration_action_get` returns the static metadata and props of one exact action. Read that metadata before choosing.
+`integration_search` ranks integrations (`kind` narrows to actions or events); `integration_action_list` ranks actions across one or all integrations; `integration_action_get` returns the static metadata and props of one exact action. Read `agentAttachable`, the exact props and, for native actions, whether a connection is needed and `usagePricingDescription` before choosing.
 
 ### Select or request a connection
 
 - `connection_list` — `integration`
 
+Skip this step when the catalog says the native action needs no connection.
+
 Use the active connection whose `integration` matches exactly. If none exists, `connection_connect_url` (it takes the `nodeSlug`) returns a `url`: show it as a markdown link, ask the user to finish, then `connection_list` with `integration` and use the new ID.
 
 ### Attach
 
-- `agent_tool_action_add` — `agentId`, `action`, `connectionId`, `description`, `integration`, `requireConfirmation`
+- `agent_tool_action_add` — `agentId`, `action`, `connectionId`, `description`, `integration`, `requireConfirmation`, `slackRoute`
 - `agent_tool_list` — `agentId`
 
-`agent_tool_action_add` takes `requireConfirmation`, optional and `false` by default.
-The description tells the agent when to choose the tool. Read the saved grant back: `toolType`, integration, action key, connection, description and confirmation policy.
+`agent_tool_action_add` takes `requireConfirmation`, optional and `false` by default; pass `connectionId` exactly when the action needs a connection.
+The description tells the agent when to choose the tool. Read the saved grant back: `toolType`, integration, action key, any required connection, description and confirmation policy.
 
 ### Update
 
-- `agent_tool_update` — `agentId`, `connectionId`, `description`, `requireConfirmation`, `toolId`
-- `agent_tool_update` — `agentId`, `connectionId`, `description`, `requireConfirmation`, `toolId`
-- `agent_tool_update` — `agentId`, `connectionId`, `description`, `requireConfirmation`, `toolId`
-- `agent_tool_update` — `agentId`, `connectionId`, `description`, `requireConfirmation`, `toolId`
+- `agent_tool_update` — `agentId`, `connectionId`, `description`, `requireConfirmation`, `toolId`, `slackRoute`
 
 `agent_tool_update` takes `toolId` and at least one of `connectionId`, `description` or `requireConfirmation: true|false`; an omitted field keeps its value, so a connection-only update never changes the approval policy.
-A connection change redirects the published action at once. A description change waits for the agent publish. A policy change is strictest-wins: turning confirmation on blocks the published action immediately until the next publish carries it, turning it off takes effect only at that publish.
+A connection change redirects a connected published action at once. A description change waits for the agent publish. A policy change is strictest-wins: turning confirmation on blocks the published action immediately until the next publish carries it, turning it off takes effect only at that publish.
 
 ### Verify in a draft conversation
 
@@ -82,8 +83,8 @@ A connection change redirects the published action at once. A description change
 
 ## Verify
 
-For an attachment, the tool list shows exactly one intended direct attachment with the exact identities, connection, description and confirmation policy; for an authorized runtime test, the draft conversation history holds the action event, its arguments and its result, and the external effect was checked separately; for discovery alone, the exact metadata was read and nothing was changed. No wrapper workflow exists unless orchestration or reuse required it.
+For an attachment, the tool list shows exactly one intended direct attachment with the exact identities, any required connection, description and confirmation policy; for an authorized runtime test, the draft conversation history holds the action event, its arguments and its result, and the external effect was checked separately; for discovery alone, the exact metadata was read and nothing was changed. No wrapper workflow exists unless orchestration or reuse required it.
 
 ## Report
 
-Which action is attached to which agent, its connection and confirmation choice, what the draft test proved, whose account and usage pool the action will use, and what remains: a connection to authorize, a publish, or a live verification.
+Which action is attached to which agent, any connection and the confirmation choice, what the draft test proved, whose account or paid rail and usage balance the action will use, and what remains: a connection to authorize, a publish, or a live verification.

package/skills-mcp/controllerai-runs/SKILL.md

@@ -43,7 +43,6 @@ Expression authoring belongs to `controllerai-expressions`, branch and loop stru
 
 ### Prepare inputs and run
 
-- `run_inputs` — `nodeIdOrFlowId`, `flow`, `workflowId`
 - `run_inputs` — `nodeIdOrFlowId`, `flow`, `workflowId`
 - `run_node` — `nodeId`, `inputs`, `waitSeconds`, `workflowId`
 - `run_flow` — `flowId`, `confirmLive`, `inputs`, `target`, `waitSeconds`, `workflowId`

package/skills-mcp/controllerai-start/SKILL.md

@@ -30,6 +30,8 @@ For the domain itself, load the relevant domain skill as the work reaches it: `c
 
 An agent can call several flows of one workflow as tools: flow inputs become tool arguments, flow outputs become tool results, and the workflow's data store is the agent's application backend.
 
+Ready integration actions come from provider integrations or native registry services; only catalog actions marked `agentAttachable` can attach directly, and a native action may run without a connection.
+
 **Rails.** Every workflow has a development version and, after publishing, a live release. Every agent has a draft and, after publishing, a live version. Agent Test runs the draft against development workflows, draft knowledge, and live runtime files overlaid by development runtime files. Agent Live runs the latest published agent against each workflow's latest live release and frozen published knowledge. A change to the draft reaches Live and shared users only through another agent publish, which also restamps existing live conversations; the owner's Test already sees the draft. Publishing a workflow never copies development records into the live data store. Two bindings change Live without an agent publish: a live agent follows each workflow's newest release as soon as it is published, and a direct action's connection is a live grant, so rebinding it redirects Live and revoking it blocks Live.
 
 **Connections.** A connection is an authorized account for an app. Deleting a connection immediately removes authorization from every node and agent tool bound to it.  Rename or change the default with `connection_update` (`displayName` and/or `isDefault`); delete one only with the user's explicit intent, with `connection_delete`. 

package/skills-mcp/controllerai-start/references/mcp-tool-map.md

@@ -3,7 +3,7 @@
 
 # CLI to typed MCP tool map
 
-This registry-derived map covers 165 CLI commands and 149 typed MCP tools. CLI examples remain the canonical grammar; typed MCP calls use the tool and camelCase parameters shown here. Global `--json` and `--api-url` flags are host-controlled and omitted.
+This registry-derived map covers 167 CLI commands and 149 typed MCP tools. CLI examples remain the canonical grammar; typed MCP calls use the tool and camelCase parameters shown here. Global `--json` and `--api-url` flags are host-controlled and omitted.
 
 | `cai` command | MCP tool | Parameter mapping | Notes |
 | --- | --- | --- | --- |
@@ -137,6 +137,8 @@ This registry-derived map covers 165 CLI commands and 149 typed MCP tools. CLI e
 | `skills install` (CLI only) | — | — | dropped: Writes guidance into a caller local project, which the hosted server cannot access. |
 | `guide_get` / `guide_list` | `guide_get`<br>`guide_list` | `guide_get`: `name` (MCP-only) → `name`<br>`guide_list`: — | hosted: guide_list and guide_get serve the bundled server guidance without inspecting a local project. |
 | `skills update` (CLI only) | — | — | dropped: Updates guidance files in a caller local project. |
+| `template-setup complete` (CLI only) | — | — | dropped: Managed-builder only: uses the current assisted-setup thread credential; no public MCP equivalent. |
+| `template-setup status` (CLI only) | — | — | dropped: Managed-builder only: uses the current assisted-setup thread credential; no public MCP equivalent. |
 | `trigger_audit` | `trigger_audit` | `--workflow` → `workflowId` | — |
 | `trigger_create` | `trigger_create` | `--connection` → `connection`; `--dynamic-props-id` → `dynamicPropsId`; `--event` → `event`; `--flow` → `flow`; `--node` → `node`; `--props` → `props`; `--source-basis` → `sourceBasis`; `--workflow` → `workflowId` | — |
 | `trigger_delete` | `trigger_delete` | `<triggerId>` → `triggerId`; `--workflow` → `workflowId` | — |

package/skills-mcp/controllerai-template-setup/SKILL.md

@@ -0,0 +1,10 @@
+---
+name: controllerai-template-setup
+description: Complete an assisted Controller AI agent-template setup from the injected setup brief. Use when the system prompt contains a `## Template Setup` section with copied workflows, required connections, expected workflow tools, and a brief.
+---
+<!-- generated from .claude/skills by cli/scripts/render-skills.mjs; edit the source -->
+
+# Assisted template setup
+
+This procedure requires the managed builder credential for the current setup thread and has no public MCP equivalent. Stop if a `## Template Setup` block appears outside that managed builder session.
+

package/skills-mcp/controllerai-triggers/SKILL.md

@@ -43,7 +43,6 @@ Flow inputs and mapping expressions belong to `controllerai-expressions`; readin
 
 ### Discover and resolve
 
-- `trigger_search` — `query`, `eventsPerNode`, `limit`, `node`, `workflowId`
 - `trigger_search` — `query`, `eventsPerNode`, `limit`, `node`, `workflowId`
 - `trigger_component_props` — `configured`, `connection`, `dynamicPropsId`, `event`, `node`, `workflowId`
 - `trigger_prop_options` — `configured`, `connection`, `dynamicPropsId`, `event`, `node`, `page`, `prevContext`, `prop`, `query`, `workflowId`
@@ -68,14 +67,12 @@ A representative event has to reach the source: through the provider, the return
 
 ### Arm ambient development dispatch (only on request)
 
-- `trigger_test_events_set` — `triggerId`, `acknowledgeDualRun`, `allowed`, `workflowId`
 - `trigger_test_events_set` — `triggerId`, `acknowledgeDualRun`, `allowed`, `workflowId`
 
 Arming makes every real event also execute the development canvas while it is half built; use it only when the user wants that after hearing it, and disarm at the end of setup. `trigger_test_events_set` takes `allowed: true|false` and `acknowledgeDualRun: true` when arming.
 
 ### Pause, resume, retire
 
-- `trigger_set_enabled` — `triggerId`, `enabled`, `workflowId`
 - `trigger_set_enabled` — `triggerId`, `enabled`, `workflowId`
 - `trigger_delete` — `triggerId`, `workflowId`
 

package/skills-mcp/controllerai-workflows/SKILL.md

@@ -79,7 +79,6 @@ Read status and every trigger first: publishing activates enabled triggers on th
 
 - `workflow_state_save` — `name`, `workflowId`
 - `workflow_history` — `group`, `version`, `workflowId`
-- `workflow_history` — `group`, `version`, `workflowId`
 - `workflow_state_restore` — `stateId`, `version`, `workflowId`
 
 Save before a risky rewrite. Expand a group to find the state ID; restore by state, not by group.

package/skills-mcp/manifest.json

@@ -1,23 +1,23 @@
 {
   "schemaVersion": 1,
-  "skillSetVersion": "2026.09.07.1",
+  "skillSetVersion": "2026.09.15.3",
   "minCliVersion": "0.2.0",
-  "latestCliVersion": "0.2.21",
+  "latestCliVersion": "0.2.23",
   "skills": [
     {
       "name": "controllerai-start",
       "files": [
         {
           "path": "controllerai-start/SKILL.md",
-          "url": "https://getcontroller.ai/skills-mcp/2026.09.07.1/controllerai-start/SKILL.md",
-          "sha256": "479df6a863d207f7f8179d6491a16c0d2399d1973c8ef0cd4a310781ff360548",
-          "size": 10967
+          "url": "https://getcontroller.ai/skills-mcp/2026.09.15.3/controllerai-start/SKILL.md",
+          "sha256": "65b35ecd4c5a94bd991f85aaaa6c26f1d551f646da136757c5a8a853b1f7389c",
+          "size": 11172
         },
         {
           "path": "controllerai-start/references/mcp-tool-map.md",
-          "url": "https://getcontroller.ai/skills-mcp/2026.09.07.1/controllerai-start/references/mcp-tool-map.md",
-          "sha256": "edf8213da96c4a8a71b74b1fb644db87a3fb8354385dd086335f08df870529ae",
-          "size": 26437
+          "url": "https://getcontroller.ai/skills-mcp/2026.09.15.3/controllerai-start/references/mcp-tool-map.md",
+          "sha256": "8dc049be93070daa4ad66d09883f2887cb130cf3d54cc50056a202a2e118a925",
+          "size": 26761
         }
       ]
     },
@@ -26,13 +26,13 @@
       "files": [
         {
           "path": "controllerai-workflows/SKILL.md",
-          "url": "https://getcontroller.ai/skills-mcp/2026.09.07.1/controllerai-workflows/SKILL.md",
-          "sha256": "45b5d4cfda5e1f8e206192fae2076d0e137300f45f264e0fc28e3f9a994351ff",
-          "size": 9607
+          "url": "https://getcontroller.ai/skills-mcp/2026.09.15.3/controllerai-workflows/SKILL.md",
+          "sha256": "94f6f343c3cc2a469cdd2247f8bcc9cb8fa56290a35d988409155d22f5c5c1f9",
+          "size": 9549
         },
         {
           "path": "controllerai-workflows/references/command-map.md",
-          "url": "https://getcontroller.ai/skills-mcp/2026.09.07.1/controllerai-workflows/references/command-map.md",
+          "url": "https://getcontroller.ai/skills-mcp/2026.09.15.3/controllerai-workflows/references/command-map.md",
           "sha256": "3a1fe464d00c2ae734dab11db3b338436d91a9c32dd8a1b3f1843ac4200a739c",
           "size": 89
         }
@@ -43,13 +43,13 @@
       "files": [
         {
           "path": "controllerai-node-config/SKILL.md",
-          "url": "https://getcontroller.ai/skills-mcp/2026.09.07.1/controllerai-node-config/SKILL.md",
+          "url": "https://getcontroller.ai/skills-mcp/2026.09.15.3/controllerai-node-config/SKILL.md",
           "sha256": "7fbc68a24ccc08c04be8b6c4184b74b238058b637e4203293e0c5eae332bac2d",
           "size": 11678
         },
         {
           "path": "controllerai-node-config/references/prop-and-readiness.md",
-          "url": "https://getcontroller.ai/skills-mcp/2026.09.07.1/controllerai-node-config/references/prop-and-readiness.md",
+          "url": "https://getcontroller.ai/skills-mcp/2026.09.15.3/controllerai-node-config/references/prop-and-readiness.md",
           "sha256": "87da8b25c8303818b1f0c677b2cc6f7121910e8fcd94371ed5bc2065f7b7b845",
           "size": 5344
         }
@@ -60,13 +60,13 @@
       "files": [
         {
           "path": "controllerai-expressions/SKILL.md",
-          "url": "https://getcontroller.ai/skills-mcp/2026.09.07.1/controllerai-expressions/SKILL.md",
-          "sha256": "993216f7070a1d4c16c66b4cc5d4e39bf87deef6a6c22b646cd72640d7dcd523",
-          "size": 10570
+          "url": "https://getcontroller.ai/skills-mcp/2026.09.15.3/controllerai-expressions/SKILL.md",
+          "sha256": "c54f8c3176ffe48ca7aa78cd85151a1edf1f0083f7cd8b906b5d1d2ff5f5cc20",
+          "size": 10495
         },
         {
           "path": "controllerai-expressions/references/dsl-and-recipes.md",
-          "url": "https://getcontroller.ai/skills-mcp/2026.09.07.1/controllerai-expressions/references/dsl-and-recipes.md",
+          "url": "https://getcontroller.ai/skills-mcp/2026.09.15.3/controllerai-expressions/references/dsl-and-recipes.md",
           "sha256": "741b03033cb655dde95be99dcf6e00295b1b2d4f385ad42bbf4bb3c4001c9973",
           "size": 4915
         }
@@ -77,15 +77,15 @@
       "files": [
         {
           "path": "controllerai-flow-control/SKILL.md",
-          "url": "https://getcontroller.ai/skills-mcp/2026.09.07.1/controllerai-flow-control/SKILL.md",
-          "sha256": "3545a2cd9dee516e2cc9a56f22a9ca6e725be5cbcc7b734ceaad8498233304ce",
-          "size": 12553
+          "url": "https://getcontroller.ai/skills-mcp/2026.09.15.3/controllerai-flow-control/SKILL.md",
+          "sha256": "4bacfc3b7501565e0e5984b19d9223da1b5bf770875db804b5e6827d33efa967",
+          "size": 12367
         },
         {
           "path": "controllerai-flow-control/references/patterns.md",
-          "url": "https://getcontroller.ai/skills-mcp/2026.09.07.1/controllerai-flow-control/references/patterns.md",
-          "sha256": "dabb6e4aa81de05cd9bceb9f4bc3b3a5a005723f17b6b69958939a36ce10062b",
-          "size": 4770
+          "url": "https://getcontroller.ai/skills-mcp/2026.09.15.3/controllerai-flow-control/references/patterns.md",
+          "sha256": "a849179afb512e8fc0c3c833a1a2c737c5108e8ab8941c9fa261767671eceb01",
+          "size": 4704
         }
       ]
     },
@@ -94,13 +94,13 @@
       "files": [
         {
           "path": "controllerai-runs/SKILL.md",
-          "url": "https://getcontroller.ai/skills-mcp/2026.09.07.1/controllerai-runs/SKILL.md",
-          "sha256": "7056e18550425bcd0bb1189f48cc06ed4d7def2c6a2becbf1a1c51f9b6ca77d3",
-          "size": 9370
+          "url": "https://getcontroller.ai/skills-mcp/2026.09.15.3/controllerai-runs/SKILL.md",
+          "sha256": "ce8109606899a36dd298aa7fc41ff2288f62bfe9adeae0806b95fd22a317fe27",
+          "size": 9312
         },
         {
           "path": "controllerai-runs/references/debugging.md",
-          "url": "https://getcontroller.ai/skills-mcp/2026.09.07.1/controllerai-runs/references/debugging.md",
+          "url": "https://getcontroller.ai/skills-mcp/2026.09.15.3/controllerai-runs/references/debugging.md",
           "sha256": "616d13ea43785e4d11bdb50b9e4098126fbc470ee2568b250e1af5f15cab3edf",
           "size": 3162
         }
@@ -111,13 +111,13 @@
       "files": [
         {
           "path": "controllerai-triggers/SKILL.md",
-          "url": "https://getcontroller.ai/skills-mcp/2026.09.07.1/controllerai-triggers/SKILL.md",
-          "sha256": "2329a5d829f21cc6cc1ec30815b8302108ea7c5eb20d7470bb340bd2798b3e30",
-          "size": 12609
+          "url": "https://getcontroller.ai/skills-mcp/2026.09.15.3/controllerai-triggers/SKILL.md",
+          "sha256": "0797e2070acbd674deca6b659d467d1cc5a86cb26120e489c52d10cb58fc044b",
+          "size": 12374
         },
         {
           "path": "controllerai-triggers/references/lifecycle.md",
-          "url": "https://getcontroller.ai/skills-mcp/2026.09.07.1/controllerai-triggers/references/lifecycle.md",
+          "url": "https://getcontroller.ai/skills-mcp/2026.09.15.3/controllerai-triggers/references/lifecycle.md",
           "sha256": "519d9f858ee2ec8ab5f1c988e547f5a8c5478f4da3d454236354ade9800ed044",
           "size": 3438
         }
@@ -128,15 +128,15 @@
       "files": [
         {
           "path": "controllerai-data/SKILL.md",
-          "url": "https://getcontroller.ai/skills-mcp/2026.09.07.1/controllerai-data/SKILL.md",
-          "sha256": "5f12370f5eb65a23aad16c3a47f32e3a1e006b47ea62caa3fff7869f66a12054",
-          "size": 12754
+          "url": "https://getcontroller.ai/skills-mcp/2026.09.15.3/controllerai-data/SKILL.md",
+          "sha256": "d17cfcda2abbccf6463edc6331c091175f7c7d92f6a2ce69dccc6d0fa4188e34",
+          "size": 12477
         },
         {
           "path": "controllerai-data/references/data-rails.md",
-          "url": "https://getcontroller.ai/skills-mcp/2026.09.07.1/controllerai-data/references/data-rails.md",
-          "sha256": "c0ee68db825b643027d348352ec5d78d3001aee233a53aabafdae1e0526569af",
-          "size": 2974
+          "url": "https://getcontroller.ai/skills-mcp/2026.09.15.3/controllerai-data/references/data-rails.md",
+          "sha256": "6d22c72b3b2da83cfaf078683ef41ec2b6f3b9b249789ab2bd23d01d6710c261",
+          "size": 2843
         }
       ]
     },
@@ -145,13 +145,13 @@
       "files": [
         {
           "path": "controllerai-ai-nodes/SKILL.md",
-          "url": "https://getcontroller.ai/skills-mcp/2026.09.07.1/controllerai-ai-nodes/SKILL.md",
-          "sha256": "af5ea6d1ffaa6d58ad6a84d048814ccf8c6100dd86e8eca7cf9450329161c326",
-          "size": 9595
+          "url": "https://getcontroller.ai/skills-mcp/2026.09.15.3/controllerai-ai-nodes/SKILL.md",
+          "sha256": "e6071d906cf1df7665cb63274a579d7a0f46796440112a74f190338389b2db33",
+          "size": 9484
         },
         {
           "path": "controllerai-ai-nodes/references/selection-and-testing.md",
-          "url": "https://getcontroller.ai/skills-mcp/2026.09.07.1/controllerai-ai-nodes/references/selection-and-testing.md",
+          "url": "https://getcontroller.ai/skills-mcp/2026.09.15.3/controllerai-ai-nodes/references/selection-and-testing.md",
           "sha256": "66b235b9e81645ab877b31443505c7b07ea3f2e5a357053f266c121415f8cf5c",
           "size": 3111
         }
@@ -162,9 +162,9 @@
       "files": [
         {
           "path": "controllerai-integration-actions/SKILL.md",
-          "url": "https://getcontroller.ai/skills-mcp/2026.09.07.1/controllerai-integration-actions/SKILL.md",
-          "sha256": "166d301233d3e5a4f0db1bf76c4c1bf28924c1fb4564d03ade0372c91d31c951",
-          "size": 9024
+          "url": "https://getcontroller.ai/skills-mcp/2026.09.15.3/controllerai-integration-actions/SKILL.md",
+          "sha256": "d0cf193ec8efbf6339352964c16ebae9a83e6e6bf5691e36a13927e687f2a5c4",
+          "size": 10086
         }
       ]
     },
@@ -173,17 +173,28 @@
       "files": [
         {
           "path": "controllerai-agents/SKILL.md",
-          "url": "https://getcontroller.ai/skills-mcp/2026.09.07.1/controllerai-agents/SKILL.md",
-          "sha256": "5bb9ee73fb9e0336a5aadf412a44d4c3012c24d7d2961544a4be1c66d6eba17f",
-          "size": 12331
+          "url": "https://getcontroller.ai/skills-mcp/2026.09.15.3/controllerai-agents/SKILL.md",
+          "sha256": "5e8cd8cf5474b22587c8083d52c56ba2b13a5e05b8c1c2fd6ed5ecaa03dfb997",
+          "size": 12725
         },
         {
           "path": "controllerai-agents/references/instructions-and-versioning.md",
-          "url": "https://getcontroller.ai/skills-mcp/2026.09.07.1/controllerai-agents/references/instructions-and-versioning.md",
+          "url": "https://getcontroller.ai/skills-mcp/2026.09.15.3/controllerai-agents/references/instructions-and-versioning.md",
           "sha256": "88b059e74aef03ccb12a53815d1090e5449090ff6dfd863b6cef5a12b434cb65",
           "size": 5644
         }
       ]
+    },
+    {
+      "name": "controllerai-template-setup",
+      "files": [
+        {
+          "path": "controllerai-template-setup/SKILL.md",
+          "url": "https://getcontroller.ai/skills-mcp/2026.09.15.3/controllerai-template-setup/SKILL.md",
+          "sha256": "a530a694257ccf7622c4f16579cad91bf96ac06dfc7cbd82a919914abe387e52",
+          "size": 609
+        }
+      ]
     }
   ]
 }