@@ -0,0 +1,10 @@
+---
+'@object-ui/console': patch
+---
+
+fix(console): the "Download skill" SKILL.md teaches `delete_record` with `confirm: true`, and the rest of what the server serves
+
+Clause-②: no
+Metadata-protocol: none
+
+The Integrations page's "Download skill" button wrote a SKILL.md that taught `delete_record({ objectName, recordId })` with no `confirm`. The MCP server refuses that call with `ACTION_CONFIRMATION_REQUIRED` and deletes nothing, so an agent that followed the downloaded skill failed every delete. The download now carries the same text the MCP server serves to an API key or a session: `delete_record({ objectName, recordId, confirm })` with the confirmation rule, the business-action tools (`list_actions`, `run_action`, `resume_run`), `validate_expression`, the OAuth connection track, and the `Authorization: Bearer` key form. A test compares the download with the server's renderer byte for byte, so the two cannot drift apart again unnoticed.
@@ -1,7 +1,18 @@
+// @vitest-environment node
 import { describe, it, expect } from 'vitest';
 
+// The canonical renderer, imported from source by relative path: the console
+// does not depend on `@objectstack/mcp` (it is not browser-safe), and the
+// comparison below is the whole point of this file.
+import {
+  renderSkillMarkdown,
+  OBJECTSTACK_MCP_SERVER_NAME as CANONICAL_MCP_SERVER_NAME,
+  OBJECTSTACK_SKILL_DESCRIPTION as CANONICAL_SKILL_DESCRIPTION,
+  OBJECTSTACK_SKILL_NAME as CANONICAL_SKILL_NAME,
+} from '../../../../../../packages/mcp/src/skill-md';
 import {
   renderObjectStackSkill,
+  OBJECTSTACK_MCP_SERVER_NAME,
   OBJECTSTACK_SKILL_NAME,
   OBJECTSTACK_SKILL_DESCRIPTION,
 } from './objectstack-skill';
@@ -17,6 +28,12 @@ function frontmatter(md: string): Record<string, string> {
   return out;
 }
 
+/** The tool names the skill's `## Tools` section teaches, in order. */
+function toolNames(md: string): string[] {
+  const section = md.split('\n## Tools\n')[1]?.split('\n## ')[0] ?? '';
+  return [...section.matchAll(/^- \*\*([a-z_]+)\(/gm)].map((m) => m[1]);
+}
+
 describe('renderObjectStackSkill', () => {
   it('emits valid SKILL.md frontmatter (name + description)', () => {
     const fm = frontmatter(renderObjectStackSkill());
@@ -34,29 +51,56 @@ describe('renderObjectStackSkill', () => {
     expect(renderObjectStackSkill()).toContain('<YOUR_ENV_MCP_URL>');
   });
 
-  it('documents x-api-key auth, not Bearer', () => {
-    const md = renderObjectStackSkill();
-    expect(md).toContain('x-api-key');
-    expect(md).not.toMatch(/Authorization:\s*Bearer/);
+  it('documents the x-api-key header for headless clients', () => {
+    expect(renderObjectStackSkill()).toContain('x-api-key: <YOUR_API_KEY>');
   });
 
-  it('lists all object-CRUD tools and instructs live discovery', () => {
+  it('lists every data and action tool and instructs live discovery', () => {
     const md = renderObjectStackSkill();
-    for (const t of [
+    expect(toolNames(md)).toEqual([
       'list_objects',
       'describe_object',
+      'validate_expression',
       'query_records',
       'get_record',
       'create_record',
       'update_record',
       'delete_record',
-    ]) {
-      expect(md).toContain(t);
-    }
+      'list_actions',
+      'run_action',
+      'resume_run',
+    ]);
     expect(md).toContain('discovered live');
   });
 
+  it('teaches delete_record with confirm: true, which the server requires', () => {
+    const md = renderObjectStackSkill();
+    expect(md).toContain('**delete_record({ objectName, recordId, confirm })**');
+    expect(md).toContain('The server REFUSES a call without `confirm: true`');
+    expect(md).not.toContain('delete_record({ objectName, recordId })');
+  });
+
   it('includes the env name when provided', () => {
     expect(renderObjectStackSkill({ envName: 'Acme CRM' })).toContain('**Acme CRM**');
   });
 });
+
+// Drift pin: the download must be the SKILL.md the server serves to a caller
+// with no OAuth scopes (an API key or a session), byte for byte.
+describe('renderObjectStackSkill mirrors renderSkillMarkdown', () => {
+  it('shares the canonical identity constants', () => {
+    expect(OBJECTSTACK_SKILL_NAME).toBe(CANONICAL_SKILL_NAME);
+    expect(OBJECTSTACK_SKILL_DESCRIPTION).toBe(CANONICAL_SKILL_DESCRIPTION);
+    expect(OBJECTSTACK_MCP_SERVER_NAME).toBe(CANONICAL_MCP_SERVER_NAME);
+  });
+
+  it.each([
+    ['no options', {}],
+    ['an MCP URL', { mcpUrl: 'https://acme.objectos.app/api/v1/mcp' }],
+    ['an env name', { envName: 'Acme CRM' }],
+    ['both, padded with whitespace', { mcpUrl: '  https://acme.objectos.app/api/v1/mcp ', envName: ' Acme CRM ' }],
+    ['blank values', { mcpUrl: '   ', envName: '' }],
+  ])('renders the canonical text for %s', (_label, options) => {
+    expect(renderObjectStackSkill(options)).toBe(renderSkillMarkdown(options));
+  });
+});
@@ -2,10 +2,14 @@
  * objectstack-skill — client-side renderer for the portable ObjectStack Agent
  * Skill (`SKILL.md`), used by the Integrations page "Download skill" button.
  *
- * CANONICAL SOURCE: `renderSkillMarkdown` in `@objectstack/mcp` (framework).
- * That package pulls in the MCP SDK and is not browser-friendly to import here,
- * so this is a faithful mirror for the download UX. Keep the two in sync — the
- * unit test asserts the structural invariants (frontmatter, URL slot, tools).
+ * CANONICAL SOURCE: `renderSkillMarkdown` in `@objectstack/mcp`
+ * (`packages/mcp/src/skill-md.ts`). That package pulls in the MCP SDK and is
+ * not browser-friendly to import here, so this is a mirror of what the server
+ * serves to a caller with no OAuth scopes (an API key or a session): the data
+ * skill, with no authoring section and no federation tools. It must stay
+ * byte-identical to that render — `objectstack-skill.test.ts` imports the
+ * canonical renderer from source and compares the two, so an edit to either
+ * side without the other goes red there.
  *
  * Per ADR-0036 Amendment C this is ONE generic skill: it never enumerates a
  * tenant's schema (the agent discovers live via list_objects/describe_object);
@@ -20,6 +24,8 @@ export interface RenderSkillOptions {
 }
 
 export const OBJECTSTACK_SKILL_NAME = 'objectstack';
+/** The server name the `claude mcp add` snippet registers (mirrors `OBJECTSTACK_MCP_SERVER_NAME`). */
+export const OBJECTSTACK_MCP_SERVER_NAME = 'objectstack';
 export const OBJECTSTACK_SKILL_DESCRIPTION =
   'Query and modify data in an ObjectStack app over MCP — discover objects, ' +
   'read and filter records, and create/update/delete under your own ' +
@@ -42,18 +48,23 @@ description: ${OBJECTSTACK_SKILL_DESCRIPTION}
 
 # ObjectStack
 
-${intro} An ObjectStack environment exposes its data **objects** (tables) as
-tools over the Model Context Protocol (MCP). Every operation runs **as you** —
-under your account's permissions and row-level security — so you may see a
-subset of rows, or get a permission error on a write. That is expected
+${intro} An ObjectStack environment exposes its data **objects** (tables) and
+its business **actions** (registered app logic: approvals, conversions, flow
+triggers) as tools over the Model Context Protocol (MCP). Every operation runs
+under the permissions and row-level security of the identity that connected you
+— and, for an OAuth connection, **within the consent scopes you were granted**
+(a read-only scope can never write, even where that user could). So you may see
+a subset of rows, or get a permission error on a write. That is expected
 governance, not a failure.
 
 ## When to use
 
 Use these tools whenever the user wants to **inspect or change data** in their
-ObjectStack app: look up records, filter/report, create or update entries, or
-clean up data. Prefer these tools over guessing — the environment is the source
-of truth.
+ObjectStack app — look up records, filter/report, create or update entries,
+clean up data — or **run a business action** the app defines (approve a
+request, convert a lead, kick off a flow). Prefer these tools over guessing —
+the environment is the source of truth, and an action is always better than
+hand-editing the records it would have touched.
 
 ## Connect
 
@@ -63,15 +74,32 @@ This skill drives the MCP server at:
 ${url}
 \`\`\`
 
-Authenticate with an ObjectStack API key sent as a request header (the key is
-shown to you once when created; treat it like a password):
+Two authentication tracks are supported:
+
+**OAuth (recommended for interactive clients).** Add the URL as a remote MCP
+server with no credentials; the deployment is its own OAuth 2.1 authorization
+server, so an OAuth-capable client (claude.ai custom connectors, Claude
+Desktop, Claude Code) discovers it automatically, registers itself, and opens
+a browser login. You authorize the connection in the browser; the client then
+acts as an agent **on your behalf** — every tool call is bounded by the
+intersection of the consent scopes you grant and your own permissions/RLS (it
+can never exceed either). Example (Claude Code):
+
+\`\`\`
+claude mcp add --transport http ${OBJECTSTACK_MCP_SERVER_NAME} ${url}
+\`\`\`
+
+**API key (headless: CI, scripts, agents without a browser).** Send an
+ObjectStack API key as a request header (the key is shown to you once when
+created; treat it like a password):
 
 \`\`\`
 x-api-key: <YOUR_API_KEY>
 \`\`\`
 
-(The header \`Authorization: ApiKey <YOUR_API_KEY>\` is also accepted.) If your
-MCP client supports custom headers on a remote server, set the header there.
+(\`Authorization: ApiKey <YOUR_API_KEY>\` and \`Authorization: Bearer
+<YOUR_API_KEY>\` are also accepted.) If your MCP client supports custom
+headers on a remote server, set the header there.
 
 ## Discover before you act
 
@@ -81,6 +109,8 @@ always current even as the app evolves:
 1. \`list_objects\` — see what objects exist.
 2. \`describe_object({ objectName })\` — get an object's fields (name, type,
    required) before querying or writing it.
+3. \`list_actions\` — see what business actions you may run (each entry
+   includes its parameters and whether it needs a \`recordId\`).
 
 Always discover the relevant object's shape before constructing a filter or a
 create/update payload.
@@ -89,14 +119,52 @@ create/update payload.
 
 - **list_objects()** — list available objects (system \`sys_*\` objects are hidden).
 - **describe_object({ objectName })** — an object's fields and features.
+- **validate_expression({ objectName, expression, site?, severity?, triggerKind?, sweepObject? })** — check a CEL
+  expression against an object's schema *before* you author it into a formula,
+  validation, or flow condition. Returns build-time errors (bare field refs,
+  unknown fields/functions) and advisory warnings (text/boolean fields misused
+  in arithmetic; an error at a \`validation\` site, worded for the rule's
+  \`severity\`, and at a \`flow_condition\` of a record-triggered or
+  time-relative flow, where it fails the run; a warning on any other flow), plus the fields and
+  stdlib functions in scope. \`site\` is \`formula\` | \`validation\` |
+  \`flow_condition\` | \`template\` (default \`formula\`). Pass the rule's
+  \`severity\` or the flow's \`triggerKind\` (\`record_change\` by default) to
+  get the verdict the publish gate gives that rule or flow; for a
+  \`time_relative\` flow, pass the object its sweep scans (\`timeRelative.object\`)
+  as \`objectName\`: its conditions read rows of that object, and a start whose
+  \`objectName\` names another object is refused at publish
+  (\`flow-time-relative-object-mismatch\`). \`sweepObject\` names that same object.
 - **query_records({ objectName, where?, fields?, limit?, offset?, orderBy? })** —
   read records. \`where\` is a field→value match, e.g. \`{ "status": "open" }\`.
   Results are page-capped; use \`limit\`/\`offset\` to page.
 - **get_record({ objectName, recordId })** — fetch one record by id.
 - **create_record({ objectName, data })** — create a record.
 - **update_record({ objectName, recordId, data })** — change fields on a record.
-- **delete_record({ objectName, recordId })** — delete a record (destructive —
-  confirm with the user first).
+- **delete_record({ objectName, recordId, confirm })** — delete a record,
+  permanently. The server REFUSES a call without \`confirm: true\`
+  (\`ACTION_CONFIRMATION_REQUIRED\`) and nothing is deleted. Ask your human
+  first; the flag asserts an approval, it does not obtain one.
+- **list_actions()** — list the business actions available to you (only those
+  the app author exposed to AI and you are permitted to run), with each
+  action's declared parameters, whether it operates on a record, and whether
+  it is flagged destructive.
+- **run_action({ actionName, objectName?, recordId?, params?, confirm? })** —
+  invoke a business action by name. Invocation is permission-gated, but the
+  action body executes the app's registered logic as trusted code (it can
+  mutate data or trigger flows with the app's own authority). Pass
+  \`recordId\` for record-scoped actions and \`params\` for declared inputs;
+  \`objectName\` only disambiguates a name shared by multiple objects. Pass
+  \`confirm: true\` on an action \`list_actions\` reports as
+  \`requiresConfirmation\` — the server REFUSES such a call without it
+  (\`ACTION_CONFIRMATION_REQUIRED\`) and nothing runs. Ask your human first;
+  the flag asserts an approval, it does not obtain one.
+- **resume_run({ runId, values?, confirm? })** — continue a flow run that
+  \`run_action\` answered with \`status: "paused"\` and a \`screen\` (a form the
+  flow needs filled in). Send the screen's field values in \`values\`, keyed by
+  the names in \`screen.fields\`. The run completes, or pauses again on its next
+  screen, which you fill with another \`resume_run\`. Only the user whose call
+  started the run can resume it, under the same gates as \`run_action\`
+  (including \`confirm: true\` for an action flagged \`requiresConfirmation\`).
 
 ## Conventions & gotchas
 
@@ -108,13 +176,20 @@ create/update payload.
 - **Writes are real and immediate.** There is no implicit dry-run. Confirm
   destructive actions (\`delete_record\`, bulk updates) with the user.
 - **Page large reads.** Use \`limit\`/\`offset\` rather than asking for everything.
+- **Prefer actions over hand-edits.** When \`list_actions\` offers an action for
+  the task (approve, convert, close, …), call it instead of updating the
+  records yourself — actions carry the app's validation and side effects.
+  Confirm first when an action is record-destructive or flagged for
+  confirmation.
 
 ## Recommended workflow
 
-1. \`list_objects\` to orient.
+1. \`list_objects\` (and \`list_actions\` when the task sounds like a business
+   operation) to orient.
 2. \`describe_object\` on the target object.
 3. \`query_records\` to read / verify current state.
-4. \`create_record\` / \`update_record\` / \`delete_record\` to make changes,
-   confirming destructive steps with the user.
+4. \`run_action\` when a matching business action exists; otherwise
+   \`create_record\` / \`update_record\` / \`delete_record\` — confirming
+   destructive steps with the user.
 `;
 }