chore: sync skills pack guides (n8n-skills 1.33.0) (czlonkowski#1035)

* chore: sync skills pack guides (v1.33.0)

Conceived by Romuald Członkowski - www.aiadvisors.pl/en

* chore: sync skills pack review fixes (n8n-skills 1.33.0)

Conceived by Romuald Członkowski - www.aiadvisors.pl/en

* chore: sync skills pack wording fixes (n8n-skills 1.33.0)

Conceived by Romuald Członkowski - www.aiadvisors.pl/en

Author: czlonkowski

data/skills/n8n-mcp-tools-expert/OPERATIONS_GUIDE.md

@@ -69,17 +69,18 @@ n8n_deploy_template({
 ## Data Table Management
 
 > **Two surfaces, don't confuse them:**
-> - **`n8n_manage_datatable` (below)** — MCP tool for managing tables and rows from *outside* a workflow (e.g. creating tables during workflow scaffolding, seeding data, or inspecting state from Claude). Covered here.
+> - **`n8n_manage_datatable` (below)** — MCP tool for managing tables, rows and columns from *outside* a workflow (e.g. creating tables during workflow scaffolding, seeding data, or inspecting state from Claude). Covered here.
 > - **`nodes-base.dataTable` node** — the in-workflow node you drop into a workflow to read/write rows *during execution*. For its parameter shapes, operation values, filter syntax, and gotchas (e.g. the `deleteRows` reserved-word workaround, the `id isNotEmpty` trick for "all rows"), see [n8n-node-configuration → OPERATION_PATTERNS.md → Storage Nodes → Data Table](../n8n-node-configuration/OPERATION_PATTERNS.md#data-table-nodes-basedatatable).
 >
 > Rule of thumb: use the MCP tool to set up a table once and the workflow node to read/write rows on every execution.
 
 ### n8n_manage_datatable
 
-Unified tool for managing n8n data tables and rows. Supports CRUD operations on tables and rows with filtering, pagination, and dry-run support.
+Unified tool for managing n8n data tables, their rows and their columns. Supports CRUD operations on tables and rows with filtering, pagination, and dry-run support, plus column changes through n8n's MCP server.
 
 **Table Actions**: `createTable`, `listTables`, `getTable`, `updateTable`, `deleteTable`
 **Row Actions**: `getRows`, `insertRows`, `updateRows`, `upsertRows`, `deleteRows`
+**Column Actions** (n8n's MCP server, `N8N_MCP_ACCESS_TOKEN`, n8n 2.34+): `addColumn`, `deleteColumn`, `renameColumn`
 
 ```javascript
 // Create a data table
@@ -129,6 +130,31 @@ n8n_manage_datatable({
 })
 ```
 
+```javascript
+// Column actions: the Public API cannot change columns after a table exists,
+// so these run through n8n's MCP server. projectId is the project owning the
+// table; when omitted it is resolved from the instance's projects (PROJECT_REQUIRED
+// asks for it when more than one project could own the table).
+n8n_manage_datatable({
+  action: "addColumn",
+  tableId: "dt-123",
+  column: {name: "status", type: "string"}   // letters/digits/underscores, starts with a letter, max 63 chars
+})
+
+n8n_manage_datatable({
+  action: "renameColumn",
+  tableId: "dt-123",
+  columnId: "col-456",   // from getTable
+  name: "state"
+})
+
+n8n_manage_datatable({
+  action: "deleteColumn",
+  tableId: "dt-123",
+  columnId: "col-456"
+})
+```
+
 **Filter conditions**: `eq`, `neq`, `like`, `ilike`, `gt`, `gte`, `lt`, `lte`
 
 **Best practices**:

data/skills/n8n-mcp-tools-expert/SKILL.md

@@ -316,7 +316,7 @@ See [WORKFLOW_GUIDE.md](WORKFLOW_GUIDE.md) for all actions, the includeUsage sha
 
 ## Agents
 
-Three tools talk to n8n's instance-level MCP server (a separate endpoint from the Public API) and need `N8N_MCP_ACCESS_TOKEN` — see "Tool Availability" below.
+The three tools in this section exist only for n8n's instance-level MCP server (a separate endpoint from the Public API). `n8n_manage_agents` and `n8n_explore_node_resources` need `N8N_MCP_ACCESS_TOKEN`; `n8n_list_catalog` works without it and uses the token only for its team-project fallback. Other tools route individual operations through the same server — `n8n_test_workflow` `prepare`/`pinned`/`direct`, `n8n_workflow_versions` `source: "native"`, the `n8n_manage_datatable` column actions — as described in their own sections; see "Tool Availability" below.
 
 - `n8n_manage_agents` — create, configure, validate, run and publish persisted n8n Agents (a standalone assistant artifact: model, instructions, tools, skills, tasks, memory, channels — not the AI Agent workflow node). Actions: `reference`, `search`, `get`, `create`, `mutate`, `validate`, `call`, `publish`, `unpublish`, `revert`, `versions`, `delete`, `discover_assets`, `verify_mcp_server`, `update_integration`. Start with `action: "reference"`, then `discover_assets` → `create` → `mutate` (one resource at a time, always the latest `configHash` — a stale one comes back as `STALE_CONFIG`) → `validate`. `publish` only on explicit request; `call` runs the agent with real credentials and tools and may return `approvals[]` for the human to decide. `timeoutMs` is a top-level parameter (default 30000, 180000 for `call`), not part of `args`. Needs n8n **2.34+** with the agents module; on 2.36.x the agents runtime rejects `azureOpenAiApi`/`aws` credentials. See **n8n-agents** skill's "Persisted n8n Agents" section for the full workflow.
 - `n8n_explore_node_resources` — resolve the real values behind a node's `loadOptions` dropdown or resource-locator `listSearch` (Slack channels, Google Sheets tabs, model lists) using a live credential, instead of guessing an ID. Use it when `get_node` (`standard` detail) shows `dynamicOptions: {methodName, methodType, dependsOn}` on a property — pass that `methodName`/`methodType` plus a `credentialId` from `n8n_manage_credentials({action: "list"})`.

data/skills/n8n-mcp-tools-expert/WORKFLOW_GUIDE.md

@@ -547,7 +547,14 @@ const result = n8n_deploy_template({
 
 ## n8n_workflow_versions (VERSION CONTROL)
 
-**Use when**: Managing workflow history, rollback, cleanup
+**Use when**: Managing workflow history, rollback, cleanup, comparing versions
+
+Two independent histories, selected with `source`:
+
+- `source: "local"` (default) — snapshots n8n-mcp takes before it changes a workflow. Any n8n version, no token; ids are numbers. Blind to edits made in the n8n UI. The only source with `delete` and `prune`.
+- `source: "native"` — n8n's own workflow history, the same list the UI shows. Needs `N8N_MCP_ACCESS_TOKEN` (n8n 2.34+; native `diff` needs 2.36) and the workflow's "Available in MCP" setting; ids are opaque strings; `list` is capped at 50 with `offset`; `delete`/`prune` return `MODE_NOT_SUPPORTED_FOR_SOURCE`; native `rollback` runs without local validation and says so in `validation`.
+
+Every response states `source` and `backend`. The examples below use `source: "local"` unless noted.
 
 ### List Versions
 ```javascript
@@ -556,27 +563,74 @@ n8n_workflow_versions({
   workflowId: "workflow-id",
   limit: 10
 })
+
+// n8n's own history (edits made in the UI included)
+n8n_workflow_versions({
+  mode: "list",
+  source: "native",
+  workflowId: "workflow-id",
+  limit: 20,
+  offset: 0
+})
 ```
 
 ### Get Specific Version
 ```javascript
 n8n_workflow_versions({
   mode: "get",
-  versionId: 123
+  workflowId: "workflow-id",
+  versionId: 123          // local ids are numbers
+})
+
+n8n_workflow_versions({
+  mode: "get",
+  source: "native",
+  workflowId: "workflow-id",
+  versionId: "8f3c…"      // native ids are strings, from the native list
+})
+```
+
+### Diff Two Versions
+```javascript
+// Local: added/removed/modified nodes reported as node IDs (data.format: "n8n-mcp")
+n8n_workflow_versions({
+  mode: "diff",
+  workflowId: "workflow-id",
+  versionId: 122,
+  toVersionId: 123
+})
+
+// Native: n8n's own payload with field-level before/after values (data.format: "n8n", n8n 2.36+)
+n8n_workflow_versions({
+  mode: "diff",
+  source: "native",
+  workflowId: "workflow-id",
+  versionId: "8f3c…",
+  toVersionId: "a91d…"
 })
 ```
+Both versions must come from the same source and the same workflow; a mismatch is refused, not silently compared.
 
 ### Rollback to Previous Version
 ```javascript
 n8n_workflow_versions({
   mode: "rollback",
   workflowId: "workflow-id",
   versionId: 123,  // Optional: specific version
-  validateBefore: true  // Default: validate before rollback
+  validateBefore: true  // Default: validate before rollback (local only)
+})
+
+// Native rollback restores n8n's own version; no local validation runs
+n8n_workflow_versions({
+  mode: "rollback",
+  source: "native",
+  workflowId: "workflow-id",
+  versionId: "8f3c…"
 })
 ```
 
 ### Delete Versions
+Local snapshots only (`source: "native"` returns `MODE_NOT_SUPPORTED_FOR_SOURCE`).
 ```javascript
 // Delete specific version
 n8n_workflow_versions({
@@ -594,6 +648,7 @@ n8n_workflow_versions({
 ```
 
 ### Prune Old Versions
+Local snapshots only.
 ```javascript
 n8n_workflow_versions({
   mode: "prune",
@@ -604,32 +659,56 @@ n8n_workflow_versions({
 
 ---
 
-## n8n_test_workflow (TRIGGER EXECUTION)
+## n8n_test_workflow (RUNNING WORKFLOWS)
 
-**Use when**: Testing workflow execution
+**Use when**: Running a workflow to test it
 
-**Auto-detects** trigger type (webhook, form, chat)
+`method` picks the path. `auto` (default) and `trigger` fire a webhook/form/chat trigger over HTTP through the Public API — the workflow must be active. `prepare`, `pinned` and `direct` go through n8n's MCP server (`N8N_MCP_ACCESS_TOKEN`, n8n 2.34+, workflow "Available in MCP") and also work for inactive workflows and workflows without an HTTP trigger. `auto` never runs anything through n8n's MCP server: without an HTTP trigger it reports that the workflow cannot be triggered and names the other methods. See SKILL.md "Running Workflows" for the full method table and the side-effect notes.
 
 ```javascript
-// Test webhook workflow
+// HTTP trigger path (method auto/trigger): the older fields still apply here
 n8n_test_workflow({
   workflowId: "workflow-id",
   triggerType: "webhook",  // Optional: auto-detected
   httpMethod: "POST",
   data: {message: "Hello!"},
   waitForResponse: true,
-  timeout: 120000
+  timeout: 120000          // HTTP trigger path only
 })
 
-// Test chat workflow
 n8n_test_workflow({
   workflowId: "workflow-id",
   triggerType: "chat",
   message: "Hello, AI agent!",
   sessionId: "session-123"  // For conversation continuity
 })
+
+// Which nodes need pinned data (read-only)
+n8n_test_workflow({
+  workflowId: "workflow-id",
+  method: "prepare"
+})
+
+// Run with pinned data standing in for trigger, credentialed and HTTP Request nodes
+n8n_test_workflow({
+  workflowId: "workflow-id",
+  method: "pinned",
+  pinData: {"Webhook": [{"json": {"id": "123"}}]},  // keyed by node name; items wrapped as {json: ...}
+  timeoutMs: 300000         // client deadline for the official call (5000-600000)
+})
+
+// Start a run without a webhook; returns once the run has started
+n8n_test_workflow({
+  workflowId: "workflow-id",
+  method: "direct",
+  data: {message: "Hello!"},
+  triggerNodeName: "Manual Trigger"   // optional; required by n8n when inputs are given
+})
+// then poll: n8n_executions({action: "get", id: executionId})
 ```
 
+`timeout` applies to the HTTP trigger path only; the routed methods use `timeoutMs`. A workflow whose "Available in MCP" setting is off comes back as `WORKFLOW_NOT_EXPOSED`; re-running with `exposeToMcp: true` enables that setting on the workflow (a visible, persistent change — confirm with the user first).
+
 ---
 
 ## n8n_manage_credentials (CREDENTIAL MANAGEMENT)

data/skills/n8n-node-configuration/SKILL.md

@@ -172,7 +172,7 @@ get_node({
 3. Looking for a specific field → `search_properties` mode. Otherwise continue.
 4. Still need more → `get_node({detail: "full"})`.
 
-**Dynamic properties**: when `standard` detail marks a property with `dynamicOptions: {methodName, methodType, dependsOn}`, its real values come from a live `loadOptions`/`listSearch` method, not from bundled docs — don't guess an ID for it. Resolve it with `n8n_explore_node_resources` (pass that `methodName`/`methodType`, plus a `credentialId` from `n8n_manage_credentials({action: "list"})`) and use the returned `value` in the config; `dependsOn` lists which other parameters must already be set before the method returns useful results.
+**Dynamic properties**: when `standard` detail marks a property with `dynamicOptions: {methodName, methodType, dependsOn}`, its real values come from a live `loadOptions`/`listSearch` method, not from bundled docs — don't guess an ID for it. Resolve it with `n8n_explore_node_resources` (needs `N8N_MCP_ACCESS_TOKEN`, n8n 2.34+; pass that `methodName`/`methodType`, plus a `credentialId` from `n8n_manage_credentials({action: "list"})`) and use the returned `value` in the config; `dependsOn` lists which other parameters must already be set before the method returns useful results.
 
 ---
 

data/skills/n8n-validation-expert/SKILL.md

@@ -451,7 +451,7 @@ n8n_autofix_workflow({
 
 ## Running the workflow after it validates
 
-`validate_workflow` checks structure, parameters and expressions — it never runs anything. A workflow that validates clean can still fail on real data, so run it once before calling it done.
+`validate_workflow` checks structure, parameters and expressions — it never runs anything. A workflow that validates cleanly can still fail on real data, so run it once before calling it done.
 
 **With a webhook, form or chat trigger:** `n8n_test_workflow({workflowId})` — the default `method: "auto"` detects the trigger and fires it over HTTP (the workflow must be active).