← VaizCONTENT HISTORY

Update to Vaiz

Snapshot Oct 27, 2026 · 00:52 UTC · version 1.1.0

Collection source: downloaded plugin package.

WHAT CHANGED

Instructions updated for vaiz-documents

Full description — Now says: fragment edits, Markdown with mentions, renaming, moving, archiving, followers,

Observed in instructions or declared skills. Runtime behavior has not been tested.

Save Vaiz and check future changes in Following.

Up to 10 plugins free · no card required.

All fields and original values.

Full description

Before

Oct 24, 2026 · 13:47 UTC

Markdown with mentions,

After

Oct 27, 2026 · 00:52 UTC

fragment edits, Markdown with mentions, renaming, moving, archiving, followers,

Skill instructions

Before

Oct 24, 2026 · 13:47 UTC

Markdown with mentions, threaded comments, and document history. Vaiz tools can appear under different names depending on how Vaiz is connected: `mcp__Vaiz__get_tasks` for a directly configured MCP server, or `mcp__codex_apps__vaiz_get_t...

After

Oct 27, 2026 · 00:52 UTC

fragment edits, Markdown with mentions, renaming, moving, archiving, followers, threaded comments, and document history. Vaiz tools can appear under different names depending on how Vaiz is connected: `mcp__Vaiz__query_tasks` for a direc...

Compare saved observations

Download comparison JSON

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -1,6 +1,6 @@
 ---
 name: vaiz-documents
-description: Read, create, and edit Vaiz documents and comments — standalone documents in personal, project, or space trees, task and milestone descriptions, Markdown with mentions, threaded comments, and document history.
+description: Read, create, and edit Vaiz documents and comments — standalone documents in personal, project, or space trees, task and milestone descriptions, fragment edits, Markdown with mentions, renaming, moving, archiving, followers, threaded comments, and document history.
 ---
 
 # Vaiz documents and comments
@@ -11,17 +11,19 @@
 
 The Vaiz MCP server (`https://api.vaiz.com/mcp`) must be available through the installed Vaiz plugin and authorized with OAuth (open the Vaiz connection and complete OAuth sign-in).
 
-Vaiz tools can appear under different names depending on how Vaiz is connected: `mcp__Vaiz__get_tasks` for a directly configured MCP server, or `mcp__codex_apps__vaiz_get_tasks` (sometimes with a longer app prefix such as `vaiz_testing_`) when Vaiz is installed as an app. Match tool names case-insensitively and by the tool suffix (`get_tasks`, `query_tasks`, …), not by an exact `Vaiz` prefix. Tools may also be loaded lazily: a Vaiz tool that is not in the current tool list is not missing — load it through tool search (for example `Vaiz get_tasks`) before concluding it is unavailable. Work with Vaiz only through these tools: do not open app.vaiz.com in a browser or drive the Vaiz desktop app with Computer Use, even if the user's `@Vaiz` mention also resolves to that app.
+Vaiz tools can appear under different names depending on how Vaiz is connected: `mcp__Vaiz__query_tasks` for a directly configured MCP server, or `mcp__codex_apps__vaiz_query_tasks` (sometimes with a longer app prefix such as `vaiz_testing_`) when Vaiz is installed as an app. Match tool names case-insensitively and by the tool suffix (`query_tasks`, `show_tasks`, …), not by an exact `Vaiz` prefix. Tools may also be loaded lazily: a Vaiz tool that is not in the current tool list is not missing — load it through tool search (for example `Vaiz query_tasks`) before concluding it is unavailable. Work with Vaiz only through these tools: do not open app.vaiz.com in a browser or drive the Vaiz desktop app with Computer Use, even if the user's `@Vaiz` mention also resolves to that app.
 
 ## Two kinds of "documents"
 
-- **User documents** — content your team wrote: standalone docs, task and milestone descriptions. Tools: `get_document`, `create_document`, `edit_document_content`.
-- **System help** — Vaiz's own knowledge base. Do not use `get_document` for it; use `list_resources` and `read_resource` (see the `vaiz-help` skill).
+- **User documents** — content your team wrote: standalone docs, task and milestone descriptions. Tools: `get_document`, `create_document`, `replace_document_fragment`, `edit_document_content`.
+- **System help** — Vaiz's own knowledge base. Do not use `get_document` for it; use `search_knowledge_base` or `read_resource` (see the `vaiz-help` skill).
+
+Task and milestone descriptions belong to their entity: their title comes from `edit_task` / `edit_milestone`, and they cannot be moved, archived, or deleted on their own.
 
 ## Reading
 
-- `get_document(documentId)` — a user document with its parent chain and child documents. Find ids with `search_space(entityType: "document")`.
-- Task and milestone descriptions are returned by `get_task` and `get_milestone`; the document id needed for editing is in that response.
+- `get_document(documentId)` — a user document as Markdown, with its parent chain and child documents. Find ids with `search_space(entityType: "document")`.
+- Task and milestone descriptions: the document id is in `get_task` (`document`) or `get_milestone` (`documentId`).
 - `get_document_comments` — comments on a standalone document; `get_task_comments` for tasks.
 - `get_document_history` — change history of a document.
 - Files referenced inside a document can be read with `read_file` (see `vaiz-files`).
@@ -32,28 +34,48 @@
 
 - `title` (required)
 - `container`: `"personal"` (default, private to you), `"project"` (requires `projectId`), or `"space"` (shared)
-- `description` — initial Markdown content
+- `description` — initial Markdown content; do not start it with a heading that repeats the title
 - `parentDocumentId` — nest under an existing document
 
-Do not use `create_document` for task or milestone descriptions; those documents already exist and are edited with `edit_document_content`.
+Ask where the document should live when the user did not say: a team-facing spec rarely belongs in personal documents. Do not use `create_document` for task or milestone descriptions; those documents already exist.
 
 ## Editing content
 
-`edit_document_content` with `data`:
+Read the document with `get_document` first, then pick the smallest edit:
 
-- `documentId` — from `get_task`, `get_milestone`, or `get_document`
-- `description` — Markdown
-- `replace`: `false` (default) appends to the existing content; `true` replaces it entirely
+| Goal | Tool |
+| --- | --- |
+| Fix a sentence, update a section, insert after a heading, remove a file or image | `replace_document_fragment` |
+| Append to the end | `edit_document_content` (`replace: false`, the default) |
+| Rewrite everything | `edit_document_content` with `replace: true` — only when the user asked for a full rewrite |
+
+`replace_document_fragment` takes `documentId`, `find`, `text`, and `mode` (`replace` by default, `insert_before`, or `insert_after`):
+
+- `find` must be copied verbatim from the `get_document` Markdown, formatting marks included, and must occur exactly once. If it is missing or ambiguous, nothing changes — extend it with neighbouring text and retry.
+- An empty `text` with `replace` deletes the fragment; this is also how you remove a file, image, or video block.
+- Several lines, or a line starting with `#`, `-`, `1.`, `>`, a code fence, or `|`, become separate blocks. A single plain line goes inline; start it with a blank line for `insert_after` to make a new paragraph.
+- Only touched blocks are rebuilt; formatting that Markdown cannot express (colors, alignment) is lost only there. A full `replace: true` loses it everywhere.
 
-Default to appending. Replace only when the user explicitly asks to rewrite, and read the current content first so nothing is lost.
+`edit_document_content` takes a `data` object with `documentId`, `description` (Markdown), and `replace`.
 
 ## Markdown and mentions
 
-Headings, lists, code blocks, and tables are supported. Mention entities with `@[label](kind:id)` where `kind` is `user`, `task`, `document`, `milestone`, `project`, or `board`, for example `@[Anna](user:64f1…)`. Use `list_members` for user ids.
+Headings, lists, code blocks, and tables are supported. Mention entities with `@[label](kind:id)` where `kind` is `user`, `task`, `document`, `milestone`, `project`, or `board`, for example `@[Anna](user:64f1…)`. Use database ids, not HRIDs, inside mentions; get member ids from `query_members`. In `find`, the label of a mention does not matter — it matches by kind and id.
+
+## Organizing the tree
+
+- `edit_document` — rename a standalone document or change its icon.
+- `move_document` — move a document with its subtree within its tree or to another tree (`container` + `projectId`). Omit `parentDocumentId` for the top level and `index` to append at the end.
+- `set_document_archived` — archive (`true`) or restore (`false`); sub-documents go and come back with it. Prefer it over `delete_document`, which is permanent (see `vaiz-safe-changes`).
+- `set_followers` with `entityType: "document"` — subscribe or unsubscribe members; works for standalone documents only.
 
 ## Comments
 
-`create_comment` with `entityType` (`"task"`, `"milestone"`, `"document"`) and `entityId` (task HRID or id; 24-char id for the others). `content` is Markdown. `replyTo` posts a threaded reply under an existing comment. `fileIds` attaches files that were already uploaded to the same entity (see `vaiz-files`); content may be omitted when files are provided.
+- `create_comment` with `entityType` (`"task"`, `"milestone"`, `"document"`) and `entityId` (task HRID or id; 24-char id for the others). `content` is Markdown. `replyTo` posts a threaded reply. `fileIds` attaches files already uploaded to the same entity (see `vaiz-files`); content may be omitted when files are provided.
+- `edit_comment` — replace the text of your own comment and/or detach files with `removeFileIds`.
+- `delete_comment` — delete your own comment; there is no archive for comments.
+
+Mentioning an AI agent (`isAgent: true`) in a **task** comment starts an agent run. Confirm with the user first and report `agentInvocations` from the response (see `vaiz-agents`).
 
 Use a comment for discussion, status, or questions. Use the description for the durable definition of the work.
 
Full technical diff · 2 changed fields

changed /description

BEFORE
"Read, create, and edit Vaiz documents and comments — standalone documents in personal, project, or space trees, task and milestone descriptions, Markdown with mentions, threaded comments, and document history."
AFTER
"Read, create, and edit Vaiz documents and comments — standalone documents in personal, project, or space trees, task and milestone descriptions, fragment edits, Markdown with mentions, renaming, moving, archiving, followers, threaded comments, and document history."

changed /skill_md_contents

BEFORE
"---\nname: vaiz-documents\ndescription: Read, create, and edit Vaiz documents and comments — standalone documents in personal, project, or space trees, task and milestone descriptions, Markdown with mentions, threaded comments, and document history.\n---\n\n# Vaiz documents and comments\n\nEvery task and milestone in Vaiz carries a document (its description). Standalone documents live in a tree that is personal, per project, or shared across the space. All content is written in Markdown.\n\n## Prerequisite\n\nThe Vaiz MCP server (`https://api.vaiz.com/mcp`) must be available through the installed Vaiz plugin and authorized with OAuth (open the Vaiz connection and complete OAuth sign-in).\n\nVaiz tools can appear under different names depending on how Vaiz is connected: `mcp__Vaiz__get_tasks` for a directly configured MCP server, or `mcp__codex_apps__vaiz_get_tasks` (sometimes with a longer app prefix such as `vaiz_testing_`) when Vaiz is installed as an app. Match tool names case-insensitively and by the tool suffix (`get_tasks`, `query_tasks`, …), not by an exact `Vaiz` prefix. Tools may also be loaded lazily: a Vaiz tool that is not in the current tool list is not missing — load it through tool search (for example `Vaiz get_tasks`) before concluding it is unavailable. Work with Vaiz only through these tools: do not open app.vaiz.com in a browser or drive the Vaiz desktop app with Computer Use, even if the user's `@Vaiz` mention also resolves to that app.\n\n## Two kinds of \"documents\"\n\n- **User documents** — content your team wrote: standalone docs, task and milestone descriptions. Tools: `get_document`, `create_document`, `edit_document_content`.\n- **System help** — Vaiz's own knowledge base. Do not use `get_document` for it; use `list_resources` and `read_resource` (see the `vaiz-help` skill).\n\n## Reading\n\n- `get_document(documentId)` — a user document with its parent chain and child documents. Find ids with `search_space(entityType: \"document\")`.\n- Task and milestone descriptions are returned by `get_task` and `get_milestone`; the document id needed for editing is in that response.\n- `get_document_comments` — comments on a standalone document; `get_task_comments` for tasks.\n- `get_document_history` — change history of a document.\n- Files referenced inside a document can be read with `read_file` (see `vaiz-files`).\n\n## Creating a standalone document\n\n`create_document` takes a `data` object:\n\n- `title` (required)\n- `container`: `\"personal\"` (default, private to you), `\"project\"` (requires `projectId`), or `\"space\"` (shared)\n- `description` — initial Markdown content\n- `parentDocumentId` — nest under an existing document\n\nDo not use `create_document` for task or milestone descriptions; those documents already exist and are edited with `edit_document_content`.\n\n## Editing content\n\n`edit_document_content` with `data`:\n\n- `documentId` — from `get_task`, `get_milestone`, or `get_document`\n- `description` — Markdown\n- `replace`: `false` (default) appends to the existing content; `true` replaces it entirely\n\nDefault to appending. Replace only when the user explicitly asks to rewrite, and read the current content first so nothing is lost.\n\n## Markdown and mentions\n\nHeadings, lists, code blocks, and tables are supported. Mention entities with `@[label](kind:id)` where `kind` is `user`, `task`, `document`, `milestone`, `project`, or `board`, for example `@[Anna](user:64f1…)`. Use `list_members` for user ids.\n\n## Comments\n\n`create_comment` with `entityType` (`\"task\"`, `\"milestone\"`, `\"document\"`) and `entityId` (task HRID or id; 24-char id for the others). `content` is Markdown. `replyTo` posts a threaded reply under an existing comment. `fileIds` attaches files that were already uploaded to the same entity (see `vaiz-files`); content may be omitted when files are provided.\n\nUse a comment for discussion, status, or questions. Use the description for the durable definition of the work.\n\n## Good habits\n\n- Search before creating a document; a similar one may already exist.\n- Keep one topic per document and nest related documents with `parentDocumentId`.\n- Decisions and conventions that should be searchable across the space belong in Space Memory (see `vaiz-memories`), possibly with a link back to the document.\n\nFurther reading: https://vaiz.com/help/tutorials/how-to-connect-vaiz-to-mcp · https://vaiz.com\n"
AFTER
"---\nname: vaiz-documents\ndescription: Read, create, and edit Vaiz documents and comments — standalone documents in personal, project, or space trees, task and milestone descriptions, fragment edits, Markdown with mentions, renaming, moving, archiving, followers, threaded comments, and document history.\n---\n\n# Vaiz documents and comments\n\nEvery task and milestone in Vaiz carries a document (its description). Standalone documents live in a tree that is personal, per project, or shared across the space. All content is written in Markdown.\n\n## Prerequisite\n\nThe Vaiz MCP server (`https://api.vaiz.com/mcp`) must be available through the installed Vaiz plugin and authorized with OAuth (open the Vaiz connection and complete OAuth sign-in).\n\nVaiz tools can appear under different names depending on how Vaiz is connected: `mcp__Vaiz__query_tasks` for a directly configured MCP server, or `mcp__codex_apps__vaiz_query_tasks` (sometimes with a longer app prefix such as `vaiz_testing_`) when Vaiz is installed as an app. Match tool names case-insensitively and by the tool suffix (`query_tasks`, `show_tasks`, …), not by an exact `Vaiz` prefix. Tools may also be loaded lazily: a Vaiz tool that is not in the current tool list is not missing — load it through tool search (for example `Vaiz query_tasks`) before concluding it is unavailable. Work with Vaiz only through these tools: do not open app.vaiz.com in a browser or drive the Vaiz desktop app with Computer Use, even if the user's `@Vaiz` mention also resolves to that app.\n\n## Two kinds of \"documents\"\n\n- **User documents** — content your team wrote: standalone docs, task and milestone descriptions. Tools: `get_document`, `create_document`, `replace_document_fragment`, `edit_document_content`.\n- **System help** — Vaiz's own knowledge base. Do not use `get_document` for it; use `search_knowledge_base` or `read_resource` (see the `vaiz-help` skill).\n\nTask and milestone descriptions belong to their entity: their title comes from `edit_task` / `edit_milestone`, and they cannot be moved, archived, or deleted on their own.\n\n## Reading\n\n- `get_document(documentId)` — a user document as Markdown, with its parent chain and child documents. Find ids with `search_space(entityType: \"document\")`.\n- Task and milestone descriptions: the document id is in `get_task` (`document`) or `get_milestone` (`documentId`).\n- `get_document_comments` — comments on a standalone document; `get_task_comments` for tasks.\n- `get_document_history` — change history of a document.\n- Files referenced inside a document can be read with `read_file` (see `vaiz-files`).\n\n## Creating a standalone document\n\n`create_document` takes a `data` object:\n\n- `title` (required)\n- `container`: `\"personal\"` (default, private to you), `\"project\"` (requires `projectId`), or `\"space\"` (shared)\n- `description` — initial Markdown content; do not start it with a heading that repeats the title\n- `parentDocumentId` — nest under an existing document\n\nAsk where the document should live when the user did not say: a team-facing spec rarely belongs in personal documents. Do not use `create_document` for task or milestone descriptions; those documents already exist.\n\n## Editing content\n\nRead the document with `get_document` first, then pick the smallest edit:\n\n| Goal | Tool |\n| --- | --- |\n| Fix a sentence, update a section, insert after a heading, remove a file or image | `replace_document_fragment` |\n| Append to the end | `edit_document_content` (`replace: false`, the default) |\n| Rewrite everything | `edit_document_content` with `replace: true` — only when the user asked for a full rewrite |\n\n`replace_document_fragment` takes `documentId`, `find`, `text`, and `mode` (`replace` by default, `insert_before`, or `insert_after`):\n\n- `find` must be copied verbatim from the `get_document` Markdown, formatting marks included, and must occur exactly once. If it is missing or ambiguous, nothing changes — extend it with neighbouring text and retry.\n- An empty `text` with `replace` deletes the fragment; this is also how you remove a file, image, or video block.\n- Several lines, or a line starting with `#`, `-`, `1.`, `>`, a code fence, or `|`, become separate blocks. A single plain line goes inline; start it with a blank line for `insert_after` to make a new paragraph.\n- Only touched blocks are rebuilt; formatting that Markdown cannot express (colors, alignment) is lost only there. A full `replace: true` loses it everywhere.\n\n`edit_document_content` takes a `data` object with `documentId`, `description` (Markdown), and `replace`.\n\n## Markdown and mentions\n\nHeadings, lists, code blocks, and tables are supported. Mention entities with `@[label](kind:id)` where `kind` is `user`, `task`, `document`, `milestone`, `project`, or `board`, for example `@[Anna](user:64f1…)`. Use database ids, not HRIDs, inside mentions; get member ids from `query_members`. In `find`, the label of a mention does not matter — it matches by kind and id.\n\n## Organizing the tree\n\n- `edit_document` — rename a standalone document or change its icon.\n- `move_document` — move a document with its subtree within its tree or to another tree (`container` + `projectId`). Omit `parentDocumentId` for the top level and `index` to append at the end.\n- `set_document_archived` — archive (`true`) or restore (`false`); sub-documents go and come back with it. Prefer it over `delete_document`, which is permanent (see `vaiz-safe-changes`).\n- `set_followers` with `entityType: \"document\"` — subscribe or unsubscribe members; works for standalone documents only.\n\n## Comments\n\n- `create_comment` with `entityType` (`\"task\"`, `\"milestone\"`, `\"document\"`) and `entityId` (task HRID or id; 24-char id for the others). `content` is Markdown. `replyTo` posts a threaded reply. `fileIds` attaches files already uploaded to the same entity (see `vaiz-files`); content may be omitted when files are provided.\n- `edit_comment` — replace the text of your own comment and/or detach files with `removeFileIds`.\n- `delete_comment` — delete your own comment; there is no archive for comments.\n\nMentioning an AI agent (`isAgent: true`) in a **task** comment starts an agent run. Confirm with the user first and report `agentInvocations` from the response (see `vaiz-agents`).\n\nUse a comment for discussion, status, or questions. Use the description for the durable definition of the work.\n\n## Good habits\n\n- Search before creating a document; a similar one may already exist.\n- Keep one topic per document and nest related documents with `parentDocumentId`.\n- Decisions and conventions that should be searchable across the space belong in Space Memory (see `vaiz-memories`), possibly with a link back to the document.\n\nFurther reading: https://vaiz.com/help/tutorials/how-to-connect-vaiz-to-mcp · https://vaiz.com\n"
Full snapshot data
{
  "description": "Read, create, and edit Vaiz documents and comments — standalone documents in personal, project, or space trees, task and milestone descriptions, fragment edits, Markdown with mentions, renaming, moving, archiving, followers, threaded comments, and document history.",
  "included_files": [],
  "name": "vaiz-documents",
  "skill_md_contents": "---\nname: vaiz-documents\ndescription: Read, create, and edit Vaiz documents and comments — standalone documents in personal, project, or space trees, task and milestone descriptions, fragment edits, Markdown with mentions, renaming, moving, archiving, followers, threaded comments, and document history.\n---\n\n# Vaiz documents and comments\n\nEvery task and milestone in Vaiz carries a document (its description). Standalone documents live in a tree that is personal, per project, or shared across the space. All content is written in Markdown.\n\n## Prerequisite\n\nThe Vaiz MCP server (`https://api.vaiz.com/mcp`) must be available through the installed Vaiz plugin and authorized with OAuth (open the Vaiz connection and complete OAuth sign-in).\n\nVaiz tools can appear under different names depending on how Vaiz is connected: `mcp__Vaiz__query_tasks` for a directly configured MCP server, or `mcp__codex_apps__vaiz_query_tasks` (sometimes with a longer app prefix such as `vaiz_testing_`) when Vaiz is installed as an app. Match tool names case-insensitively and by the tool suffix (`query_tasks`, `show_tasks`, …), not by an exact `Vaiz` prefix. Tools may also be loaded lazily: a Vaiz tool that is not in the current tool list is not missing — load it through tool search (for example `Vaiz query_tasks`) before concluding it is unavailable. Work with Vaiz only through these tools: do not open app.vaiz.com in a browser or drive the Vaiz desktop app with Computer Use, even if the user's `@Vaiz` mention also resolves to that app.\n\n## Two kinds of \"documents\"\n\n- **User documents** — content your team wrote: standalone docs, task and milestone descriptions. Tools: `get_document`, `create_document`, `replace_document_fragment`, `edit_document_content`.\n- **System help** — Vaiz's own knowledge base. Do not use `get_document` for it; use `search_knowledge_base` or `read_resource` (see the `vaiz-help` skill).\n\nTask and milestone descriptions belong to their entity: their title comes from `edit_task` / `edit_milestone`, and they cannot be moved, archived, or deleted on their own.\n\n## Reading\n\n- `get_document(documentId)` — a user document as Markdown, with its parent chain and child documents. Find ids with `search_space(entityType: \"document\")`.\n- Task and milestone descriptions: the document id is in `get_task` (`document`) or `get_milestone` (`documentId`).\n- `get_document_comments` — comments on a standalone document; `get_task_comments` for tasks.\n- `get_document_history` — change history of a document.\n- Files referenced inside a document can be read with `read_file` (see `vaiz-files`).\n\n## Creating a standalone document\n\n`create_document` takes a `data` object:\n\n- `title` (required)\n- `container`: `\"personal\"` (default, private to you), `\"project\"` (requires `projectId`), or `\"space\"` (shared)\n- `description` — initial Markdown content; do not start it with a heading that repeats the title\n- `parentDocumentId` — nest under an existing document\n\nAsk where the document should live when the user did not say: a team-facing spec rarely belongs in personal documents. Do not use `create_document` for task or milestone descriptions; those documents already exist.\n\n## Editing content\n\nRead the document with `get_document` first, then pick the smallest edit:\n\n| Goal | Tool |\n| --- | --- |\n| Fix a sentence, update a section, insert after a heading, remove a file or image | `replace_document_fragment` |\n| Append to the end | `edit_document_content` (`replace: false`, the default) |\n| Rewrite everything | `edit_document_content` with `replace: true` — only when the user asked for a full rewrite |\n\n`replace_document_fragment` takes `documentId`, `find`, `text`, and `mode` (`replace` by default, `insert_before`, or `insert_after`):\n\n- `find` must be copied verbatim from the `get_document` Markdown, formatting marks included, and must occur exactly once. If it is missing or ambiguous, nothing changes — extend it with neighbouring text and retry.\n- An empty `text` with `replace` deletes the fragment; this is also how you remove a file, image, or video block.\n- Several lines, or a line starting with `#`, `-`, `1.`, `>`, a code fence, or `|`, become separate blocks. A single plain line goes inline; start it with a blank line for `insert_after` to make a new paragraph.\n- Only touched blocks are rebuilt; formatting that Markdown cannot express (colors, alignment) is lost only there. A full `replace: true` loses it everywhere.\n\n`edit_document_content` takes a `data` object with `documentId`, `description` (Markdown), and `replace`.\n\n## Markdown and mentions\n\nHeadings, lists, code blocks, and tables are supported. Mention entities with `@[label](kind:id)` where `kind` is `user`, `task`, `document`, `milestone`, `project`, or `board`, for example `@[Anna](user:64f1…)`. Use database ids, not HRIDs, inside mentions; get member ids from `query_members`. In `find`, the label of a mention does not matter — it matches by kind and id.\n\n## Organizing the tree\n\n- `edit_document` — rename a standalone document or change its icon.\n- `move_document` — move a document with its subtree within its tree or to another tree (`container` + `projectId`). Omit `parentDocumentId` for the top level and `index` to append at the end.\n- `set_document_archived` — archive (`true`) or restore (`false`); sub-documents go and come back with it. Prefer it over `delete_document`, which is permanent (see `vaiz-safe-changes`).\n- `set_followers` with `entityType: \"document\"` — subscribe or unsubscribe members; works for standalone documents only.\n\n## Comments\n\n- `create_comment` with `entityType` (`\"task\"`, `\"milestone\"`, `\"document\"`) and `entityId` (task HRID or id; 24-char id for the others). `content` is Markdown. `replyTo` posts a threaded reply. `fileIds` attaches files already uploaded to the same entity (see `vaiz-files`); content may be omitted when files are provided.\n- `edit_comment` — replace the text of your own comment and/or detach files with `removeFileIds`.\n- `delete_comment` — delete your own comment; there is no archive for comments.\n\nMentioning an AI agent (`isAgent: true`) in a **task** comment starts an agent run. Confirm with the user first and report `agentInvocations` from the response (see `vaiz-agents`).\n\nUse a comment for discussion, status, or questions. Use the description for the durable definition of the work.\n\n## Good habits\n\n- Search before creating a document; a similar one may already exist.\n- Keep one topic per document and nest related documents with `parentDocumentId`.\n- Decisions and conventions that should be searchable across the space belong in Space Memory (see `vaiz-memories`), possibly with a link back to the document.\n\nFurther reading: https://vaiz.com/help/tutorials/how-to-connect-vaiz-to-mcp · https://vaiz.com\n"
}

SHA-256 of public snapshot: 6557b274cead66e89cd6f0c1818c2a7dd9092d5594658a9b9a3d629fa3e441e0