소스 정보
- 저장소
- vellum-ai/vellum-assistant
- 최근 소스 활동
- 2026년 6월 15일 22:50
- 감지된 SKILL.md 언어
- 영어
- 스타
- 1,091
- 포크
- 160
설치 방법
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
소스 파일 검토
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
메뉴
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/vellum-ai/vellum-assistant --skill notion명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
Use when the user wants to build, scaffold, ship, or edit a Vellum plugin that bundles multiple surfaces (hooks, tools, skills, and more) into one installable package.
Perform a one-time migration from memory v1, to memory v2, which was introduced in 0.8.0.
Migrate from ChatGPT, Claude, OpenClaw, Hermes, Manus, and other AI assistants into Vellum by inspecting their data exports, conversation archives, files, prompts, custom instructions, memory, saved memories, tools, GPTs, workflows, integrations, and relationships, then mapping as much as safely possible into Vellum primitives. Handles single-source and multi-source migrations with a unified, deduplicated inventory.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | notion |
| description | Read and write Notion pages and databases using the Notion API |
| compatibility | Designed for Vellum personal assistants |
| metadata | {"icon":"assets/icon.svg","emoji":"📝","vellum":{"category":"productivity","display-name":"Notion","activation-hints":["User asks to read, find, search, or open a page, doc, database, or directory in their Notion (e.g. 'find it in notion', 'look in my Notion', 'this is a notion directory')","User references Notion content by name or path and wants its contents pulled","User wants to create, update, append to, or query Notion pages or databases","User asks anything that requires reading or writing Notion data, including checking a task list or workspace held in Notion"],"avoid-when":["User wants to set up, connect, or reconnect the Notion OAuth integration for the first time; load vellum-oauth-integrations instead"]}} |
You have access to the Notion API via the managed OAuth connection or an internal integration secret stored in the credential vault. Both paths inject the Authorization header automatically. Never reveal credential values or echo token values into the shell.
Step 1 - Determine connection type:
assistant credentials list
Look at the results to decide which path to use:
service: "notion" entry is needed in the vault. The OAuth connection is managed by the platform. Use Path A below.service: "notion" and field: "internal_secret" is present. Use Path A below (recommended) or Path B if the credential has the required metadata (see Path B for details).Step 2 - Make authenticated API calls:
Choose the path that matches what you found in Step 1.
Use assistant oauth request --provider notion. The Authorization header is injected automatically; do not supply it manually.
assistant oauth request --provider notion \
-X POST \
-H "Notion-Version: 2022-06-28" \
-H "Content-Type: application/json" \
-d '{}' \
https://api.notion.com/v1/search
General shape: assistant oauth request --provider notion -X <METHOD> -H "Notion-Version: 2022-06-28" [-H "Content-Type: application/json"] [-d '<json-body>'] <url>
https://api.notion.com/v1/pages/...) or relative (/v1/pages/...).-d accepts inline JSON, @filename, or @- for stdin.Note: The standard Notion setup flow (
vellum-oauth-integrations) does not currently produce credentials with the metadata required by this path. Most users should use Path A instead. Path B is documented for credentials that have been manually configured with the required metadata.
For internal integration secrets registered with allowedTools: ["bash"] and an injection_templates entry for api.notion.com. The proxy adds Authorization: Bearer <token> automatically. Do not include an Authorization header in the curl command.
bash:
network_mode: proxied
credential_ids: ["<credential_id_from_step_1>"]
command: |
curl -s -X POST https://api.notion.com/v1/search \
-H "Notion-Version: 2022-06-28" \
-H "Content-Type: application/json" \
-d '{}'
Where <credential_id_from_step_1> is the id field from the matching entry in assistant credentials list output.
The credential MUST have:
allowedTools including "bash" (otherwise the proxy blocks the call).injection_templates with host pattern api.notion.com and header injection type for Authorization.If these are missing, you will get a credential tool policy denied error. Switch to Path A instead.
All Notion API calls go to https://api.notion.com/v1/. Always include the Notion-Version: 2022-06-28 header.
GET https://api.notion.com/v1/pages/{page_id}
Returns page properties. Use the page ID from a Notion URL - the last segment of the URL, e.g. for https://notion.so/My-Page-abc123def456 the ID is abc123def456 (formatted as UUID: abc123de-f456-...).
GET https://api.notion.com/v1/blocks/{block_id}/children?page_size=100
Pages are blocks too - use the page ID as the block_id. Iterates through the page's child blocks. Use start_cursor for pagination when has_more is true.
Block types and how to render them:
paragraph: Read paragraph.rich_text[].plain_textheading_1, heading_2, heading_3: Read heading_N.rich_text[].plain_textbulleted_list_item, numbered_list_item: Read *.rich_text[].plain_textto_do: Read to_do.rich_text[].plain_text and to_do.checkedtoggle: Read toggle.rich_text[].plain_text; children are nested blockscode: Read code.rich_text[].plain_text and code.languagequote: Read quote.rich_text[].plain_textcallout: Read callout.rich_text[].plain_textdivider: Render as ---image: Read image.external.url or image.file.urlchild_page: Read child_page.title; use its id to recursively fetch if neededPOST https://api.notion.com/v1/search
{
"query": "your search term",
"filter": { "value": "page", "property": "object" },
"sort": { "direction": "descending", "timestamp": "last_edited_time" },
"page_size": 10
}
Omit filter to search both pages and databases. Use filter.value: "database" to search only databases.
Returns results[] with id, url, properties.title (for pages), and title[] (for databases).
GET https://api.notion.com/v1/databases/{database_id}
Returns the database schema (all property definitions).
POST https://api.notion.com/v1/databases/{database_id}/query
{
"filter": {
"property": "Status",
"select": { "equals": "In Progress" }
},
"sorts": [
{ "property": "Created", "direction": "descending" }
],
"page_size": 20
}
Omit filter to retrieve all rows. Returns results[] where each item is a page (database row).
Extracting property values from database rows:
title: properties.Name.title[].plain_textrich_text: properties.Notes.rich_text[].plain_textnumber: properties.Price.numberselect: properties.Status.select.namemulti_select: properties.Tags.multi_select[].namedate: properties.Due.date.start (ISO 8601)checkbox: properties.Done.checkboxurl: properties.Link.urlemail: properties.Email.emailpeople: properties.Owner.people[].namerelation: properties.Projects.relation[].id (array of page IDs)POST https://api.notion.com/v1/pages
{
"parent": { "page_id": "<parent_page_id>" },
"properties": {
"title": {
"title": [{ "text": { "content": "My New Page" } }]
}
},
"children": [
{
"object": "block",
"type": "paragraph",
"paragraph": {
"rich_text": [{ "text": { "content": "Page content here." } }]
}
}
]
}
For database rows, use "parent": { "database_id": "<database_id>" } and include the database's required properties.
PATCH https://api.notion.com/v1/pages/{page_id}
{
"properties": {
"Status": { "select": { "name": "Done" } },
"Due": { "date": { "start": "2024-12-31" } }
}
}
PATCH https://api.notion.com/v1/blocks/{block_id}/children
{
"children": [
{
"object": "block",
"type": "paragraph",
"paragraph": {
"rich_text": [{ "text": { "content": "Appended content." } }]
}
},
{
"object": "block",
"type": "heading_2",
"heading_2": {
"rich_text": [{ "text": { "content": "A heading" } }]
}
},
{
"object": "block",
"type": "bulleted_list_item",
"bulleted_list_item": {
"rich_text": [{ "text": { "content": "A bullet point" } }]
}
},
{
"object": "block",
"type": "to_do",
"to_do": {
"rich_text": [{ "text": { "content": "A task" } }],
"checked": false
}
}
]
}
PATCH https://api.notion.com/v1/blocks/{block_id}
{
"paragraph": {
"rich_text": [{ "text": { "content": "Updated text." } }]
}
}
DELETE https://api.notion.com/v1/blocks/{block_id}
Notion does not permanently delete pages via the API - it archives them:
PATCH https://api.notion.com/v1/pages/{page_id}
{
"archived": true
}
When a response includes "has_more": true, pass "start_cursor": response.next_cursor in the next request to get the next page of results.
message field with details.credential tool policy denied: The credential is missing bash in allowedTools or an injection_templates entry for api.notion.com, so the proxy cannot inject the Authorization header. Switch to Path A (managed OAuth), which bypasses credential metadata requirements entirely.abc123def456... or abc123de-f456-....Notion-Version: 2022-06-28 header to get stable API behavior.plain_text values in the array to get the full text content.annotations and href fields in rich_text objects.