Update to OneNote
Snapshot Oct 24, 2026 · 12:48 UTC · version 0.1.6
Collection source: downloaded plugin package. These snapshots do not have a confirmed matching collection source. Differences in file lists alone do not establish changes to the package.
Instructions updated for onenote
Skill instructions — Now says: URL. Continue `next_skip` even when a page contains no owned locations. If a named location remains unavailable, explain the access boundary and request a...
Observed in instructions or declared skills. Runtime behavior has not been tested.
Up to 3 plugins free · no card required.
All fields and original values.
Skill instructions
Sep 30, 2026 · 22:47 UTC
URL. - Use `search_pages_by_title` only for case-insensitive title matching. For a body-content request, use `search_pages_by_text` with the narrowest known section and date window, then continue with `next_skip` only when broader covera...
Oct 24, 2026 · 12:48 UTC
URL. Continue `next_skip` even when a page contains no owned locations. If a named location remains unavailable, explain the access boundary and request a known group/site location or refreshed connection; do not create a replacement not...
Compare saved observations
Download comparison JSONSKILL.md text changes
− removed · + added
--- before +++ after @@ -6,14 +6,15 @@ # OneNote - For requests to export, back up, archive, download, or migrate OneNote content to Markdown or Obsidian, use [Export OneNote to Markdown](../export-onenote-to-markdown/SKILL.md). The live `export_page_as_markdown` action exports one personal page at a time as a downloadable Markdown file; do not promise a ZIP, direct Obsidian-vault write, embedded resources, or shared-page export. -- Start with the narrowest discovery path. Use `list_notebooks`, then `list_sections` and `list_section_groups` for a named personal notebook; use `list_pages` for a known section or a bounded recent-page window. Match returned IDs, titles, parent metadata, and web URLs rather than guessing opaque IDs from a browser URL. -- Use `search_pages_by_title` only for case-insensitive title matching. For a body-content request, use `search_pages_by_text` with the narrowest known section and date window, then continue with `next_skip` only when broader coverage is needed. It scans at most ten owner-verified personal pages per call, searches sanitized visible text rather than raw HTML, and is not a global native index; say when pagination or truncation leaves the search incomplete. -- Prefer `get_page_text` for visible paragraph-like text, checklist tags, and addressable blocks; use `get_page_tables` for table structure, `find_page_text` for one exact case-sensitive occurrence in one known page, and `fetch_page` when the original bounded HTML is needed. Use `fetch_page_resource` only with both the page ID and exact resource ID observed in that page's current content. +- Start with the narrowest discovery path. Use `list_notebooks`, then `list_sections` and `list_section_groups` for a named personal notebook; use `list_pages` for a known section or a bounded recent-page window. Match returned IDs, titles, parent metadata, and web URLs rather than guessing opaque IDs from a browser URL. Continue `next_skip` even when a page contains no owned locations. If a named location remains unavailable, explain the access boundary and request a known group/site location or refreshed connection; do not create a replacement notebook. +- Use `search_pages_by_title` only for case-insensitive title matching. For a body-content request, use `search_pages_by_text` with the narrowest known section and date window, then continue with `next_skip` only when broader coverage is needed. Use `created_after` and `created_before` for when a page was created; use `modified_after` and `modified_before` for its last edit. It scans at most ten owner-verified personal pages per call, searches sanitized visible text rather than raw HTML, and is not a global native index; say when pagination or truncation leaves the search incomplete. +- Prefer `get_page_text` for visible text, checklist tags, and addressable blocks; use `get_page_tables` for table structure and `fetch_page` for bounded HTML. For images, pass a non-null `images[].resource_id` from a fresh structured read to `fetch_page_resource`. Use `list_page_resources` to discover audio, video, attachments, or additional images, then pass its resource ID, file name, and media type hint with the page ID to `fetch_page_resource`. Inspect downloaded images before describing their contents; these tools do not decode native ink strokes. Empty text and tables do not establish that a page is blank when its resource manifest is nonempty. - Raw `fetch_page` HTML can contain non-visible provider markup; do not surface it or choose it as an update target, and rely on visible structured extractors for user-visible content. -- Personal-only discovery, read, export, hierarchy, and update actions operate only on notebooks owned by the signed-in Microsoft account; they intentionally omit directly shared personal notebooks. Treat the mixed `create_page` and `copy_page_to_section` actions as shared-capable. For a Microsoft 365 group or SharePoint site notebook, require a known `resource_type` and `resource_id`, then use `list_shared_notebooks`, `list_shared_sections`, `list_shared_section_groups`, `list_shared_pages`, and `fetch_shared_page`. Do not pass shared-page IDs to personal-only page actions or imply a shared structured extractor that is not present in the live tool surface. +- Personal-only discovery, read, export, hierarchy, and update actions operate only on notebooks owned by the signed-in Microsoft account; they intentionally omit directly shared personal notebooks. `create_page` supports known group or site destinations, while `copy_page_to_section` supports personal or Microsoft 365 group roots only. For a Microsoft 365 group or SharePoint site notebook, require a known `resource_type` and `resource_id`, then use `list_shared_notebooks`, `list_shared_sections`, `list_shared_section_groups`, `list_shared_pages`, and `fetch_shared_page`. Do not pass shared-page IDs to personal-only page actions or imply a shared structured extractor or resource downloader that is not present in the live tool surface. - Before a targeted edit, read a fresh snapshot with element IDs or structured update targets. Use `update_page` or `update_shared_page` for exact insert, replace, prepend, or append operations, and re-read after any mutation because targets can become stale. - Use `append_to_page` or `append_to_shared_page` for simple additive notes. Use `add_page_resources` on a personal page for staged images, PDF printouts, or attachments, and keep the supplied filenames and MIME types accurate. - Use `create_notebook`, `create_section_group`, and `create_section` only in the destination the user selected; `create_page` can target a personal section or a known shared section. Use simple OneNote-compatible HTML for new content, and disambiguate similarly named notebooks, sections, or pages before writing. -- Treat page copying as asynchronous: call `copy_page_to_section`, retain its returned operation reference, and poll `get_operation` until it reaches a terminal state. Never report the copy as complete from the initial accepted response. +- Treat page copying as non-idempotent and asynchronous. Snapshot destination page IDs when feasible, call `copy_page_to_section` once, retain its operation reference, and poll that reference with `get_operation` until a terminal state. An explicit HTTP 429 rejects the copy request: wait for `Retry-After`, or use exponential backoff if absent, before retrying that request. Retry transient or 404 polling failures using the same reference; do not restart the copy. If the copy outcome is unknown or Microsoft accepted the copy without a usable reference, inspect the exact destination before retrying or using `create_page` as a fallback. Report uncertainty if pagination or matching cannot rule out an existing copy. Never report completion from the initial accepted response. +- OneNote exposes no notebook ACL, invite, or share-link action. `list_shared_notebooks` browses existing access; it does not grant it. For an explicit sharing request, use an available SharePoint or OneDrive permission tool with the resolved backing item and recipient. The notebook's web URL can be passed to that connector for resolution; do not derive a backing-item ID from a OneNote notebook ID. If resolution is unavailable, explain the limitation and direct the user to Microsoft. - Use `next_skip` for bounded pagination; never invoke or reconstruct an opaque `next_link` URL. - Read-only requests do not authorize edits. Confirm the exact target and intended change before a consequential write, and require explicit confirmation immediately before `delete_page` because deletion is permanent.
Full technical diff · 1 changed fields
changed /skill_md_contents
"---\nname: onenote\ndescription: Use when asked to find, read, summarize, create, organize, update, export, back up, archive, or migrate Microsoft OneNote notebooks, sections, pages, tables, checklists, and shared group or site notes; also for copying a known page, attaching files to a personal page, or deleting a personal page.\n---\n\n# OneNote\n\n- For requests to export, back up, archive, download, or migrate OneNote content to Markdown or Obsidian, use [Export OneNote to Markdown](../export-onenote-to-markdown/SKILL.md). The live `export_page_as_markdown` action exports one personal page at a time as a downloadable Markdown file; do not promise a ZIP, direct Obsidian-vault write, embedded resources, or shared-page export.\n- Start with the narrowest discovery path. Use `list_notebooks`, then `list_sections` and `list_section_groups` for a named personal notebook; use `list_pages` for a known section or a bounded recent-page window. Match returned IDs, titles, parent metadata, and web URLs rather than guessing opaque IDs from a browser URL.\n- Use `search_pages_by_title` only for case-insensitive title matching. For a body-content request, use `search_pages_by_text` with the narrowest known section and date window, then continue with `next_skip` only when broader coverage is needed. It scans at most ten owner-verified personal pages per call, searches sanitized visible text rather than raw HTML, and is not a global native index; say when pagination or truncation leaves the search incomplete.\n- Prefer `get_page_text` for visible paragraph-like text, checklist tags, and addressable blocks; use `get_page_tables` for table structure, `find_page_text` for one exact case-sensitive occurrence in one known page, and `fetch_page` when the original bounded HTML is needed. Use `fetch_page_resource` only with both the page ID and exact resource ID observed in that page's current content.\n- Raw `fetch_page` HTML can contain non-visible provider markup; do not surface it or choose it as an update target, and rely on visible structured extractors for user-visible content.\n- Personal-only discovery, read, export, hierarchy, and update actions operate only on notebooks owned by the signed-in Microsoft account; they intentionally omit directly shared personal notebooks. Treat the mixed `create_page` and `copy_page_to_section` actions as shared-capable. For a Microsoft 365 group or SharePoint site notebook, require a known `resource_type` and `resource_id`, then use `list_shared_notebooks`, `list_shared_sections`, `list_shared_section_groups`, `list_shared_pages`, and `fetch_shared_page`. Do not pass shared-page IDs to personal-only page actions or imply a shared structured extractor that is not present in the live tool surface.\n- Before a targeted edit, read a fresh snapshot with element IDs or structured update targets. Use `update_page` or `update_shared_page` for exact insert, replace, prepend, or append operations, and re-read after any mutation because targets can become stale.\n- Use `append_to_page` or `append_to_shared_page` for simple additive notes. Use `add_page_resources` on a personal page for staged images, PDF printouts, or attachments, and keep the supplied filenames and MIME types accurate.\n- Use `create_notebook`, `create_section_group`, and `create_section` only in the destination the user selected; `create_page` can target a personal section or a known shared section. Use simple OneNote-compatible HTML for new content, and disambiguate similarly named notebooks, sections, or pages before writing.\n- Treat page copying as asynchronous: call `copy_page_to_section`, retain its returned operation reference, and poll `get_operation` until it reaches a terminal state. Never report the copy as complete from the initial accepted response.\n- Use `next_skip` for bounded pagination; never invoke or reconstruct an opaque `next_link` URL.\n- Read-only requests do not authorize edits. Confirm the exact target and intended change before a consequential write, and require explicit confirmation immediately before `delete_page` because deletion is permanent.\n"
"---\nname: onenote\ndescription: Use when asked to find, read, summarize, create, organize, update, export, back up, archive, or migrate Microsoft OneNote notebooks, sections, pages, tables, checklists, and shared group or site notes; also for copying a known page, attaching files to a personal page, or deleting a personal page.\n---\n\n# OneNote\n\n- For requests to export, back up, archive, download, or migrate OneNote content to Markdown or Obsidian, use [Export OneNote to Markdown](../export-onenote-to-markdown/SKILL.md). The live `export_page_as_markdown` action exports one personal page at a time as a downloadable Markdown file; do not promise a ZIP, direct Obsidian-vault write, embedded resources, or shared-page export.\n- Start with the narrowest discovery path. Use `list_notebooks`, then `list_sections` and `list_section_groups` for a named personal notebook; use `list_pages` for a known section or a bounded recent-page window. Match returned IDs, titles, parent metadata, and web URLs rather than guessing opaque IDs from a browser URL. Continue `next_skip` even when a page contains no owned locations. If a named location remains unavailable, explain the access boundary and request a known group/site location or refreshed connection; do not create a replacement notebook.\n- Use `search_pages_by_title` only for case-insensitive title matching. For a body-content request, use `search_pages_by_text` with the narrowest known section and date window, then continue with `next_skip` only when broader coverage is needed. Use `created_after` and `created_before` for when a page was created; use `modified_after` and `modified_before` for its last edit. It scans at most ten owner-verified personal pages per call, searches sanitized visible text rather than raw HTML, and is not a global native index; say when pagination or truncation leaves the search incomplete.\n- Prefer `get_page_text` for visible text, checklist tags, and addressable blocks; use `get_page_tables` for table structure and `fetch_page` for bounded HTML. For images, pass a non-null `images[].resource_id` from a fresh structured read to `fetch_page_resource`. Use `list_page_resources` to discover audio, video, attachments, or additional images, then pass its resource ID, file name, and media type hint with the page ID to `fetch_page_resource`. Inspect downloaded images before describing their contents; these tools do not decode native ink strokes. Empty text and tables do not establish that a page is blank when its resource manifest is nonempty.\n- Raw `fetch_page` HTML can contain non-visible provider markup; do not surface it or choose it as an update target, and rely on visible structured extractors for user-visible content.\n- Personal-only discovery, read, export, hierarchy, and update actions operate only on notebooks owned by the signed-in Microsoft account; they intentionally omit directly shared personal notebooks. `create_page` supports known group or site destinations, while `copy_page_to_section` supports personal or Microsoft 365 group roots only. For a Microsoft 365 group or SharePoint site notebook, require a known `resource_type` and `resource_id`, then use `list_shared_notebooks`, `list_shared_sections`, `list_shared_section_groups`, `list_shared_pages`, and `fetch_shared_page`. Do not pass shared-page IDs to personal-only page actions or imply a shared structured extractor or resource downloader that is not present in the live tool surface.\n- Before a targeted edit, read a fresh snapshot with element IDs or structured update targets. Use `update_page` or `update_shared_page` for exact insert, replace, prepend, or append operations, and re-read after any mutation because targets can become stale.\n- Use `append_to_page` or `append_to_shared_page` for simple additive notes. Use `add_page_resources` on a personal page for staged images, PDF printouts, or attachments, and keep the supplied filenames and MIME types accurate.\n- Use `create_notebook`, `create_section_group`, and `create_section` only in the destination the user selected; `create_page` can target a personal section or a known shared section. Use simple OneNote-compatible HTML for new content, and disambiguate similarly named notebooks, sections, or pages before writing.\n- Treat page copying as non-idempotent and asynchronous. Snapshot destination page IDs when feasible, call `copy_page_to_section` once, retain its operation reference, and poll that reference with `get_operation` until a terminal state. An explicit HTTP 429 rejects the copy request: wait for `Retry-After`, or use exponential backoff if absent, before retrying that request. Retry transient or 404 polling failures using the same reference; do not restart the copy. If the copy outcome is unknown or Microsoft accepted the copy without a usable reference, inspect the exact destination before retrying or using `create_page` as a fallback. Report uncertainty if pagination or matching cannot rule out an existing copy. Never report completion from the initial accepted response.\n- OneNote exposes no notebook ACL, invite, or share-link action. `list_shared_notebooks` browses existing access; it does not grant it. For an explicit sharing request, use an available SharePoint or OneDrive permission tool with the resolved backing item and recipient. The notebook's web URL can be passed to that connector for resolution; do not derive a backing-item ID from a OneNote notebook ID. If resolution is unavailable, explain the limitation and direct the user to Microsoft.\n- Use `next_skip` for bounded pagination; never invoke or reconstruct an opaque `next_link` URL.\n- Read-only requests do not authorize edits. Confirm the exact target and intended change before a consequential write, and require explicit confirmation immediately before `delete_page` because deletion is permanent.\n"
Full snapshot data
{
"description": "Use when asked to find, read, summarize, create, organize, update, export, back up, archive, or migrate Microsoft OneNote notebooks, sections, pages, tables, checklists, and shared group or site notes; also for copying a known page, attaching files to a personal page, or deleting a personal page.",
"included_files": [
{
"relative_path": "agents/openai.yaml",
"size_in_bytes": 378
},
{
"relative_path": "assets/onenote-small.svg",
"size_in_bytes": 645
},
{
"relative_path": "assets/onenote.svg",
"size_in_bytes": 645
}
],
"name": "onenote",
"skill_md_contents": "---\nname: onenote\ndescription: Use when asked to find, read, summarize, create, organize, update, export, back up, archive, or migrate Microsoft OneNote notebooks, sections, pages, tables, checklists, and shared group or site notes; also for copying a known page, attaching files to a personal page, or deleting a personal page.\n---\n\n# OneNote\n\n- For requests to export, back up, archive, download, or migrate OneNote content to Markdown or Obsidian, use [Export OneNote to Markdown](../export-onenote-to-markdown/SKILL.md). The live `export_page_as_markdown` action exports one personal page at a time as a downloadable Markdown file; do not promise a ZIP, direct Obsidian-vault write, embedded resources, or shared-page export.\n- Start with the narrowest discovery path. Use `list_notebooks`, then `list_sections` and `list_section_groups` for a named personal notebook; use `list_pages` for a known section or a bounded recent-page window. Match returned IDs, titles, parent metadata, and web URLs rather than guessing opaque IDs from a browser URL. Continue `next_skip` even when a page contains no owned locations. If a named location remains unavailable, explain the access boundary and request a known group/site location or refreshed connection; do not create a replacement notebook.\n- Use `search_pages_by_title` only for case-insensitive title matching. For a body-content request, use `search_pages_by_text` with the narrowest known section and date window, then continue with `next_skip` only when broader coverage is needed. Use `created_after` and `created_before` for when a page was created; use `modified_after` and `modified_before` for its last edit. It scans at most ten owner-verified personal pages per call, searches sanitized visible text rather than raw HTML, and is not a global native index; say when pagination or truncation leaves the search incomplete.\n- Prefer `get_page_text` for visible text, checklist tags, and addressable blocks; use `get_page_tables` for table structure and `fetch_page` for bounded HTML. For images, pass a non-null `images[].resource_id` from a fresh structured read to `fetch_page_resource`. Use `list_page_resources` to discover audio, video, attachments, or additional images, then pass its resource ID, file name, and media type hint with the page ID to `fetch_page_resource`. Inspect downloaded images before describing their contents; these tools do not decode native ink strokes. Empty text and tables do not establish that a page is blank when its resource manifest is nonempty.\n- Raw `fetch_page` HTML can contain non-visible provider markup; do not surface it or choose it as an update target, and rely on visible structured extractors for user-visible content.\n- Personal-only discovery, read, export, hierarchy, and update actions operate only on notebooks owned by the signed-in Microsoft account; they intentionally omit directly shared personal notebooks. `create_page` supports known group or site destinations, while `copy_page_to_section` supports personal or Microsoft 365 group roots only. For a Microsoft 365 group or SharePoint site notebook, require a known `resource_type` and `resource_id`, then use `list_shared_notebooks`, `list_shared_sections`, `list_shared_section_groups`, `list_shared_pages`, and `fetch_shared_page`. Do not pass shared-page IDs to personal-only page actions or imply a shared structured extractor or resource downloader that is not present in the live tool surface.\n- Before a targeted edit, read a fresh snapshot with element IDs or structured update targets. Use `update_page` or `update_shared_page` for exact insert, replace, prepend, or append operations, and re-read after any mutation because targets can become stale.\n- Use `append_to_page` or `append_to_shared_page` for simple additive notes. Use `add_page_resources` on a personal page for staged images, PDF printouts, or attachments, and keep the supplied filenames and MIME types accurate.\n- Use `create_notebook`, `create_section_group`, and `create_section` only in the destination the user selected; `create_page` can target a personal section or a known shared section. Use simple OneNote-compatible HTML for new content, and disambiguate similarly named notebooks, sections, or pages before writing.\n- Treat page copying as non-idempotent and asynchronous. Snapshot destination page IDs when feasible, call `copy_page_to_section` once, retain its operation reference, and poll that reference with `get_operation` until a terminal state. An explicit HTTP 429 rejects the copy request: wait for `Retry-After`, or use exponential backoff if absent, before retrying that request. Retry transient or 404 polling failures using the same reference; do not restart the copy. If the copy outcome is unknown or Microsoft accepted the copy without a usable reference, inspect the exact destination before retrying or using `create_page` as a fallback. Report uncertainty if pagination or matching cannot rule out an existing copy. Never report completion from the initial accepted response.\n- OneNote exposes no notebook ACL, invite, or share-link action. `list_shared_notebooks` browses existing access; it does not grant it. For an explicit sharing request, use an available SharePoint or OneDrive permission tool with the resolved backing item and recipient. The notebook's web URL can be passed to that connector for resolution; do not derive a backing-item ID from a OneNote notebook ID. If resolution is unavailable, explain the limitation and direct the user to Microsoft.\n- Use `next_skip` for bounded pagination; never invoke or reconstruct an opaque `next_link` URL.\n- Read-only requests do not authorize edits. Confirm the exact target and intended change before a consequential write, and require explicit confirmation immediately before `delete_page` because deletion is permanent.\n"
}SHA-256 of public snapshot: 92a812e049cf9e231cc0ded7e7bf203c572ea7172ba09025f668ff613c2a89b7