Installs into .claude/skills of the current project.
Sponsors
SSkills DirectorySkills Directory
Is that skill safe to install?
SSkills DirectorySkills Directory
Know which skills are safe — weekly.
Are you the author of Cache Notes?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/benoror-cache-notes)
---
name: cache-notes
description: "Fetch & embed AI transcripts as Obsidian callouts. Args: <path>, all, refresh <path>. Prompts for URLs if empty."
license: MIT
compatibility: Requires Obsidian CLI (property:read/set, outline, base:query) with Obsidian running, gws CLI for Google Docs/Drive (read-only), and Meetings.base (CachePending view). QMD optional fallback. See [google-workspace-cli](../_shared/google-workspace-cli.md).
---
# Cache Notes
## Usage
- `/cache-notes all` — Scan all meetings with `Notes:` links that haven't been cached yet, fetch and embed them.
- `/cache-notes <path>` — Cache notes for a specific meeting file.
- `/cache-notes refresh <path>` — Re-fetch and overwrite existing cached content for a file.
If the target file has an **empty `Notes:` property** (no URLs yet), run **`/mail-transcripts`** first when doing a full wrap (see [meeting](../meeting/SKILL.md) Mode C) — it may populate `Notes:` from the Gemini inbox mail. If still empty, prompt the user to paste the Google Doc URL. Add it to the `Notes:` frontmatter, then proceed with fetching and caching as normal.
## How It Works
The supported **external transcript provider** is **Google Docs** (Gemini notes). When a Doc URL appears in frontmatter `Notes:`, the agent fetches the transcript and embeds it as **collapsible Obsidian callouts** in the meeting note. A `NotesCached:` frontmatter timestamp marks the file as cached.
## Frontmatter Convention
Before caching:
```yaml
Notes:
- https://docs.google.com/document/d/{id}/edit?tab=t.{tab}
```
After caching:
```yaml
Notes:
- https://docs.google.com/document/d/{id}/edit?tab=t.{tab}
NotesCached: 2026-02-25T15:00:00+00:00
```
## Provider: Gemini (Google Docs)
### Fetching
1. Extract document ID from the Google Docs URL in `Notes:`.
2. Run **`gws`** in the terminal to fetch the document (read-only). See [google-workspace-cli](../_shared/google-workspace-cli.md) for exact commands.
3. Prefer `gws docs documents get` with `includeTabsContent: true` and parse the JSON into text (optionally inserting `--- TAB: … ---` separators from tab titles), **or** `gws drive files export` with `mimeType: text/plain` for a simpler single stream. Parsed content should mirror the old tab layout where needed: `--- TAB: Notes ---`, `--- TAB: Transcript ---`.
### Parsing the Notes Tab
Gemini notes have a consistent structure. Parse into three sections:
| Section | Starts after | Ends before | Callout |
|---------|-------------|-------------|---------|
| Summary + Details | `Summary` heading | `Suggested next steps` heading | `[!gemini_notes]` |
| Suggested next steps | `Suggested next steps` heading | Gemini disclaimer footer | `[!gemini_todos]` |
| Transcript | `--- TAB: Transcript ---` | End of content | `[!gemini_transcript]` |
**Strip the Gemini disclaimer footer** — lines starting with "You should review Gemini's" or "Please provide feedback" are noise. Do not include them.
### Output Format
All cached content goes under a top-level `## 🤖 AI Notes` section appended after frontmatter. Each provider gets its own `### {Provider}` subsection. Callouts are nested under the provider heading.
```markdown
## 🤖 AI Notes
### Gemini
> [!gemini_notes]- Summary & Details
> ### Summary
> {summary text}
>
> ### Details
> {details as bullet points}
> [!gemini_todos]- Suggested Next Steps
> - {next step 1}
> - {next step 2}
> [!gemini_transcript]- Transcript
> {transcript content, if available}
```
**Formatting rules for callout content:**
- Every line inside a callout must start with `> `.
- Preserve markdown formatting (bold, bullet points, headings) inside callouts.
- Keep the `-` after the callout type (e.g. `[!gemini_notes]-`) — this makes it collapsed by default in Obsidian.
- Blank lines between callouts (no `>` prefix) to separate them.
- If transcript tab is not available, omit the `[!gemini_transcript]` callout entirely.
- The `## 🤖 AI Notes` heading is created once. Provider subsections are added beneath it.
- If the file already has user-written content between frontmatter `---` and `## 🤖 AI Notes`, preserve it. Always append `## 🤖 AI Notes` at the end of the file.
## Adding a provider
Google Docs (Gemini) is the transcript provider that ships. IDE wrappers (`CLAUDE.md`, `OpenCode.md`, Cursor rules) stay pointers to [AGENTS.md](../../../AGENTS.md). Plug a CLI, MCP, or API in as a skill under `.agents/skills/`, not by copying rules into those wrappers.
A provider needs three things:
- a `Notes:` URL pattern
- a fetch step
- callout names under `## 🤖 AI Notes`: `[!<name>_notes]-`, `[!<name>_todos]-`, `[!<name>_transcript]-`
Register the provider in this skill and in [fill-participants](../fill-participants/SKILL.md). Do not name a second provider until that skill exists.
## Workflow
### Mode: Specific file (`/cache-notes <path>`)
1. **Read frontmatter only**. Check `Notes:` and `NotesCached:` via `obsidian property:read` (see [frontmatter-mutations](../_shared/frontmatter-mutations.md)). To check whether the body already has an `## 🤖 AI Notes` section without reading the whole file, run `obsidian outline path="<file>" format=json` and look for that heading — much cheaper than a full `Read` on large transcript files.
2. If `Notes:` is empty or absent, **prompt the user** to paste the external resource URL(s). Set them via `obsidian property:set name=Notes value='["<url1>","<url2>"]' type=list path="<file>"`, then continue.
3. If `NotesCached:` exists and this is not a `refresh`, inform the user and stop.
4. **Verify each URL** before caching (see URL Verification below).
5. **For each URL in `Notes:`**, fetch and parse by provider:
- **Google Docs**: Extract document ID, fetch via **`gws`** (see [google-workspace-cli](../_shared/google-workspace-cli.md)), parse into sections per [Provider: Gemini](#provider-gemini-google-docs).
6. Build the callout blocks from all fetched content.
7. If the file already has callout blocks (refresh mode), replace them. Otherwise append under `## 🤖 AI Notes` after frontmatter `---` (see [Output Format](#output-format)).
8. Set `NotesCached:` timestamp: `obsidian property:set name=NotesCached value="$(date +%FT%T%z)" type=datetime path="<file>"`. See [frontmatter-mutations](../_shared/frontmatter-mutations.md).
### Mode: All (`/cache-notes all`)
1. Discover uncached files via the live Base view: `obsidian base:query path=Meetings.base view=CachePending format=paths`. Returns only files with `Notes` populated but no `NotesCached:` — exactly the work queue. (The `/note-status pending --step=cache` delegation in [Detecting Uncached Files](#detecting-uncached-files) is the fallback when `Meetings.base` is unavailable.)
2. Present the list to the user with count. Ask for confirmation before proceeding.
3. Process each file per the specific-file workflow above.
4. Report results: successes, failures, and any skipped (e.g. provider not yet implemented).
## URL Verification
Before caching, verify that each external resource actually corresponds to the meeting note. This prevents accidentally caching the wrong document when a user pastes an incorrect URL.
### How it works
1. **Extract the meeting date** from the note. Try these sources in order until one yields a date:
- Filename date pattern (any format — see Date Parsing below)
- `created:` frontmatter timestamp
2. **Fetch the document title** from Drive metadata via `gws drive files get` (`name` field), e.g. `"Daily Standup - 2026/02/24 09:43 EST - Notes by Gemini"` — same string you would have seen in older MCP `File:` lines.
3. **Extract the date from the doc title** (any format — see Date Parsing below).
4. **Compare**: normalize both dates to `YYYY-MM-DD` and check equality.
- If the dates match, proceed silently.
- If the dates **don't match**, warn the user:
```
⚠️ Date mismatch for Meetings/Engineering/Scrum/2026-02-24.md:
Note date: 2026-02-24
Doc title: "Daily Standup - 2026/02/26 09:41 EST - Notes by Gemini"
Doc date: 2026-02-26
Wrong document? [Continue anyway / Skip this URL / Replace URL]
```
4. **If no date is found** in the doc title, fall back to a title similarity check — warn if the doc title has no obvious overlap with the meeting note's title (e.g. a "Sprint Retro" doc linked to a "Daily Standup" note).
5. **In batch mode** (`/cache-notes all` or `/meeting wrap pending`), collect all mismatches and present them together before proceeding, rather than interrupting one by one.
### Date Parsing
See [date-filter](../_shared/date-filter.md) § "Date Parsing" for the full list of recognized formats and ambiguity rules.
### Skip verification
Verification is skipped for:
- `refresh` mode (the URL was already verified on first cache)
- Non-Google Docs URLs
## Detecting Uncached Files
Delegate to [/note-status pending --step=cache](../note-status/SKILL.md#pending-mode). That skill handles discovery, frontmatter checks, and the dependency chain (only notes with `Notes:` containing a supported provider URL are considered actionable for caching). See [/note-status § Dependency Chain](../note-status/SKILL.md#dependency-chain) for the full rules.
## Refresh Mode
`/cache-notes refresh <path>`:
- Delete the entire `## 🤖 AI Notes` section and everything below it.
- Re-fetch all providers and re-build the section.
- Update `NotesCached:` timestamp.
## Offer to Commit
See [/commit](../commit/SKILL.md). Skip when called as part of a sequence (e.g. `/meeting wrap`).
## Important Notes
- Use `obsidian property:set` for frontmatter writes (`Notes:`, `NotesCached:`) — see [frontmatter-mutations](../_shared/frontmatter-mutations.md); never hand-roll `StrReplace` against frontmatter anchors. Body content (the callout blocks) is still appended/replaced with `Edit`/`Write`.
- The `Notes:` URLs should NOT be modified — they remain as the canonical source links.
- `NotesCached:` is the single indicator that caching was done. No other markers.
- For `all` mode, process in batches and report progress to the user.
- Gemini anonymizes some speakers as "someone in [location]" — this is expected; `/fill-participants` handles name resolution separately.