agentleFS
benororbenoror/obsidianos_work/.agents/skills/otter-fetch/SKILL.md

otter-fetch

Skill166 starsChanged 5 months agoMITView on GitHub

Fetch Otter.ai transcript data. Sub-skill used by cache-notes and fill-participants when Notes: contains an Otter URL.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    cache-notes: When caching a meeting that has https://otter.ai/u/{otid} in Notes: — need callout markdown to embed.

    line 17
  2. Distinctive:

    fill-participants: When resolving participants for a meeting that only has Otter links (no Google Doc) — need speaker names from the …

    line 18
  3. Very specific:

    Always extract otid from the share URL (query params like ?utm_source=copy_url can be ignored).

    line 51
  4. Very specific:

    If the user doesn't have the JSON, they can open the Otter meeting page while signed in, open DevTools → Network, reload, and copy the …

    line 52

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Otter Fetch

Single place for obtaining Otter.ai transcript data. No direct slash command — other skills invoke this when they encounter an Otter.ai URL (e.g. in Notes: frontmatter).

Usage

This skill has no slash command. It's a sub-skill: /cache-notes and /fill-participants invoke its workflow (and run parse_otter.js) when a meeting's Notes: contains an https://otter.ai/u/... URL.

When to use

  • cache-notes: When caching a meeting that has https://otter.ai/u/{otid} in Notes: — need callout markdown to embed.
  • fill-participants: When resolving participants for a meeting that only has Otter links (no Google Doc) — need speaker names from the transcript.

How to get the data

Otter has no public API. Use user-pasted JSON:

  1. Extract otid from the URL: https://otter.ai/u/aBcDeFgHiJkLmNoPqRsT → otid = aBcDeFgHiJkLmNoPqRsT.
  2. Ask the user to copy the JSON response from GET https://otter.ai/forward/api/v1/speech?otid={otid} (e.g. from DevTools → Network while signed in, or from a signed-in request).
  3. User pastes the JSON; the agent (or script) parses it.

Outputs (same JSON, different consumers)

The pasted JSON has speech with:

Use caseWhat to useHow
cache-notesCallout markdownRun parse_otter.js with JSON on stdin → stdout is ## 🤖 AI Notes / ### Otter block with [!otter_notes]-, [!otter_todos]-, [!otter_transcript]-.
fill-participantsSpeaker namesFrom speech.speakers: array of { speaker_name }. Use those names with people-resolver to build Participants:.

So one paste can serve both skills if needed (e.g. cache-notes runs the script; fill-participants reads speech.speakers from the same JSON or from the cached transcript callout).

Script: parse_otter.js

In this folder: parse_otter.js reads the full Otter speech JSON from stdin and writes callout markdown to stdout (for cache-notes).

node .agents/skills/otter-fetch/parse_otter.js < pasted.json

Output is the exact block to append under ## 🤖 AI Notes (including ### Otter and the three callouts). Caller appends it to the note and sets NotesCached:.

Important notes

  • Always extract otid from the share URL (query params like ?utm_source=copy_url can be ignored).
  • If the user doesn't have the JSON, they can open the Otter meeting page while signed in, open DevTools → Network, reload, and copy the response body of the speech?otid=... request.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.