メニュー
Use when finding meeting transcripts, searching Fireflies recordings, getting action items from calls, or answering 'what was discussed in the meeting' questions
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | fireflies |
| description | Use when finding meeting transcripts, searching Fireflies recordings, getting action items from calls, or answering 'what was discussed in the meeting' questions |
| version | 1.0.0 |
| category | research |
| triggers | ["fireflies","meeting transcript","meeting notes","what was discussed","action items","zoom call","teams meeting","google meet"] |
Clear triggers:
fireflies today
fireflies date 2026-01-28
fireflies search "product roadmap" fireflies search "budget discussion"
fireflies get abc123xyz
fireflies me
</commands>
<response-format>
**List view includes:**
- id, title, duration, host, participants
- AI-generated overview and action items
**Full transcript includes:**
- Complete sentences with speaker names and timestamps
- Keywords, topics discussed, outline
- Extracted action items
</response-format>
<api-notes>
- Works with Zoom, Google Meet, Microsoft Teams
- Speaker names from calendar invites
- GraphQL API docs: [docs.fireflies.ai](https://docs.fireflies.ai)
</api-notes>
<llm-api-reference>
If you need to look up API details beyond this skill's commands, use Context7:
resolve-library-id: fireflies → /websites/fireflies_ai query-docs: /websites/fireflies_ai with "GraphQL transcripts query"
Context7 has full GraphQL schema documentation with code examples in Python, JavaScript, and cURL.
</llm-api-reference>
Use when facing hard architectural decisions, multiple valid approaches exist, need diverse perspectives before committing, or want M-of-N synthesis on complex problems
Use when rough ideas need design before code, requirements are fuzzy, multiple approaches exist, or you need to explore options before implementation
Use when testing MCP servers, debugging MCP tool responses, exploring MCP capabilities, or diagnosing why an MCP tool returns unexpected data
Use when debugging bugs, test failures, unexpected behavior, or needing to find root cause before fixing
Use when managing project learnings - view, add, search, prune, or export operational knowledge that persists across sessions
Use when shipping code - complete workflow: merge main, run tests, multi-review with auto-fix, commit, push, create PR. Replaces manual commit-push-pr flows.