Token导航 LogoToken导航TokenDH.com
研究检索敏感数据github未标认证来源可访问许可证需确认审计提醒

fireflies技能安全扫描

Agent Skill

fireflies 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

494

周安装

20

GitHub Stars

56

下载量

155
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:fireflies(技能安全扫描)
来源仓库:https://github.com/vm0-ai/vm0-skills
仓库路径:skills/fireflies
安装命令:
npx skills add https://github.com/vm0-ai/vm0-skills --skill fireflies
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/vm0-ai/vm0-skills --skill fireflies

简介

fireflies 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。

  • 适用于需要根据关键词或任务场景从来源线索中获取信息的场景。
  • 通过 npx skills add 命令从 GitHub 仓库安装并使用。
  • 安装前建议确认权限范围和维护状态,注意可能触发联网或文件读写操作。
  • 可结合原始 README 进一步核验具体用法和功能细节。

SKILL.md

Troubleshooting

If requests fail, run zero doctor check-connector --env-name FIREFLIES_TOKEN or zero doctor check-connector --url https://api.fireflies.ai/graphql --method POST

How to Use

All examples below assume you have FIREFLIES_TOKEN set.

Endpoint: https://api.fireflies.ai/graphql

The Fireflies API is GraphQL-based. All requests are POST to a single endpoint. Write the GraphQL query to /tmp/fireflies_request.json, then execute with curl.

1. Get Current User

Fetch details for the API key owner. Omit the userId variable to get the current user.

Write to /tmp/fireflies_request.json:

{
  "query": "query { user { user_id name email num_transcripts minutes_consumed is_admin integrations } }"
}

Then run:

curl -s -X POST "https://api.fireflies.ai/graphql" --header "Content-Type: application/json" --header "Authorization: Bearer $FIREFLIES_TOKEN" -d @/tmp/fireflies_request.json | jq '.data.user'

2. List Transcripts

Fetch a list of recent meeting transcripts.

Write to /tmp/fireflies_request.json:

{
  "query": "query { transcripts(limit: 10) { id title date duration organizer_email participants host_email } }"
}

Then run:

curl -s -X POST "https://api.fireflies.ai/graphql" --header "Content-Type: application/json" --header "Authorization: Bearer $FIREFLIES_TOKEN" -d @/tmp/fireflies_request.json | jq '.data.transcripts'

Search by Keyword

Write to /tmp/fireflies_request.json:

{
  "query": "query Transcripts($keyword: String) { transcripts(keyword: $keyword, limit: 10) { id title date duration } }",
  "variables": { "keyword": "product roadmap" }
}

Then run:

curl -s -X POST "https://api.fireflies.ai/graphql" --header "Content-Type: application/json" --header "Authorization: Bearer $FIREFLIES_TOKEN" -d @/tmp/fireflies_request.json | jq '.data.transcripts'

Filter by Date Range

Write to /tmp/fireflies_request.json:

{
  "query": "query Transcripts($fromDate: DateTime, $toDate: DateTime) { transcripts(fromDate: $fromDate, toDate: $toDate, limit: 20) { id title date duration } }",
  "variables": { "fromDate": "2025-01-01T00:00:00.000Z", "toDate": "2025-12-31T23:59:59.000Z" }
}

Then run:

curl -s -X POST "https://api.fireflies.ai/graphql" --header "Content-Type: application/json" --header "Authorization: Bearer $FIREFLIES_TOKEN" -d @/tmp/fireflies_request.json | jq '.data.transcripts'

Filter by Participant

Write to /tmp/fireflies_request.json:

{
  "query": "query Transcripts($participants: [String]) { transcripts(participants: $participants, limit: 10) { id title date participants } }",
  "variables": { "participants": ["alice@example.com"] }
}

Then run:

curl -s -X POST "https://api.fireflies.ai/graphql" --header "Content-Type: application/json" --header "Authorization: Bearer $FIREFLIES_TOKEN" -d @/tmp/fireflies_request.json | jq '.data.transcripts'

Transcripts Parameters:

ParameterTypeDescription
keywordStringSearch in title and spoken words (max 255 chars)
fromDate / toDateDateTimeISO 8601 date range filter
host_emailStringFilter by host email
organizers[String]Filter by organizer emails
participants[String]Filter by participant emails
mineBooleanOnly meetings owned by API key owner
limitIntMax results (default 50)
skipIntPagination offset

3. Get Single Transcript

Fetch full details for a specific transcript.

Basic Info

Write to /tmp/fireflies_request.json:

{
  "query": "query Transcript($transcriptId: String!) { transcript(id: $transcriptId) { id title date duration host_email organizer_email participants transcript_url audio_url } }",
  "variables": { "transcriptId": "your_transcript_id" }
}

Then run:

curl -s -X POST "https://api.fireflies.ai/graphql" --header "Content-Type: application/json" --header "Authorization: Bearer $FIREFLIES_TOKEN" -d @/tmp/fireflies_request.json | jq '.data.transcript'

With Summary and Action Items

Write to /tmp/fireflies_request.json:

{
  "query": "query Transcript($transcriptId: String!) { transcript(id: $transcriptId) { id title summary { keywords action_items outline overview short_summary topics_discussed } } }",
  "variables": { "transcriptId": "your_transcript_id" }
}

Then run:

curl -s -X POST "https://api.fireflies.ai/graphql" --header "Content-Type: application/json" --header "Authorization: Bearer $FIREFLIES_TOKEN" -d @/tmp/fireflies_request.json | jq '.data.transcript.summary'

With Sentences (Full Transcript)

Write to /tmp/fireflies_request.json:

{
  "query": "query Transcript($transcriptId: String!) { transcript(id: $transcriptId) { id title sentences { index speaker_name text start_time end_time } } }",
  "variables": { "transcriptId": "your_transcript_id" }
}

Then run:

curl -s -X POST "https://api.fireflies.ai/graphql" --header "Content-Type: application/json" --header "Authorization: Bearer $FIREFLIES_TOKEN" -d @/tmp/fireflies_request.json | jq '.data.transcript.sentences'

With Analytics

Write to /tmp/fireflies_request.json:

{
  "query": "query Transcript($transcriptId: String!) { transcript(id: $transcriptId) { id title analytics { sentiments { negative_pct neutral_pct positive_pct } speakers { name duration word_count words_per_minute questions filler_words } } } }",
  "variables": { "transcriptId": "your_transcript_id" }
}

Then run:

curl -s -X POST "https://api.fireflies.ai/graphql" --header "Content-Type: application/json" --header "Authorization: Bearer $FIREFLIES_TOKEN" -d @/tmp/fireflies_request.json | jq '.data.transcript.analytics'

4. Upload Audio for Transcription

Upload an audio file URL for Fireflies to transcribe. The file must be publicly accessible via HTTPS. Supported formats: mp3, mp4, wav, m4a, ogg.

Write to /tmp/fireflies_request.json:

{
  "query": "mutation($input: AudioUploadInput) { uploadAudio(input: $input) { success title message } }",
  "variables": {
    "input": {
      "url": "https://example.com/meeting-recording.mp3",
      "title": "Team Standup 2025-01-15"
    }
  }
}

Then run:

curl -s -X POST "https://api.fireflies.ai/graphql" --header "Content-Type: application/json" --header "Authorization: Bearer $FIREFLIES_TOKEN" -d @/tmp/fireflies_request.json | jq '.data.uploadAudio'

Upload with Attendees

Write to /tmp/fireflies_request.json:

{
  "query": "mutation($input: AudioUploadInput) { uploadAudio(input: $input) { success title message } }",
  "variables": {
    "input": {
      "url": "https://example.com/meeting-recording.mp3",
      "title": "Product Review",
      "attendees": [
        { "displayName": "Alice", "email": "alice@example.com" },
        { "displayName": "Bob", "email": "bob@example.com" }
      ]
    }
  }
}

Then run:

curl -s -X POST "https://api.fireflies.ai/graphql" --header "Content-Type: application/json" --header "Authorization: Bearer $FIREFLIES_TOKEN" -d @/tmp/fireflies_request.json | jq '.data.uploadAudio'

Upload Parameters:

ParameterTypeDescription
urlStringPublic HTTPS URL of audio/video file (required)
titleStringTitle for the meeting
attendees[Object]Array of {displayName, email, phoneNumber}
webhookStringURL to notify when transcription completes
custom_languageStringLanguage code (e.g., es, de, ja)
save_videoBooleanRetain video file
client_reference_idStringCustom identifier for the upload

5. List Team Users

Fetch all users in the team.

Write to /tmp/fireflies_request.json:

{
  "query": "query { users { user_id name email is_admin num_transcripts minutes_consumed } }"
}

Then run:

curl -s -X POST "https://api.fireflies.ai/graphql" --header "Content-Type: application/json" --header "Authorization: Bearer $FIREFLIES_TOKEN" -d @/tmp/fireflies_request.json | jq '.data.users'

Guidelines

  1. GraphQL single endpoint: All requests go to POST https://api.fireflies.ai/graphql with the query in the JSON body
  2. Request only needed fields: GraphQL lets you specify exactly which fields to return; keep queries minimal for better performance
  3. Pagination: Use limit and skip parameters on the transcripts query. Maximum limit is 50
  4. Date format: Use ISO 8601 format for fromDate and toDate (e.g., 2025-01-01T00:00:00.000Z)
  5. Audio uploads are async: After uploading, the transcription is queued. Use webhooks or poll the transcripts list to check completion
  6. File requirements: Uploaded audio must be a valid HTTPS URL and publicly accessible. Supported formats: mp3, mp4, wav, m4a, ogg
  7. Check for errors: GraphQL errors appear in the errors array of the response, not in HTTP status codes

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Claude

32.25%
按下载量换算50

Codex

31.46%
按下载量换算49

Cursor

17.33%
按下载量换算27

Gemini CLI

9.92%
按下载量换算15

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills