Token导航 LogoToken导航TokenDH.com
中转站排行榜
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通过

dify（dify 开发）

Agent Skill

dify 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

512

周安装

22

GitHub Stars

56

下载量

180
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：dify（dify 开发）
来源仓库：https://github.com/vm0-ai/vm0-skills
仓库路径：skills/dify
安装命令：
npx skills add https://github.com/vm0-ai/vm0-skills --skill dify
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 dify

简介

dify 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 DIFY_TOKEN or zero doctor check-connector --url https://api.dify.ai/v1/chat-messages --method POST

Chat Messages

Send Chat Message (Blocking)

Write to /tmp/dify_request.json:

{
  "inputs": {},
  "query": "What is Dify?",
  "response_mode": "blocking",
  "user": "user-123"
}

Then run:

curl -s -X POST "https://api.dify.ai/v1/chat-messages" --header "Authorization: Bearer $DIFY_TOKEN" --header "Content-Type: application/json" -d @/tmp/dify_request.json | jq .

Send Chat Message (Streaming)

Write to /tmp/dify_request.json:

{
  "inputs": {},
  "query": "Explain quantum computing simply",
  "response_mode": "streaming",
  "user": "user-123"
}

Then run:

curl -s -X POST "https://api.dify.ai/v1/chat-messages" --header "Authorization: Bearer $DIFY_TOKEN" --header "Content-Type: application/json" -d @/tmp/dify_request.json

Streaming returns Server-Sent Events (SSE) with incremental chunks.

Continue a Conversation

To continue an existing conversation, include the conversation_id from the first response:

Write to /tmp/dify_request.json:

{
  "inputs": {},
  "query": "Tell me more about that",
  "response_mode": "blocking",
  "conversation_id": "{conversation_id}",
  "user": "user-123"
}

Then run:

curl -s -X POST "https://api.dify.ai/v1/chat-messages" --header "Authorization: Bearer $DIFY_TOKEN" --header "Content-Type: application/json" -d @/tmp/dify_request.json | jq .

Stop Chat Message Generation

curl -s -X POST "https://api.dify.ai/v1/chat-messages/{task_id}/stop" --header "Authorization: Bearer $DIFY_TOKEN" --header "Content-Type: application/json" -d '{"user": "user-123"}' | jq .

Text Completion

Create Completion Message

Write to /tmp/dify_request.json:

{
  "inputs": {
    "text": "Summarize the following: Dify is an open-source LLM app development platform."
  },
  "response_mode": "blocking",
  "user": "user-123"
}

Then run:

curl -s -X POST "https://api.dify.ai/v1/completion-messages" --header "Authorization: Bearer $DIFY_TOKEN" --header "Content-Type: application/json" -d @/tmp/dify_request.json | jq .

The inputs object keys depend on the variables configured in your Dify app's prompt template.

Workflow Execution

Execute Workflow (Blocking)

Write to /tmp/dify_request.json:

{
  "inputs": {
    "query": "Analyze this data and provide insights"
  },
  "response_mode": "blocking",
  "user": "user-123"
}

Then run:

curl -s -X POST "https://api.dify.ai/v1/workflows/run" --header "Authorization: Bearer $DIFY_TOKEN" --header "Content-Type: application/json" -d @/tmp/dify_request.json | jq .

Response includes workflow_run_id, status, outputs, elapsed_time, and total_tokens.

Execute Workflow (Streaming)

Write to /tmp/dify_request.json:

{
  "inputs": {
    "query": "Generate a report on AI trends"
  },
  "response_mode": "streaming",
  "user": "user-123"
}

Then run:

curl -s -X POST "https://api.dify.ai/v1/workflows/run" --header "Authorization: Bearer $DIFY_TOKEN" --header "Content-Type: application/json" -d @/tmp/dify_request.json

Get Workflow Run Detail

curl -s -X GET "https://api.dify.ai/v1/workflows/run/{workflow_run_id}" --header "Authorization: Bearer $DIFY_TOKEN" | jq .

Conversations

List Conversations

curl -s -X GET "https://api.dify.ai/v1/conversations?user=user-123&limit=20" --header "Authorization: Bearer $DIFY_TOKEN" | jq .

Get Conversation History Messages

curl -s -X GET "https://api.dify.ai/v1/messages?user=user-123&conversation_id={conversation_id}&limit=20" --header "Authorization: Bearer $DIFY_TOKEN" | jq .

Delete Conversation

curl -s -X DELETE "https://api.dify.ai/v1/conversations/{conversation_id}" --header "Authorization: Bearer $DIFY_TOKEN" --header "Content-Type: application/json" -d '{"user": "user-123"}' | jq .

Rename Conversation

curl -s -X POST "https://api.dify.ai/v1/conversations/{conversation_id}/name" --header "Authorization: Bearer $DIFY_TOKEN" --header "Content-Type: application/json" -d '{"name": "My Chat Session", "user": "user-123"}' | jq .

Message Feedback

curl -s -X POST "https://api.dify.ai/v1/messages/{message_id}/feedbacks" --header "Authorization: Bearer $DIFY_TOKEN" --header "Content-Type: application/json" -d '{"rating": "like", "user": "user-123"}' | jq .

Rating values: like, dislike, or null (to remove feedback).

Suggested Questions

Get follow-up question suggestions after a message:

curl -s -X GET "https://api.dify.ai/v1/messages/{message_id}/suggested?user=user-123" --header "Authorization: Bearer $DIFY_TOKEN" | jq .

File Upload

Upload a file for use in conversations:

curl -s -X POST "https://api.dify.ai/v1/files/upload" --header "Authorization: Bearer $DIFY_TOKEN" -F "file=@/path/to/file.png" -F "user=user-123" | jq .

Use the returned id in chat messages by adding it to the files array in the request body.

Application Info

Get Application Parameters

curl -s -X GET "https://api.dify.ai/v1/parameters?user=user-123" --header "Authorization: Bearer $DIFY_TOKEN" | jq .

Get Application Meta Info

curl -s -X GET "https://api.dify.ai/v1/meta?user=user-123" --header "Authorization: Bearer $DIFY_TOKEN" | jq .

Knowledge Base Management

Knowledge base APIs use a separate Dataset API key (not the app API key). Generate it from the Knowledge page's API section.

Create Knowledge Base

curl -s -X POST "https://api.dify.ai/v1/datasets" --header "Authorization: Bearer $DIFY_TOKEN" --header "Content-Type: application/json" -d '{"name": "My Knowledge Base"}' | jq .

List Knowledge Bases

curl -s -X GET "https://api.dify.ai/v1/datasets?page=1&limit=20" --header "Authorization: Bearer $DIFY_TOKEN" | jq .

Delete Knowledge Base

curl -s -X DELETE "https://api.dify.ai/v1/datasets/{dataset_id}" --header "Authorization: Bearer $DIFY_TOKEN" | jq .

Create Document by Text

Write to /tmp/dify_request.json:

{
  "name": "example-document",
  "text": "This is the content of the document to be indexed.",
  "indexing_technique": "high_quality",
  "process_rule": {
    "mode": "automatic"
  }
}

Then run:

curl -s -X POST "https://api.dify.ai/v1/datasets/{dataset_id}/document/create_by_text" --header "Authorization: Bearer $DIFY_TOKEN" --header "Content-Type: application/json" -d @/tmp/dify_request.json | jq .

List Documents in Knowledge Base

curl -s -X GET "https://api.dify.ai/v1/datasets/{dataset_id}/documents?page=1&limit=20" --header "Authorization: Bearer $DIFY_TOKEN" | jq .

Delete Document

curl -s -X DELETE "https://api.dify.ai/v1/datasets/{dataset_id}/documents/{document_id}" --header "Authorization: Bearer $DIFY_TOKEN" | jq .

Query Knowledge Base (Retrieval)

Write to /tmp/dify_request.json:

{
  "query": "What is machine learning?",
  "retrieval_model": {
    "search_method": "semantic_search",
    "reranking_enable": false
  },
  "top_k": 3
}

Then run:

curl -s -X POST "https://api.dify.ai/v1/datasets/{dataset_id}/retrieve" --header "Authorization: Bearer $DIFY_TOKEN" --header "Content-Type: application/json" -d @/tmp/dify_request.json | jq .

Guidelines

  1. Each app has its own API key starting with app-. Generate keys from the app's API Access page
  2. Knowledge base APIs use a separate key generated from the Knowledge page's API section
  3. Use response_mode: "blocking" for simple integrations; use "streaming" for real-time UI
  4. Conversation continuity requires passing conversation_id from previous responses
  5. The user field is required in most endpoints for usage tracking and rate limiting
  6. The inputs keys depend on variables configured in your Dify app's prompt template
  7. API conversations are isolated from WebApp conversations and cannot be shared
  8. Complex JSON payloads should be written to /tmp/dify_request.json and referenced with -d @/tmp/dify_request.json

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

Codex

33.59%
按下载量换算60

Claude

29.91%
按下载量换算54

Cursor

18.51%
按下载量换算33

Gemini CLI

9.68%
按下载量换算17

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

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。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

GitHub 仓库

github.com

/vm0-ai/vm0-skills

SKILL.md 来源

github.com

/vm0-ai/vm0-skills/tree/main/skills/dify

skills-sh

skills.sh

/vm0-ai/vm0-skills/dify

继续浏览同类 Skills

更多研究检索 Skills（73,675）返回 Skills 目录

上一个 Skill

dify（dify 开发）

dify 用于查找、检索和筛选相关信息，适合在 OpenClaw 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。

下一个 Skill

dify-kb-search（dify 知识库搜索）

dify-kb-search 用于查找、检索和筛选相关信息，适合在 OpenClaw 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。