s-annam

Dizest Summarize

ナレッジ管理v1.0.1
作者:s-annam更新日 2026-05-11全 2 バージョン · 最新版の公開日 2026-03-10dizest-summarize@clawhub_s-annam/dizest-summarize
要約長文読解#Summarize

AlphaMoatによると、2026-09時点でDizest Summarizeのダウンロード数は2,191、スター数は0で、AIスキル全体5,078件中4,294位、ナレッジ管理では442件中373位です。

インストール数
111
ダウンロード数
2191
スター数
-
総合順位
#4,294
全体の上位 85% · ナレッジ管理の上位 85%
プラットフォームインストール数ダウンロード数スター数コメント
ClawHub ↗642162--
SkillHub ↗1112191-—

プラットフォームごとに集計方法と集計時点が異なります。

このスキルでできること

ユーザーが指定した内容を外部のDizest APIに送り、構造化された要約を得る手順です。クライアントは独自に取得や前処理を行わず、ペイウォールを回避しないよう求められます。外部処理が承認された内容だけを送り、機密情報と認証情報を守り、APIキーの取得にはHTTPSを使用してください。

資料公開日 2026-10-29

できること

  • 承認済みの記事、ポッドキャスト、論文、文書を要約する
  • 指定した観点に沿った構造化要約を作成する
  • 出力言語とAPI結果の提示方法を確認する

使う場面

  • 外部のDizest APIでコンテンツを要約するとき
  • 第三者処理が承認されたデータか確認し、未承認の機密情報を送らず、ペイウォールを回避しない

プロンプト例

スキルのドキュメントをもとに生成した例であり、実際の実行結果ではありません。

文書の手順を整理し、外部操作は実行しないでください。
アップロード、ダウンロード、デプロイ、アカウント操作の前に確認すべき許可とデータ処理を列挙してください。

月次の推移

ダウンロード数2191
1322178922552026-03 · ダウンロード数 13862026-05 · ダウンロード数 16032026-06 · ダウンロード数 17072026-07 · ダウンロード数 19222026-08 · ダウンロード数 20392026-09 · ダウンロード数 219126-0326-09
スター数-
0112026-03 · スター数 -2026-05 · スター数 -2026-06 · スター数 -2026-07 · スター数 -2026-08 · スター数 -2026-09 · スター数 -26-0326-09

2026-09 から集計方法を変更し、同名スキルを作者ごとに分けて集計し、全スキルを対象にしました。破線は変更前の月で、変更後のデータとは直接比較せず、変更をまたぐ増減も計算していません。

月ダウンロード数前月比スター数
2026-092191—-
2026-082039+6.1%-
2026-071922+12.6%-
2026-061707+6.5%-
2026-051603—-
2026-031386—-

SKILL.md 原文

作者が公開した元のファイルをテキストのまま表示しています。AlphaMoat による編集や審査はしていません。リンクはクリックできません。コマンドは内容を確認してから実行してください。取得日 2026-10-23。

8.4 KB・ClawHub v1.0.1
---
name: dizest-summarize
description: "Summarize long-form content — articles, podcasts, research papers, PDFs, notes, and more — using the Dizest API. Turn what you read into structured, searchable knowledge."
metadata: {"openclaw":{"emoji":"📝","requires":{"env":["DIZEST_API_KEY"]}}}
---

# Dizest Summarize

Summarize long-form content and turn it into structured, searchable knowledge. Powered by the API behind [Dizest: AI Summarizer](https://www.dizest.ai) — available on the [App Store](https://apps.apple.com/app/id6752311120) and [Google Play](https://play.google.com/store/apps/details?id=com.ideas116.dizest).
すべて表示(全 255 行)
**Base URL:** `https://api.dizest.ai`

Visit [www.dizest.ai](https://www.dizest.ai) for more information about the product.

---

## When to Use This Skill

Use this skill when the user asks to:

- Summarize research papers or academic content to extract key findings
- Summarize long podcasts, interviews, or video content from YouTube and other platforms
- Process articles, blog posts, or web content (by URL)
- Summarize PDFs, reports, market analysis, or business documents
- Summarize plain text such as notes, transcripts, or pasted content
- Summarize any of the above with a custom focus (e.g., "focus on methodology and key findings")

---

## Critical Agent Behavior

**The agent MUST act as a thin client.** Specifically:

- **Do NOT** extract, parse, or classify URLs from the user's input.
- **Do NOT** attempt to determine whether the input is a URL, plain text, or text with an embedded URL.
- **Do NOT** fetch, scrape, or pre-process any content before calling the API.
- **Do NOT** handle paywalled content or attempt workarounds.

All content analysis, URL detection, extraction, paywall handling, and execution logic is performed **server-side**. The agent's only job is to forward the user's input to the API exactly as provided.

---

## Authentication

All requests require the `x-api-key` header. The value should come from the `DIZEST_API_KEY` environment variable.

```
x-api-key: $DIZEST_API_KEY
```

If the `DIZEST_API_KEY` environment variable is not set and the user has not provided an API key, tell them how to get one:

1. **Download Dizest** from [dizest.ai](https://www.dizest.ai/#download) — available on iOS, Android, and macOS (coming soon)
2. **Create an account** and sign in
3. **Activate your account** through the app (one-time setup)
4. **Generate your API key** at [dizest.ai/api/keys](https://dizest.ai/api/keys) — sign in with the same account

Account activation through the app is required to generate API keys. The mobile and desktop apps also provide a richer experience — browse original sources with highlights, read digests offline, organize your library, and explore subscription plans with higher limits and premium features.

---

## API Flow

There are two steps: **create an execution**, then **retrieve the results**.

### Step 1: Create Execution

**Endpoint:**

```
POST https://api.dizest.ai/v1/summarize
```

**Headers:**

```
Content-Type: application/json
x-api-key: $DIZEST_API_KEY
```

**Request Body (minimal):**

```json
{
  "content": "<user input>"
}
```

**Request Body (with custom instructions):**

```json
{
  "content": "<user input>",
  "custom_instructions": "<what to focus on>"
}
```

**Request Body (with output language):**

```json
{
  "content": "<user input>",
  "output_language": "ja"
}
```

Pass the user's input directly as the `content` value. Do not modify, parse, or pre-process it.

**Request Fields:**

| Field                | Type   | Required | Description                                                                 |
|----------------------|--------|----------|-----------------------------------------------------------------------------|
| `content`            | string | Yes      | The user's input to summarize. Pass as-is without modification.             |
| `custom_instructions`| string | No       | Focus instructions for the summary (e.g., "focus on key findings").         |
| `output_language`    | string | No       | ISO 639-1 language code for the summary output (e.g., `"ja"`, `"es"`). Defaults to `"en"`. |

**Response:**

```json
{
  "execution_id": "b7e2c1a4-93f1-4d2a-8e56-1a2b3c4d5e6f",
  "cached": false
}
```

| Field          | Type    | Description                                                  |
|----------------|---------|--------------------------------------------------------------|
| `execution_id` | string  | UUID identifying this execution. Used to retrieve results.   |
| `cached`       | boolean | `true` if result was cached and is ready immediately.        |

### Step 2: Retrieve Results

Use the `execution_id` from Step 1 to retrieve the summary. There are two methods.

#### Preferred: Server-Sent Events (SSE) Stream

```
GET https://api.dizest.ai/v1/executions/<execution_id>/events
```

**Headers:**

```
x-api-key: $DIZEST_API_KEY
```

The server responds with a stream of Server-Sent Events. Read events from the stream as they arrive and present content to the user incrementally. The stream closes when the execution is complete.

#### Fallback: JSON Polling

> **Note:** The polling endpoint is not yet available. SSE is the only supported retrieval method in v1. This section will be updated when polling support is added.

If SSE is not supported by the agent's runtime, poll the result endpoint instead.

```
GET https://api.dizest.ai/v1/executions/<execution_id>/result
```

**Headers:**

```
x-api-key: $DIZEST_API_KEY
```

Poll this endpoint at reasonable intervals (e.g., every 2–3 seconds) until the result is available. The response is a JSON object containing the final summary.

---

## Examples

### Example 1: Summarize a URL

User says: *"Summarize https://example.com/article-about-ai"*

**POST /v1/summarize**

```json
{
  "content": "https://example.com/article-about-ai"
}
```

### Example 2: Summarize Text with an Embedded URL

User says: *"Can you summarize this for me? I found it interesting: https://example.com/post/12345"*

**POST /v1/summarize**

```json
{
  "content": "Can you summarize this for me? I found it interesting: https://example.com/post/12345"
}
```

> Forward the entire input as-is. Do not extract the URL.

### Example 3: Summarize Plain Text

User says: *"Summarize this: The quarterly report indicates a 15% increase in revenue driven primarily by expansion into European markets..."*

**POST /v1/summarize**

```json
{
  "content": "The quarterly report indicates a 15% increase in revenue driven primarily by expansion into European markets..."
}
```

### Example 4: Summarize a Podcast or Video

User says: *"Summarize this podcast https://www.youtube.com/watch?v=dQw4w9WgXcQ"*

**POST /v1/summarize**

```json
{
  "content": "https://www.youtube.com/watch?v=dQw4w9WgXcQ"
}
```

### Example 5: Custom Instructions

> **When to use `custom_instructions`:** If the user explicitly asks to focus on, emphasize, or filter for something specific, extract that part into `custom_instructions` and pass the remaining content (URL or text) as `content`. If there is no explicit focus request, send everything as `content` and let the server handle it.

User says: *"Summarize https://example.com/research-paper but focus on the methodology and key findings"*

**POST /v1/summarize**

```json
{
  "content": "https://example.com/research-paper",
  "custom_instructions": "Focus on the methodology and key findings"
}
```

---

## Output Expectations

- The API returns a summary generated server-side.
- Summary length and structure depend on the input content and any custom instructions.
- Present the summary to the user as-is. Do not further condense or reformat unless the user requests it.

---

## Troubleshooting

| Problem | Cause | Resolution |
|---|---|---|
| `401 Unauthorized` | Missing or invalid `x-api-key` header. | Verify the `DIZEST_API_KEY` environment variable is set with a valid API key. API keys require an activated Dizest account — see the Authentication section above for setup steps. |
| `403 Forbidden` | The API key does not have access. | Confirm the key belongs to an activated account. |
| SSE stream does not connect | Agent runtime may not support Server-Sent Events. | Fall back to polling `GET /v1/executions/<execution_id>/result`. |
| Polling returns no result | The execution is still processing. | Continue polling every 2–3 seconds. Allow sufficient time for longer content. |
| Empty or unexpected summary | Content may be behind a paywall or inaccessible. | Inform the user. Do not attempt client-side workarounds — the server handles extraction. |

ナレッジ管理の人気スキル

データ月:2026-09 · ダウンロード数、スター数、インストール数は公開スキルレジストリ(ClawHub、SkillHub)から月単位で集計しています。詳しくはデータの方法論をご覧ください。