← 返回 Skills 市场
803
总下载
2
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install digest
功能描述
Curate external information into personalized updates. Auto-learns format, timing, sources, and depth preferences.
使用说明 (SKILL.md)
Core Role
Digest = curate the external world for your human. News, industry, trends, competitors — filtered and formatted to their preferences.
Not: internal business info (→ use Brief), synthesis of documents (→ use Synthesize)
Protocol
Source → Filter → Prioritize → Format → Deliver → Learn
1. Source
Pull from configured feeds, news, social, industry sources. Respect preferences.md source rules.
2. Filter
Apply user's interest profile:
- Topics they care about
- Topics explicitly excluded
- Recency requirements
- Credibility thresholds
3. Prioritize
Rank by user's ponderación profile:
- Breaking/urgent items first?
- Or calm, curated order?
- What gets highlighted vs buried?
4. Format
Deliver in their preferred format (see dimensions.md):
- Channel (which chat/group/email)
- Format (PDF, text, bullets, audio summary)
- Length (headlines only vs analysis)
- Tone (formal digest vs casual update)
- Visuals (with/without images)
5. Deliver
Timing per user preference:
- Morning digest, evening digest, or both
- Weekday vs weekend differences
- On-demand vs scheduled
6. Learn
After delivery, observe signals:
- "Too long" → shorten
- "Missed X" → adjust filters
- "Don't care about Y" → exclude
- "Love this format" → reinforce
Update preferences.md following the pattern/confirm/lock cycle.
Preference System
Check preferences.md for current user preferences. Empty = still learning defaults.
Check dimensions.md for all trackable dimensions.
Output Format (Default)
📰 [DIGEST TYPE] — [DATE/TIME]
🔥 HIGHLIGHTS
• [Top item with 1-line summary]
• [Second item]
📋 FULL DIGEST
[Items organized per user's structure preference]
💡 WORTH NOTING
[Lower priority but interesting items]
---
Sources: [count] | Next digest: [time]
Adapt format entirely based on learned preferences.
References: dimensions.md, preferences.md
安全使用建议
This skill is internally coherent: it reads and updates the included preferences files and outlines a reasonable digest workflow. Before installing, confirm the following: 1) How will the agent fetch external sources (web browsing, platform connectors, or separate skills)? If you plan to include paywalled or private sources, understand where credentials must be stored and who has access. 2) How will delivery channels (Slack, Telegram, email) be connected — check whether those credentials live on the agent platform and review their scope. 3) Because the skill can update preferences.md, review or back up that file if you want an audit trail of changes. 4) Monitor initial runs (or restrict autonomous invocation) to ensure it only pulls from sources you expect and doesn't post to channels you didn't authorize. If any of the above integration details are unclear, treat the setup as incomplete until you confirm where credentials and connectors live.
功能分析
Type: OpenClaw Skill
Name: digest
Version: 1.0.0
The 'Digest' skill is designed to curate and deliver external information based on user preferences. Its instructions in SKILL.md clearly outline a benign process of sourcing, filtering, prioritizing, formatting, delivering, and learning. The skill requires network access to pull data, the ability to deliver content to various channels (e.g., chat, email), and file write access to `preferences.md` to store learned user settings. All these capabilities are directly aligned with its stated purpose, and there is no evidence of malicious intent, prompt injection attempts to subvert the agent, or risky behaviors beyond what is necessary for its legitimate function.
能力评估
Purpose & Capability
Name and description match the instructions: the skill curates external content into personalized digests. It only references local preference files (preferences.md, dimensions.md) that are included and needed for personalization. There are no unexpected environment variables, binaries, or config paths required.
Instruction Scope
SKILL.md stays on-task (Source → Filter → Prioritize → Format → Deliver → Learn) and only references the included preference/dimension files. It is somewhat vague about the mechanics of 'Pull from configured feeds, news, social' and 'Deliver' to channels (Telegram/Slack/email) — it does not specify how credentials or channel integrations are obtained or used. The instructions do explicitly tell the agent to update preferences.md (writing its own file), which is coherent for a learning preference system.
Install Mechanism
Instruction-only skill with no install spec and no code files. This minimizes disk-write/execution risk. Nothing is downloaded or installed by the skill itself.
Credentials
The skill requires no environment variables, credentials, or config paths. That is proportionate to the instruction set given. Note: delivering to external channels or scraping private sources would normally require credentials, but the skill does not request them — it likely expects the platform or other skills to provide channel integrations. Verify where those credentials live on your agent platform before connecting to private sources.
Persistence & Privilege
always is false and model invocation is allowed (default). The skill writes/updates its own preferences.md, which is normal for a learning digest. It does not request system-wide privileges or modify other skills' configs.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install digest - 安装完成后，直接呼叫该 Skill 的名称或使用
/digest触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release
元数据
常见问题
Digest 是什么？
Curate external information into personalized updates. Auto-learns format, timing, sources, and depth preferences. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 803 次。
如何安装 Digest？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install digest」即可一键安装，无需额外配置。
Digest 是免费的吗？
是的，Digest 完全免费（开源免费），可自由下载、安装和使用。
Digest 支持哪些平台？
Digest 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Digest？
由 Iván（@ivangdavila）开发并维护，当前版本 v1.0.0。
推荐 Skills