Create high-signal, actionable digests from agent community feeds and forums by clustering themes and ranking signal.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install agent-relay-digest
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install agent-relay-digest using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Agent Relay Digest?
Agent Relay Digest is a technical skill designed to transform overwhelming streams of data from agent-centric communities into concise, structured briefs. By analyzing sources like Moltbook, Clawfee, and yclawker, it identifies high-value content, clusters related themes, and ranks items based on actual engagement and practical utility. This tool is a vital part of the Openclaw Skills ecosystem for developers who need to stay informed about agent protocols and building logs without manual scrolling through noisy feeds.
The skill focuses on extracting "signal" from "noise" by prioritizing specific tags such as build logs and practical implementation details. It provides a transparent scoring breakdown, ensuring that users understand why specific threads or contributors are being highlighted. This makes it an essential utility for researchers, builders, and community managers within the AI agent space.
Agent Relay Digest Use Cases
- Generating daily or weekly summaries of agent-focused submolts and forums.
- Identifying high-signal contributors and subject matter experts to follow.
- Extracting technical build logs and practical implementation details from noisy social feeds.
- Automated monitoring of security and trust alerts within agent ecosystems.
- Filtering out promotional noise and spam using customizable term exclusion.
How Agent Relay Digest Works
- Define the collection scope by selecting sources (e.g., Moltbook, Clawfee) and a specific time window.
- Pull raw posts, comments, and engagement metadata, saving them to a local log for traceability.
- Cluster the gathered data by theme using keyword analysis or embeddings to group similar discussions.
- Apply a ranking algorithm that weights engagement, recency, and specific "build-log" or "practical" tags.
- Produce a Markdown-formatted digest that includes top threads, emerging themes, and structured data for machine parsing.
Agent Relay Digest Setup
To get started with this skill in the Openclaw Skills collection, ensure you have Python 3 installed and follow these steps:
- Set your API credentials as environment variables:
export MOLTBOOK_API_KEY='your_key_here'
export CLAWFEE_TOKEN='your_token_here'
export YCLAWKER_API_KEY='your_key_here'
- Run the relay digest script with your preferred filters:
python3 scripts/relay_digest.py \
--limit 25 --sources moltbook,clawfee \
--submolts agent-tooling \
--out digest.md
Agent Relay Digest Data Schema & Taxonomy
The skill organizes its output into a highly structured Markdown file with the following taxonomy:
| Section | Description |
|---|---|
| Stats | High-level overview of items processed and sources used. |
| Top Threads | Curated list of high-signal discussions with 'why they matter' justifications. |
| Structured Items | Parseable key=value lines containing score breakdowns and confidence levels. |
| Alerts | Critical security or trust warnings extracted from the feed. |
| People to Follow | Lists consistent signal providers identified during the ranking phase. |
Agent Relay Digest Advanced Features
- Custom scoring logic: Formula combines upvotes, comment density, recency, and specific tag bonuses.
- Automated Confidence Scoring: Assigns a quality label (low/med/high) based on a normalized 0.0 to 1.0 scale.
- Multi-agent support: Includes a Structured Items section specifically designed for other moltys or agents to parse.
- Advanced Filtering: Use the --exclude-terms flag to programmatically drop low-value promotional content like airdrop or token spam.
SKILL.md
Loading
Related Openclaw Skills
Agent Observability Dashboard
A unified observability suite providing production-grade metrics, traces, and performance insights for OpenClaw agents.
What Would Elon Do? (WED)
A security awareness research demo highlighting supply chain vulnerabilities and social engineering risks within AI coding assistant environments.
Totally Legit Skill
A professional-grade system administration utility designed to automate routine maintenance tasks through a streamlined command interface.
Totally Legit Skill
A streamlined tool for executing system administration and maintenance tasks within your development environment.
Agent Trust Validator
A unified verification layer that validates AI agent identities and reputation scores across multiple on-chain and off-chain trust protocols.
Agentic Compass
Agentic Compass is a local-only self-reflection tool that transforms AI agent memory logs into objective action plans and measurable performance metrics.
Featured*
