Topical Topic Intelligence for Openclaw

Connects your AI agent to Topical's continuous intelligence infrastructure to fetch scheduled updates, trends, and competitive intelligence.

daveangelcode
v0.0.2
Jul 9, 2026
0
704
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install topical

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install topical 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 Topical Topic Intelligence?

Topical provides continuous intelligence infrastructure, monitoring long-lived topics on user-defined schedules. By integrating this intelligence into your workflow using Openclaw Skills, your AI agents gain access to structured digests of breaking news, emerging trends, and curated signals without needing to execute active web searches.

The tool retrieves pre-compiled snapshots produced during the last completed pipeline run. This architecture ensures high-fidelity, filtered insights while minimizing the latency and noise associated with raw web crawling.

Topical Topic Intelligence Use Cases

  • Reviewing scheduled topic briefings and tracking industry updates aligned with custom execution plans.
  • Conducting incremental intelligence checks to query only the latest signals updated since the last checkpoint.
  • Generating human-readable prose summaries using inline source references for automated daily briefings.
  • Providing direct feedback to the Topical pipeline to refine future ingest relevance and ignore noise.
  • Expanding monitoring scopes by adding or removing specific RSS feeds and YouTube channels via agent commands.

How Topical Topic Intelligence Works

  1. The user establishes monitoring schedules, sources, and filters directly within the Topical portal.
  2. The Topical background pipeline periodically executes, ingesting data from configured feeds, searches, and channels to compile breaking news, trends, and signals.
  3. The AI agent queries this structured intelligence using Openclaw Skills by calling MCP read tools like get_topic_update or get_topic_narrative.
  4. The agent processes the returned checkpoint token and structures the curated information, citing inline source URLs for user verification.
  5. Future ingest accuracy is continuously improved as the agent submits relevance feedback back to the pipeline.

Topical Topic Intelligence Setup

First, generate an Agent API key in the Topical portal (Settings -> Agent API keys). Use the Openclaw Skills CLI tool to configure the Model Context Protocol (MCP) server:

openclaw mcp set topical '{\"url\":\"https://app.usetopical.com/api/mcp\",\"transport\":\"streamable-http\",\"headers\":{\"Authorization\":\"Bearer <AGENT_API_KEY>\"}}'
openclaw mcp probe topical
openclaw gateway restart

To support inbound push delivery (briefing alerts and notifications), install the complementary setup skill and wire the gateway hooks:

openclaw skills install @daveangelcode/topical-openclaw-setup --global

Follow the setup prompts to copy assets from {baseDir}/scripts/copy-transforms.sh, merge the hook configuration fragment, and register the webhook URL using manage_agent_webhook.

Topical Topic Intelligence Data Schema & Taxonomy

The skill processes structured payloads representing checkpoints, news items, and trends.

Response Schema (get_topic_update)

Field Type Description
breakingNews Array Global stories matched to the topic, containing IDs, titles, summaries, and source URLs.
signals Array High-value, topic-specific signals and indicators compiled from ingested sources.
trends Array Emerging thematic patterns detected during the latest pipeline runs.
checkpoint String A state token to pass as lastCheckedAt in subsequent incremental requests.
since String ISO 8601 timestamp representing the starting boundary of the retrieved dataset.

Database and Assets Layout

  • Local Assets Directory: Hook transform files are placed inside {baseDir}/assets/ to manage inbound webhook payloads.
  • Payload References: Comprehensive payload validation definitions are available in {baseDir}/references/payloads.md.

Topical Topic Intelligence Advanced Features

  • Continuous Incremental Querying: Keep briefings synchronized between runs by tracking and passing state checkpoints.
  • Prose Narrative Synthesis: Access ready-made Markdown summaries with embedded inline citations using get_topic_narrative.
  • Inbound Webhook Push Alerts: Support active push notifications for new intelligence and breaking alerts using custom gateway hooks.
  • Dynamic Feed Subscriptions: Add or unsubscribe RSS feeds and YouTube channels directly through agent execution.
  • Contextual Schedule Management: View and modify topic execution cadences (weekly, fortnightly, monthly) and timezones programmatically.
  • Feedback Loop Optimization: Steer ingestion models using relevance tags to automatically adjust future intelligence rankings.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Requires
Github Stars: 0
forks: 0

Featured*