Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
v0.3.9: Remove eval shell injection from reference docs — fixes suspicious classification
What This Skill Does
Gives an AI agent a persistent WebID and personal data store (Pod) on a Solid server. The agent reads, writes, and deletes data across sessions using standard HTTP requests with Bearer tokens. Credentials are encrypted locally; access control is enforced server-side per the W3C Solid Protocol.
Uses the open W3C Solid Protocol, so the agent's storage works with any compliant server rather than a proprietary API.
When to use it
- Persisting notes and learned facts between agent sessions
- Sharing structured RDF data with another agent on the same Solid server
- Giving an agent a verifiable web identity for inter-agent authentication
- Storing user preferences that survive conversation resets
- Logging conversation history to a private Pod container
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Remember that the project deadline is March 20
- 1Run scripts/get-token.sh --agent my-agent to obtain a Bearer token and Pod URL
- 2Extract token and podUrl from the JSON response using jq
- 3Format the deadline as a Turtle RDF note with schema:text and schema:dateCreated fields
- 4Send a PUT request to ${POD_URL}memory/notes.ttl with Authorization: Bearer $TOKEN header
- 5Confirm a 201 or 204 response indicating the write succeeded
Deadline stored at the agent's Pod under memory/notes.ttl, readable in future sessions
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.