Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Pull personal data (emails, issues) and propose outbound actions (drafts, replies) through the PersonalDataHub access control gateway. Data is filtered, reda...
Pull personal data (emails, issues) and propose outbound actions (drafts, replies) through the PersonalDataHub access control gateway. Data is filtered, reda...
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Access personal data from Gmail, GitHub, and other sources through the PersonalDataHub access control gateway. The data owner controls what the agent can see, which fields are visible, what gets redacted, and which actions are allowed.
PersonalDataHub provides an MCP server for native tool discovery. Add to your Claude Code config (.claude/settings.json): { "mcpServers": { "personaldatahub": { "command": "npx", "args": ["pdh", "mcp"] } } } This registers source-specific tools dynamically โ only sources with connected OAuth tokens get tools.
(Gmail โ requires connected Gmail OAuth) Pull emails from Gmail. Data is filtered and redacted according to the owner's access control policy. Parameters: purpose (required) โ Why this data is needed (logged for audit) query (optional) โ Gmail search query (e.g., "is:unread from:alice newer_than:7d") limit (optional) โ Maximum number of results Example: Pull my recent unread emails about the Q4 report.
(Gmail โ requires connected Gmail OAuth) Draft an email via Gmail. The draft is staged for the data owner to review โ it does NOT send until approved. Parameters: to (required) โ Recipient email address subject (required) โ Email subject body (required) โ Email body purpose (required) โ Why this action is being proposed (logged for audit) in_reply_to (optional) โ Message ID for threading
(Gmail โ requires connected Gmail OAuth) Send an email via Gmail. The action is staged for the data owner to review โ it does NOT execute until approved. Parameters: to (required) โ Recipient email address subject (required) โ Email subject body (required) โ Email body purpose (required) โ Why this action is being proposed (logged for audit) in_reply_to (optional) โ Message ID for threading
(Gmail โ requires connected Gmail OAuth) Reply to an email via Gmail. The reply is staged for the data owner to review โ it does NOT send until approved. Parameters: to (required) โ Recipient email address subject (required) โ Email subject body (required) โ Email body in_reply_to (required) โ Message ID of the email being replied to purpose (required) โ Why this action is being proposed (logged for audit)
(GitHub โ requires connected GitHub OAuth) Search GitHub issues. Data is filtered according to the owner's access control policy. Parameters: purpose (required) โ Why this data is needed (logged for audit) query (optional) โ Search query for issues limit (optional) โ Maximum number of results
(GitHub โ requires connected GitHub OAuth) Search GitHub pull requests. Data is filtered according to the owner's access control policy. Parameters: purpose (required) โ Why this data is needed (logged for audit) query (optional) โ Search query for pull requests limit (optional) โ Maximum number of results
If the MCP tools above are not available, you can call the PersonalDataHub API directly via HTTP. Config: Read ~/.pdh/config.json to get hubUrl. Pull data: curl -X POST <hubUrl>/app/v1/pull \ -H "Content-Type: application/json" \ -d '{"source": "gmail", "purpose": "reason for pulling data"}' Propose an action: curl -X POST <hubUrl>/app/v1/propose \ -H "Content-Type: application/json" \ -d '{"source": "gmail", "action_type": "draft_email", "action_data": {"to": "...", "subject": "...", "body": "..."}, "purpose": "reason for action"}'
If calls fail, check if the PersonalDataHub server is running: curl <hubUrl>/health If the server is not running, find and start it: # Check where PersonalDataHub is installed cat ~/.pdh/config.json # look at hubDir # Start the server cd <hubDir> && node dist/index.js
The install hook bootstraps PersonalDataHub automatically: Installs dependencies, builds the project, initializes the database Saves hub URL and directory to ~/.pdh/config.json Starts the server in the background After installation, open http://localhost:3000 to connect Gmail/GitHub via OAuth. Agents read config automatically from ~/.pdh/config.json โ no manual configuration needed.
is:unread โ unread emails from:alice โ emails from Alice newer_than:7d โ emails from the last 7 days subject:report โ emails with "report" in subject Combine: is:unread from:alice newer_than:7d
Data is filtered: The owner controls which fields you see. Some fields may be missing or redacted. Actions require approval: All outbound actions (emails, drafts) go to a staging queue. The owner must approve before execution. Everything is audited: Every pull and propose is logged with your purpose string.
Writing, remixing, publishing, visual generation, and marketing content production.
Largest current source with strong distribution and engagement signals.