← Back to Skills Marketplace
Safegraph
by
Vlad Ursul
· GitHub ↗
· v1.0.2
· MIT-0
109
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install safegraph
Description
SafeGraph integration. Manage data, records, and automate workflows. Use when the user wants to interact with SafeGraph data.
Usage Guidance
This skill is instruction-only and coherent: it tells you to use the Membrane CLI to connect to SafeGraph rather than embedding credentials locally. Before installing or following the instructions: (1) verify you trust the Membrane service and @membranehq/cli (review their docs, privacy, and terms), because API calls and auth happen through their servers; (2) prefer using npx @membranehq/cli@latest for one-off runs if you don't want a global npm install; (3) understand that proxying arbitrary endpoints will send whatever request body/parameters you provide to Membrane — avoid sending sensitive local secrets unless you intend them to be transmitted; (4) in headless or automated environments, follow the documented headless-auth flow carefully and avoid exposing login codes in logs. Overall the skill appears coherent with its purpose, but trust in the third-party (Membrane) is the main consideration.
Capability Assessment
Purpose & Capability
Name/description match the instructions: the SKILL.md directs the user to use the Membrane CLI to connect to SafeGraph and run actions. There are no unrelated credential or binary requests in the manifest.
Instruction Scope
Instructions ask the user to install and run the Membrane CLI, perform browser-based login, create connections, list actions, run actions, and proxy arbitrary SafeGraph API requests via Membrane. These steps are within the stated purpose, but proxying arbitrary endpoints means requests (and any data you send) will flow through Membrane's service — users should be aware of that external data flow.
Install Mechanism
No install spec in the skill bundle (instruction-only), but SKILL.md recommends installing @membranehq/cli via npm -g. Installing an npm package globally is a reasonable step for this integration, but global npm installs modify the system and pull code from the public registry — verify you trust @membranehq/cli or use npx to avoid a global install.
Credentials
The skill declares no required env vars or credentials and explicitly instructs not to ask users for SafeGraph API keys (Membrane handles auth). That is proportionate to the stated goal. Note: using Membrane implies third-party custody of auth/session tokens handled server-side.
Persistence & Privilege
The skill is not always-enabled and is user-invocable. It does not request persistent system privileges or modify other skills' configuration. No elevated persistence is requested.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install safegraph - After installation, invoke the skill by name or use
/safegraph - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
Revert refresh marker
v1.0.1
Refresh update marker
v1.0.0
Auto sync from membranedev/application-skills
Metadata
Frequently Asked Questions
What is Safegraph?
SafeGraph integration. Manage data, records, and automate workflows. Use when the user wants to interact with SafeGraph data. It is an AI Agent Skill for Claude Code / OpenClaw, with 109 downloads so far.
How do I install Safegraph?
Run "/install safegraph" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Safegraph free?
Yes, Safegraph is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Safegraph support?
Safegraph is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Safegraph?
It is built and maintained by Vlad Ursul (@gora050); the current version is v1.0.2.
More Skills