← Back to Skills Marketplace
safatinaztepe

Knowledge Graph

by SafaTinaztepe · GitHub ↗ · v1.0.0
cross-platform ✓ Security Clean
7448
Downloads
5
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install knowledge-graph
Description
Maintain Clawdbot's compounding knowledge graph under life/areas/** by adding/superseding atomic facts (items.json), regenerating entity summaries (summary.md), and keeping IDs consistent. Use when you need deterministic updates to the knowledge graph rather than manual JSON edits.
Usage Guidance
Install this if you want an agent to maintain local knowledge-graph files under life/areas. Review or back up those files if they matter, and prefer a version that explicitly declares its file read/write scope.
Capability Analysis
Type: OpenClaw Skill Name: knowledge-graph Version: 1.0.0 The skill bundle is designed to manage a file-based knowledge graph within the OpenClaw workspace. The `SKILL.md` provides clear, non-malicious instructions for the agent, with no evidence of prompt injection attempts. The `scripts/kg.py` Python script performs file I/O operations (reading/writing `items.json` and `summary.md`) strictly within the designated `life/areas/` directory relative to the workspace root. It does not access sensitive files, make network calls, execute arbitrary commands, or exhibit any other high-risk behaviors or obfuscation techniques.
Capability Assessment
Purpose & Capability
The stated purpose is a file-based knowledge graph, and reading/writing items.json and summary.md under life/areas is coherent with that purpose.
Instruction Scope
The described runtime scope is narrow and workspace-local, but the supplied SkillSpector finding indicates the skill does not explicitly declare its needed file read/write permissions.
Install Mechanism
No install-time execution, dependency installation, persistence setup, or privileged configuration is indicated by the supplied telemetry.
Credentials
Workspace-local file I/O for knowledge graph data is proportionate; there is no indicated access to credentials, session stores, broad private files, or network services.
Persistence & Privilege
The skill intentionally modifies persistent knowledge graph files, which is expected for its function; no background worker, privilege escalation, or hidden persistence is indicated.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install knowledge-graph
  3. After installation, invoke the skill by name or use /knowledge-graph
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of the knowledge-graph skill. - Enables safe, programmatic updates to Clawdbot's knowledge graph under life/areas/**. - Add or supersede atomic facts for any entity via command-line scripts. - Ensures fact IDs remain consistent and auto-increment per entity. - Supports regenerating entity summaries from active facts. - Removes the need for manual JSON edits; prevents deletion of facts by enforcing supersession.
Metadata
Slug knowledge-graph
Version 1.0.0
License
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Knowledge Graph?

Maintain Clawdbot's compounding knowledge graph under life/areas/** by adding/superseding atomic facts (items.json), regenerating entity summaries (summary.md), and keeping IDs consistent. Use when you need deterministic updates to the knowledge graph rather than manual JSON edits. It is an AI Agent Skill for Claude Code / OpenClaw, with 7448 downloads so far.

How do I install Knowledge Graph?

Run "/install knowledge-graph" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Knowledge Graph free?

Yes, Knowledge Graph is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Knowledge Graph support?

Knowledge Graph is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Knowledge Graph?

It is built and maintained by SafaTinaztepe (@safatinaztepe); the current version is v1.0.0.

💬 Comments