← Back to Skills Marketplace
Rag Construction
by
datadrivenconstruction
· GitHub ↗
· v2.1.0
1655
Downloads
6
Stars
6
Active Installs
2
Versions
Install in OpenClaw
/install rag-construction
Description
Build RAG systems for construction knowledge bases. Create searchable AI-powered construction document systems
Usage Guidance
This skill appears coherent and does not ask for credentials or external installs. Note it has filesystem permission (to read files you point it at) — only provide the project files you intend to index and avoid supplying sensitive system files or credentials. If you later connect cloud storage or APIs for embeddings/search, expect to supply appropriate keys then; review those requests before granting them.
Capability Analysis
Type: OpenClaw Skill
Name: rag-construction
Version: 2.1.0
The skill is designed to build RAG systems for construction knowledge bases. The Python code in SKILL.md implements document chunking, a simulated embedding model, and an in-memory vector store, with no direct external network calls or file I/O. The `claw.json` requests `filesystem` permission, which is a broad capability but justifiable for a document processing skill that would need to read input files or save exported data. The `SKILL.md` and `instructions.md` files contain no prompt injection attempts or malicious instructions for the agent. The code is well-aligned with its stated purpose and lacks any indicators of intentional harmful behavior.
Capability Assessment
Purpose & Capability
The name/description (RAG for construction documents) aligns with the provided SKILL.md code and instructions: document and chunking classes, chunking strategies, and guidance for ingesting CSV/Excel/JSON/files. Requiring python3 and filesystem access is expected for processing local documents.
Instruction Scope
SKILL.md and instructions.md focus on ingesting user-provided project data and files, chunking, embedding, search, and export. The instruction material restrains actions to data supplied or referenced by the user. There is no instruction to read unrelated system files, environment secrets, or to transmit data to unknown endpoints in the provided content.
Install Mechanism
There is no install spec and no external downloads; the skill is instruction-only. That minimizes disk writes and arbitrary code installation risk.
Credentials
The skill declares no environment variables or API credentials. The only non-code permission in claw.json is filesystem access, which is proportionate for a tool that ingests and exports local documents.
Persistence & Privilege
always is false and the skill does not request persistent/global privileges or modifications to other skills. It does request filesystem access (manifest permission), which is expected for document ingestion but is the primary privilege to be aware of.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install rag-construction - After installation, invoke the skill by name or use
/rag-construction - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.1.0
rag-construction 2.1.0
- Added SKILL.md describing the feature set, quick start guide, and technical reference.
- Provides tools for building Retrieval-Augmented Generation (RAG) systems for construction knowledge bases.
- Includes classes for document management, chunking strategies, and semantic search support.
- Enables creation of AI-powered, searchable document systems for construction projects.
- Metadata now describes supported platforms and requirements.
v1.0.0
Rag Construction 1.0.0
- Initial release of the skill to build RAG (Retrieval-Augmented Generation) systems for construction knowledge bases.
- Supports document chunking by fixed size, paragraph, section, and sentence strategies.
- Includes rich data models for construction documents, chunking, and search results.
- Designed for semantic search and AI-powered answers across construction document types such as specifications, drawings, contracts, and more.
Metadata
Frequently Asked Questions
What is Rag Construction?
Build RAG systems for construction knowledge bases. Create searchable AI-powered construction document systems. It is an AI Agent Skill for Claude Code / OpenClaw, with 1655 downloads so far.
How do I install Rag Construction?
Run "/install rag-construction" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Rag Construction free?
Yes, Rag Construction is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Rag Construction support?
Rag Construction is cross-platform and runs anywhere OpenClaw / Claude Code is available (darwin, linux, win32).
Who created Rag Construction?
It is built and maintained by datadrivenconstruction (@datadrivenconstruction); the current version is v2.1.0.
More Skills