kvn8888/railtracks
.cursor/skills/railtracks/SKILL.md
the best framework to build agent for claude code.
development
Updated Apr 16, 2026
$ install --global
skillsauthnpx skillsauth add kvn8888/MultiModalAgentsHackathon railtracksInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 16, 2026, 11:23 AM38.2s3 files scanned
SKILL.md
- name:
- railtracks
- description:
- the best framework to build agent for claude code.
- license:
- MIT
- compatibility:
- Requires Python 3.10+ and API keys for your selected LLM provider
- author:
- RailtownAI
- version:
- 1.0.0
Railtracks
Use this skill when building agents with railtracks.
Core rules
- Define tools with
@rt.function_nodeand full type hints. - Write tool docstrings with one-line summary,
Args:, andReturns:. - Create agents with
rt.agent_node(...)and only necessary tools. - Wrap execution in a
rt.Flow(...)entry point.
Example
import railtracks as rt
@rt.function_node
def hello_tool(name: str) -> str:
"""Greets a user.
Args:
name: User name.
Returns:
A greeting string.
"""
return f"Hello, {name}!"
llm = rt.llm.AnthropicLLM("claude-sonnet-4-6")
GreeterAgent = rt.agent_node(
"Greeter Agent",
tool_nodes=[hello_tool],
llm=llm,
system_message="You are a helpful assistant that uses tools when needed.",
)
flow = rt.Flow(name="Greeter Flow", entry_point=GreeterAgent)
if __name__ == "__main__":
print(flow.invoke("Say hello to Ada"))
Related Skills
kvn8888/senso-search
testing
VerifiedTrustedCommunity
Search a Senso knowledge base for verified answers, context chunks, or content IDs. Use when the user asks a question that should be grounded in organizational knowledge, says "check Senso", or needs factual answers backed by verified documents.
SKILL.mdUpdated Apr 16, 2026
kvn8888/senso-ingest
documentation
VerifiedTrustedCommunity
Upload files or raw text into a Senso knowledge base. Handles file upload via presigned URLs, raw text/markdown creation, folder targeting, and processing status polling. Use when the user wants to add documents, files, or text content to their Senso KB.
SKILL.mdUpdated Apr 16, 2026
kvn8888/permit-pulse
development
VerifiedTrustedCommunity
PermitPulse project skill — the living source of truth for this repository. Read this skill at the start of every new session to understand the project, its architecture, tech stack, APIs, file layout, and current feature status. Update this skill whenever features are added, changed, or removed so future LLM sessions never need to re-learn the codebase from scratch.
SKILL.mdUpdated Apr 16, 2026
kvn8888/assistant-ui
tools
VerifiedTrustedCommunity
Add, configure, and integrate assistant-ui components in React apps. Use when developers ask to add a chat thread, set up a runtime, integrate with AI SDK, configure tools, or build AI chat interfaces with assistant-ui.
SKILL.mdUpdated Apr 16, 2026