spectredeath/skill-flywheel/skill-sme-gateway-connection

Claude Code and agent skill by spectredeath/skill-flywheel

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Install

npx vskill@latest install spectredeath/skill-flywheel/skill-sme-gateway-connection

SKILL.md

The same SKILL.md was published earlier as spectredeath/skill-flywheel/skill-sme-gateway-connection.

Purpose

Establishes and manages connection to the SME (Semantic Memory Engine) MCP Gateway for accessing forensic AI capabilities. This skill enables AI agents to connect to the Lawnmower Man gateway and execute MCP tools.

Description

The SME Gateway provides a Model Context Protocol (MCP) server that exposes forensic capabilities including trust scoring, adversarial pattern detection, stylometric analysis, and web ingestion. This skill handles connection lifecycle, authentication, and tool invocation through the MCP protocol.

Workflow

  1. Connection Setup: Initialize MCP client with gateway URL and credentials
  2. Handshake: Perform capability negotiation with the gateway
  3. Tool Discovery: Enumerate available MCP tools and their schemas
  4. Tool Invocation: Execute specific forensic tools via JSON-RPC
  5. Result Processing: Parse and validate tool responses
  6. Connection Management: Handle reconnection and session persistence

Examples

Example 1: Connect to Local SME Gateway

Input: Request to connect to SME gateway at localhost:8000 Output: Active MCP connection with discovered tools Use Case: Connecting to local SME instance for testing

Example 2: Connect to Remote SME Gateway

Input: Request to connect to SME gateway with API key Output: Authenticated connection to remote SME instance Use Case: Connecting to production SME deployment

Example 3: List Available Tools

Input: Request to enumerate MCP tools Output: List of available forensic tools with schemas Use Case: Discovering tool capabilities before execution

Implementation Notes

  • Protocol: MCP (Model Context Protocol) over stdio or HTTP
  • Authentication: API key or TPM-signed requests
  • Python Dependencies: mcp client SDK, pydantic
  • Gateway Location: D:/SME/gateway/mcp_server.py
  • Port: 8000 (default)

Capabilities Exposed

  • trust_score_analysis - Calculate epistemic trust scores
  • adversarial_pattern_detect - Detect AI-smoothed text
  • stylometric_analyze - Analyze writing style signatures
  • harvester_ingest - Ingest web content
  • forensic_store - Store evidentiary data
  • logic_verify - Verify logical consistency

See Also

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
1
Repository forks
1
7-day trend score
8

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/spectredeath/skill-flywheel/skill-sme-gateway-connection/badge)](https://verified-skill.com/skills/spectredeath/skill-flywheel/skill-sme-gateway-connection)

Something wrong with this skill or its page? Tell us.