← All topics

Prompting

Prompt engineering, system prompts, and reusable patterns.

377 posts

Claude Skill 4

A local-first SAST & Runtime Security scanner built exclusively for LLM Agents. Detects cross-modal data leaks, prompt injections, and inter...

Python Updated 2w ago
MCP Server 17

.NET MCP bridge: expose app methods/data as MCP tools, prompts, and resources via an in-app plugin + lightweight server (SignalR; stdio/http...

C# Apache-2.0 Updated 2w ago
MCP Server 8

A magical witch assistant equipped with an enchanted grimoire powered by AI, yet shaped by you: your agents, your prompts, your tools...wove...

C# Apache-2.0 Updated 2w ago
MCP Server 29

local-first MCP discovery runtime for agents — search before invoke, reduce prompt bloat, and route to local MCP tools

Go MIT Updated 2mos ago
MCP Server 9

Arc Gate — LLM proxy with prompt injection detection. Bendex Geometry.

Python NOASSERTION Updated 2w ago
MCP Server 2

An automated red-teaming and reliability-auditing platform for AI agents - tests for prompt injection, tool hijacking and data exfiltration....

Python MIT Updated 2w ago
MCP Server 35

Arkana - Your entire malware analysis lab, behind one AI prompt. 250+ MCP tools for binary analysis with Claude Code or other MCP

Python MIT Updated 3mos ago
MCP Server 6

Intent-addressable code for AI agents. Causari records every action an agent takes on your codebase - the prompt, model, reads, writes and r...

Rust NOASSERTION Updated 2w ago
MCP Server 13

Full-featured Android Debug Bridge MCP server — 204 tools across 45 modules, 5 resources, and 4 prompts, from UI to baseband.

TypeScript Apache-2.0 Updated 1mo ago
MCP Server 60

The AI-native workspace platform. Projects remember. Agents think. Automations execute. One prompt to production — bug reports & feature req...

NOASSERTION Updated 1mo ago
MCP Server 46

Save 47% on Manus AI credits automatically. Zero downsides. Pays for itself in ~27 prompts. Free MCP Server (PyPI) + $12 Manus Skill bundle...

Python MIT Updated 2mos ago
Claude Skill 35

Trust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, red-flag patterns, ref...

Shell MIT Updated 2mos ago