Apeironics

Silently restructures the user's natural-language prompt into the format the model CURRENTLY running this skill handles best, then answers. On activation it identifies which model family is executing it (Claude, GPT, Gemini, Llama, DeepSeek, Mistral, Qwen, Grok, Perplexity, Kimi, GLM, Command, Nova, or Phi) and loads that one model's official strategy — so the optimization always matches the model that actually runs it. Activate with /prompt-refine. Use when users want better answers without learning prompt engineering.

Scan Model Context Protocol (MCP) servers for security vulnerabilities with the MCP-Safeguard CLI (@mcp-safeguard/cli). Use this when the user wants to audit or scan an MCP server/tool for security risks, triage or explain scan findings, fix MCP security issues (tool poisoning, rug-pull, cross-server shadowing, prompt injection, credential passthrough, command injection, secrets, SSRF, path traversal, excessive agency, context overshare), produce SARIF/JSON/HTML reports, or add MCP security scanning to CI / GitHub Actions. This skill drives the existing published CLI — it never reimplements the scanner.

Scan Model Context Protocol (MCP) servers for security vulnerabilities with the MCP-Safeguard CLI (@mcp-safeguard/cli). Use this when the user wants to audit or scan an MCP server/tool for security risks, triage or explain scan findings, fix MCP security issues (tool poisoning, rug-pull, cross-server shadowing, prompt injection, credential passthrough, command injection, secrets, SSRF, path traversal, excessive agency, context overshare), produce SARIF/JSON/HTML reports, or add MCP security scanning to CI / GitHub Actions. This skill drives the existing published CLI — it never reimplements the scanner.