blockrun 86 /100 Use when user needs capabilities Claude lacks (image generation, real-time X/Twitter data) or explicitly requests external models ("blockrun", "use grok", "use gpt", "dall-e", "deepseek")
uses shell commands
Type: Agent skill (SKILL.md) · Category: Marketing & SEO · Source: https://github.com/aicodedecode/awesome-muse-skills/tree/HEAD/skills-imported/bl
Score breakdown Capabilities (fewer powerful permissions = higher) 45/50 Maintenance 26/35 Documentation 15/15
Why this score Runs shell commands or spawns processes (instructions/allowed tools ask the agent to) −5 Docs include setup/install commands (one-time setup, not penalised) Instructions only: no bundled scripts Last updated 5 days ago +15 23 GitHub stars +4 2 contributors +2 License: MIT +5 Description and source link present +15 Always review files before installing. How scores work . Request a correction
Weekly: new skills & MCP servers, scored.
Scores are automated static checks of public files and metadata, not a security audit. They describe what an item can do, not its authors' intent. Updated 2026-10-16.