mmm-trust-router
100 / 100 · Low risk
Fine to try.
Per-channel "act on the MMM" vs "validate with a test first" vs "model insufficient" classifier. Tells you which channels you can trust the MMM enough to make budget decisions on, and which require an incrementality test before acting. Use when the user mentions "which channels can I trust", "should I test or just act", "channel confidence", "trust router", "do I need to test this", "incrementality vs MMM", "where does the MMM have signal", or "what should I test next".
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'mmm-trust-router' ] || [ -L ~/.agents/skills/'mmm-trust-router' ]; then echo 'A skill folder named mmm-trust-router already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/bluealpha-labs/bluealpha-mcp-plugins' "$d" && git -C "$d" checkout --quiet '2fe5f0e3033c2d40a856758cd4ac659f3a446f1f' -- 'plugins/bluealpha-marketing-plugin/skills/mmm-trust-router' && mkdir -p ~/.agents/skills && cp -R "$d"/'plugins/bluealpha-marketing-plugin/skills/mmm-trust-router' ~/.agents/skills/'mmm-trust-router' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'mmm-trust-router' ~/.claude/skills/'mmm-trust-router' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/bluealpha-labs/bluealpha-mcp-plugins/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-10 | 2fe5f0e | 100 |