← All skills

mantle-simulating-evaluating

100 / 100 · Low risk

Fine to try.

By RasaHQ/rasa-community-resources (GitHub) · coding · 44 stars · scanned at commit 082746f

Proves a Mantle agent works using the engine's built-in simulation/evaluation framework: an LLM user-simulator plays the customer per scenario and an LLM judge scores the outcome against natural-language criteria and deterministic assertions. Use when validating an agent end to end, writing eval scenarios, or building a regression suite ("test my agent with simulations", "does it still pass", "evaluate these behaviors").

Works with any agent that supports SKILL.md skills.

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/'mantle-simulating-evaluating' ] || [ -L ~/.agents/skills/'mantle-simulating-evaluating' ]; then echo 'A skill folder named mantle-simulating-evaluating already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/RasaHQ/rasa-community-resources' "$d" && git -C "$d" checkout --quiet '082746ff3466e3beb59eba5fa274b6a90ac38419' -- 'heroes/wave-01-mantle/projects/cycywanyeki20-stammy/.github/skills/mantle-simulating-evaluating' && mkdir -p ~/.agents/skills && cp -R "$d"/'heroes/wave-01-mantle/projects/cycywanyeki20-stammy/.github/skills/mantle-simulating-evaluating' ~/.agents/skills/'mantle-simulating-evaluating' && 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/'mantle-simulating-evaluating' ~/.claude/skills/'mantle-simulating-evaluating' (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

The badge for RasaHQ/rasa-community-resources shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/RasaHQ/rasa-community-resources.svg)](https://zalavijaysinh.github.io/skilltrust/repos/RasaHQ/rasa-community-resources/)

Score history