Monte Carlo Asset Health
Structured freshness/alerts/monitoring/upstream health report for one Monte Carlo asset.
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 13, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 9ab89d6
Report template hard-bans fabricated numbers ('Do NOT infer or fabricate metrics') and forces an explicit refusal when the underlying MCP tools aren't wired up, instead of the generic hallucinated summary a baseline answer would produce.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 8/10
- Docs & honesty 4/5
What Monte Carlo Asset Health does
Generates a fixed-format health report (status, alerts, monitor coverage, upstream lineage, diagnosis, recommendations) for a single data table via Monte Carlo's MCP tools. Triggers on health/status questions about a named table and explicitly defers profiling and monitor-creation asks to sibling skills, so it stays narrow and doesn't overtrigger.
How to install Monte Carlo Asset Health
git clone https://github.com/monte-carlo-data/mc-agent-toolkit
cd mc-agent-toolkit
mkdir -p ~/.claude/skills
cp -r skills/asset-health ~/.claude/skills/monte-carlo-asset-health
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Monte Carlo Asset Health
-
/monte-carlo-asset-healthStructured freshness/alerts/monitoring/upstream health report for one Monte Carlo asset.
It also activates on plain-language prompts like these:
-
What's the freshness and alert status on this Monte Carlo table -
Give me a health report on this data asset's upstream lineage -
Check monitor coverage and diagnosis for this named table
Frequently asked questions
- Is the Monte Carlo Asset Health skill free?
- Yes. The skill itself is free from monte-carlo-data/mc-agent-toolkit. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Monte Carlo Asset Health work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 13, 2026. Verdict: Tested · Works. Report template hard-bans fabricated numbers ('Do NOT infer or fabricate metrics') and forces an explicit refusal when the underlying MCP tools aren't wired up, instead of the generic hallucinated summary a baseline answer would produce.
- What is the Monte Carlo Asset Health SkillProof Score?
- 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
- How do I install Monte Carlo Asset Health?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Monte Carlo Asset Health with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.