Skill Crossroads — ml-engineer

Skill Crossroads ml-engineer
rubric v1.2 · deterministic

overall

Correctness & Structure 100 pass

Triggering & Discoverability 85 1 warn

Clarity & Instructions 100 pass

Token & Context Cost 100 pass

Safety & Security 79 2 warn

Verifiability & Maintainability not yet scored

Top fixes — ranked by score impact

⚠ SAFETY-03 No destructive auto-invocation

ml-engineer.md:3auto-invocable (no disable-model-invocation) → performs a destructive action ("deployment")

Skill appears to "deployment" but the model can auto-invoke it — a destructive action could fire without the user asking.

deployment

Fix If this action is destructive/irreversible, set `disable-model-invocation: true` so it only runs when explicitly invoked.

⚠ TRIGGER-03 Invocation cues in the description

ml-engineer.md:1description will match user requests → no explicit cue ('use when …', 'triggers on …', quoted user phrases) found

Pure what-it-does prose — the model has to guess when to invoke it.

Designs, builds, and manages the end-to-end lifecycle of machine learning mod…

Fix State the trigger explicitly: 'Use when the user says "…", "…", or wants to …'.

⚠ SAFETY-02 allowed-tools least-privilege

ml-engineer.md:1— → grants unrestricted shell access

`allowed-tools` grants unrestricted `Bash` — scope it to specific commands.

Bash

Fix Replace bare `Bash` with scoped grants, e.g. `Bash(git status)`, `Bash(npm test)`.

Partial grade — some applicable rubric categories were not scored on this scan (e.g. LLM-assisted checks without a key) and are excluded from the overall.

Embed this badge

Always-fresh — it re-scans and updates on its own.

[![Skill Crossroads](https://skillcrossroads.com/api/badge/qdhenry/Claude-Command-Suite/.claude/agents/data-ai/ml-engineer.md.svg)](https://skillcrossroads.com/s/qdhenry/Claude-Command-Suite/.claude/agents/data-ai/ml-engineer.md)

Grade your own Claude Code skill — evidence-cited, file-and-line, free. Scan your own skill →