vmobifystudio

App Eval — Development skill for Claude Code

Development community

/app-eval — run deterministic agent evaluations.

How to install App Eval

Installs to ~/.claude/skills/vmobifystudio-app-dev-team-app-eval/SKILL.md

Terminal

mkdir -p ~/.claude/skills/vmobifystudio-app-dev-team-app-eval && curl -fsSL https://raw.githubusercontent.com/vmobifystudio/app-dev-team/HEAD/commands/app-eval.md -o ~/.claude/skills/vmobifystudio-app-dev-team-app-eval/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What App Eval does

/app-eval — run deterministic agent evaluations

Evaluation manifests define reproducible cases with an executable command, expected exit code, and required evidence text:

node "${CLAUDE_PLUGIN_ROOT}/scripts/eval-lab.mjs" --manifest eval/manifest.json

Add role, policy, workflow, and long-horizon fixtures as the team grows. A missing manifest or malformed case is `CANNOT EVALUATE`, never a passing empty suite.

Alternatives in Development

Learn Eval — 从会话中提取可复用的模式（Patterns），在保存前进行质量自评，并确定合适的保存位置（全局 vs 项目） 1.9k ★
/autopilot — Autonomous hunt loop with deterministic scope safety and configurable checkpoints 1.2k ★
Hippo Feature — Build one hippo feature from RESEARCH.md using the micro-eval TDD loop 734 ★