What it does. Help the user evaluate and evolve Agent Skills through the
skill-up
CLI.
Default to English when responding to the user. If the user writes in Chinese (or any other language), switch to that language and stay consistent with the user's input throughout the session.
Highlights
- Keep technical identifiers unchanged, such as
schema_version
, environment.type
, engine.name
, rule_based
, agent_judge
, script_path
, file paths, and commands.
- Generated YAML comments must use field-leading comments. Keep each comment short: one line for field meaning, plus one line for options only when useful.
- When listing options in comments, keep enum values unchanged, such as
none | opensandbox | docker
and rule_based | agent_judge | script
.
skill-up import
uses the CLI conversion path and does not preserve template comments; do not promise commented YAML for import-generated files.- The user asks to "run / evaluate / verify / test this skill".
When to use it. Create, run, diagnose, and iteratively improve Agent Skill evaluations (evals) with the skill-up CLI / 使用 skill-up CLI 创建、运行、诊断并持续改进 Agent Skill 评测. Use when the user asks to evaluate, test, regress…
Install
npx skills add alibaba/skill-up --skill skill-upper
Or copy the skill folder manually:
git clone https://github.com/alibaba/skill-up.git
cp -r skill-up/skills/skill-upper/ ~/.claude/skills/skill-upper
Source: alibaba/skill-up — 802 stars, Apache-2.0, last pushed 2026-09-02.
