skill-upper
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, verify, fix, improve, iterate, or evolve a Skill; add or strengthen eval cases; write eval.yaml/case.yaml; run skill-up run/validate/list-cases/report/import/init; or migrate from Anthropic evals.json. Handles Skill discovery, eval scaffolding, judge authoring, validation, runs, reports, and evidence-based repair loops.
Profile →npx skills add alibaba/skill-up --skill skill-upper --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# use-skill-up-cli Help the user evaluate and evolve Agent Skills through the `skill-up` CLI. Manual: <https://alibaba.github.io/skill-up/> ## Language Policy **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.** Detection rules (highest priority first): 1. The user explicitly specifies a language in the current message (e.g. "answer in English" / "用中文回答") → follow the user's instruction. 2. The natural language used in the user's current message → match it. 3. None of the above → use English (default). Regardless of the response language, technical identifiers in this SKILL — CLI commands, `eval.yaml` / `case.yaml` field names, report field names, etc. — MUST stay in their original English form. Do not translate them. ### Language Rules for Generated Artifacts When creating or editing `eval.yaml`, `case.yaml`, grading scripts, README snippets, final replies, or any other user-visible artifact, treat the language of the user's current message as the output language for this turn: - If the user asks in Chinese, write the final response and al
- Language Policy
- Language Rules for Generated Artifacts
- What is skill-up
- When to trigger
- Main flow (follow this order strictly)
- Step 0: Make sure skill-up is installed
- Step 0.5 (optional): User config and telemetry
- Step 1: Locate the target Skill
- Step 2: Scaffold the evals (only when none exist)
- Step 3: Fill the gaps (when evals already exist)
- Step 4: Validate the configuration
- Step 5: Prepare credentials
- Step 6: Run the evaluation
- Step 7: Interpret the report
command -v skill-up && skill-up --version curl -fsSL https://raw.githubusercontent.com/alibaba/skill-up/main/install.sh | bash export SKILL_UP_VERSION=v0.1.0 export INSTALL_DIR="$HOME/bin" skill-up init skill-up init --local skill-up init --print skill-up init --force skill-up validate <skill-root>/evals/eval.yaml printenv | grep -E 'ANTHROPIC_API_KEY|OPENAI_API_KEY|QODER_PERSONAL_ACCESS_TOKEN'
What does the skill-upper skill do?
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, verify, fix, improve, iterate, or evolve a Skill; add or strengthen eval cases; write eval.yaml/case.yaml; run skill-up run/validate/list-cases/report/import/init; or migrate from Anthropic evals.json. Handles Skill discovery, eval scaffolding, judge authoring, validation, runs, reports, and evidence-based repair loops.
How do I install it?
Run `npx skills add alibaba/skill-up --skill skill-upper --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From alibaba/skill-up, a repository with 374 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.