← All skills
skill-upper
72 / 100 · Review before installing
Check before installing.
By alibaba/skill-up (GitHub) · other · 1,474 stars · scanned at commit 1d624e0
Capture and review Agent Skill observations, and create, run, diagnose, or iteratively improve Skill evaluations (evals) with the skill-up CLI. Use when the user asks to record explicitly attributed Skill usage or feedback; review observations or user-supplied traces/transcripts; turn an approved observation into a regression case; 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-ca…
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
This is disclosed by the author in the skill's SKILL.md or README.
Found in 22 places.
Show 17 more
- skills/skill-upper/SKILL.md, line 238
skill-up validate <skill-root>/evals/eval.yaml - skills/skill-upper/SKILL.md, line 269
if printenv OPENAI_API_KEY | grep -q .; then - skills/skill-upper/SKILL.md, line 295
skill-up run <skill-root>/evals/eval.yaml - skills/skill-upper/evals/fixtures/scripts/assert-credential-presence.sh, line 601
result = subprocess.run(argv, cwd=root, env=env, text=True, capture_output=True, timeout=10) - skills/skill-upper/evals/fixtures/scripts/assert-localized-regressions.sh, line 316
validation = subprocess.run(["skill-up", "validate", "evals/eval.yaml"], text=True, capture_output=True, timeout=20) - skills/skill-upper/evals/fixtures/scripts/assert-localized-regressions.sh, line 318
result = subprocess.run(["skill-up", "list-cases", "evals/eval.yaml"], text=True, errors="replace", capture_output=True, timeout=20) - skills/skill-upper/evals/test_regression_scripts.py, line 32
result = subprocess.run( - skills/skill-upper/evals/test_regression_scripts.py, line 160
self.check_command('assert-credential-presence.sh', 'bash -c \'"$1" run evals/eval.yaml\' ignored skill-up', False, 'positional shell') - skills/skill-upper/evals/test_regression_scripts.py, line 161
self.check_command('assert-read-only-plan.sh', 'bash -c \'cat SKILL.md\' ignored', True) - skills/skill-upper/evals/test_regression_scripts.py, line 162
self.check_command('assert-localized-regressions.sh', 'bash -c \'skill-up run evals/eval.yaml\' ignored', False, 'launched an evaluation') - skills/skill-upper/evals/test_regression_scripts.py, line 166
('assert-credential-presence.sh', "bash -c 'echo ready' ignored; printenv OPENAI_API_KEY | cut -c 1"), - skills/skill-upper/evals/test_regression_scripts.py, line 167
('assert-credential-presence.sh', "bash -c 'echo ready' ignored \"$OPENAI_API_KEY\""), - skills/skill-upper/evals/test_regression_scripts.py, line 168
('assert-read-only-plan.sh', "bash -c 'cat SKILL.md' ignored; touch /tmp/outside-fixture"), - skills/skill-upper/evals/test_regression_scripts.py, line 169
('assert-localized-regressions.sh', "bash -c 'echo ready' ignored; skill-up run evals/eval.yaml"), - skills/skill-upper/evals/test_regression_scripts.py, line 170
('assert-credential-presence.sh', "bash -c 'echo ready' ignored\nprintenv OPENAI_API_KEY | cut -c 1"), - skills/skill-upper/evals/test_regression_scripts.py, line 175
self.check_command('assert-credential-presence.sh', "bash -c 'printenv OPENAI_API_KEY | grep -q .' 'ignored;label'", True) - skills/skill-upper/evals/test_regression_scripts.py, line 189
for command in ("env bash -c 'printenv OPENAI_API_KEY | cut -c 1'", "nice bash -c 'skill-up run evals/eval.yaml'", "nohup sh -c 'printenv OPENAI_API_KEY | cut -
and 2 more places
Downloads and installs other software
The author does not mention this.
Found in 8 places.
Show 5 more
Sends data to these websites: raw.githubusercontent.com
The author does not mention this.
Found in 8 places.
Show 5 more
Changes files outside its own folder
This is disclosed by the author in the skill's SKILL.md or README.
Found in 2 places.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'skill-upper' ] || [ -L ~/.agents/skills/'skill-upper' ]; then echo 'A skill folder named skill-upper already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/alibaba/skill-up' "$d" && git -C "$d" checkout --quiet '1d624e036195bc317d7d8c8779402329783c7835' -- 'skills/skill-upper' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/skill-upper' ~/.agents/skills/'skill-upper' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'skill-upper' ~/.claude/skills/'skill-upper' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for alibaba/skill-up shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/alibaba/skill-up/)
Score history
| Date | Version | Score |
|---|
| 2026-11-14 | 1d624e0 | 72 |
| 2026-11-10 | 7814813 | 72 |
| 2026-11-08 | 80a6a8d | 72 |
| 2026-11-07 | 80a6a8d | 62 |