← All skills
skill-evaluator
79 / 100 · Review before installing
Check before installing. Some of what it can do is expected: a coding skill usually runs build and test commands.
By HeshamFS/materials-simulation-skills (GitHub) · coding · 83 stars · scanned at commit 7750559
Rigorously evaluate an Agent Skill end-to-end across ANY coding-agent CLI — verify its scripts emit the documented numbers (deterministic checks), test whether its description triggers on the right prompts, and measure whether an agent following the SKILL.md beats a no-skill baseline (with/without pass-rate delta, mean ± stddev, benchmarked). Use whenever you need to test, benchmark, validate, grade, or quantify a skill's quality, check if a skill "actually works," compare two skill versions, o…
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. Expected for a coding skill.
Found in 13 places.
Show 10 more
- skills/meta/skill-evaluator/SKILL.md, line 91
python scripts/run_trigger_eval.py --skill <path> --agent <agent> --dry-run - skills/meta/skill-evaluator/SKILL.md, line 108
python scripts/run_quality_eval.py --skill <path> --agent <agent> \ - skills/meta/skill-evaluator/SKILL.md, line 128
python scripts/aggregate_benchmark.py <skill>-workspace/iteration-1 \ - skills/meta/skill-evaluator/SKILL.md, line 140
python eval-viewer/generate_review.py <skill>-workspace/iteration-1/benchmark.json -o review.html - skills/meta/skill-evaluator/SKILL.md, line 213
`shell=True`); commands are built from the adapter spec, not string-concatenated. - skills/meta/skill-evaluator/scripts/run_quality_eval.py, line 138
proc = subprocess.run(argv, cwd=cwd, capture_output=True, text=True, - skills/meta/skill-evaluator/scripts/run_quality_eval.py, line 149
except subprocess.TimeoutExpired: - skills/meta/skill-evaluator/scripts/run_script_checks.py, line 129
proc = subprocess.run([sys.executable, str(script), *[str(a) for a in cmd[1:]]], - skills/meta/skill-evaluator/scripts/run_trigger_eval.py, line 76
proc = subprocess.run(argv, cwd=cwd, capture_output=True, text=True, - skills/meta/skill-evaluator/scripts/run_trigger_eval.py, line 82
except subprocess.TimeoutExpired:
Downloads and installs other software
The author does not mention this.
Found in 8 places.
Show 5 more
- skills/meta/skill-evaluator/scripts/agent_adapters.py, line 129
"install": "curl https://cursor.com/install -fsS | bash", - skills/meta/skill-evaluator/scripts/agent_adapters.py, line 152
"install": "npm i -g @github/copilot (requires Node 22+)", - skills/meta/skill-evaluator/scripts/agent_adapters.py, line 176
"install": "curl -fsSL https://ampcode.com/install.sh | bash", - skills/meta/skill-evaluator/scripts/agent_adapters.py, line 200
"install": "curl -fsSL https://opencode.ai/install | bash (the sst/opencode at opencode.ai)", - skills/meta/skill-evaluator/scripts/agent_adapters.py, line 224
"install": "curl -fsSL https://x.ai/cli/install.sh | bash",
Sends data to these websites: claude.ai, antigravity.google, cursor.com, ampcode.com, opencode.ai, x.ai
This is disclosed by the author in the skill's SKILL.md or README.
Found in 6 places.
Show 3 more
Safer alternatives
Low-risk skills in the same category (coding) that look related. Check that one does what you need.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'skill-evaluator' ] || [ -L ~/.agents/skills/'skill-evaluator' ]; then echo 'A skill folder named skill-evaluator already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/HeshamFS/materials-simulation-skills' "$d" && git -C "$d" checkout --quiet '775055956bb8fa3838032c49a346e26d94d0d1f6' -- 'skills/meta/skill-evaluator' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/meta/skill-evaluator' ~/.agents/skills/'skill-evaluator' && 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-evaluator' ~/.claude/skills/'skill-evaluator' (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 HeshamFS/materials-simulation-skills shows the score of its lowest-scoring skill.

[](https://zalavijaysinh.github.io/skilltrust/repos/HeshamFS/materials-simulation-skills/)
Score history
| Date | Version | Score |
|---|
| 2026-11-08 | 7750559 | 100 |
| 2026-11-06 | 7750559 | 79 |