← All skills
llm-stats
75 / 100 · Review before installing
Check before installing.
By Integralist/agent-skills (GitHub) · other · 25 stars · scanned at commit 2979675
Build a shareable, offline HTML chart of Artificial Analysis model benchmarks, with a line per model family across effort levels and searchable model selection. Use when the user wants to compare LLM benchmark scores against cost, tokens, time, price, or speed.
Works with any agent that supports SKILL.md skills.
What this skill can do
Downloads and installs other software
The author does not mention this.
Found in 3 places.
Runs commands on your computer
The author does not mention this.
Found in 16 places.
Show 13 more
- .agents/skills/llm-stats/scripts/report.py, line 827
subprocess.run( - .agents/skills/llm-stats/tests/test_report.py, line 564
result = subprocess.run( - .agents/skills/llm-stats/tests/test_report.py, line 742
result = subprocess.CompletedProcess([], 0, stdout="secret-from-op\n", stderr="") - .agents/skills/llm-stats/tests/test_report.py, line 743
with patch("report.subprocess.run", return_value=result) as command: - .agents/skills/llm-stats/tests/test_report.py, line 763
subprocess.CompletedProcess([], 1, stdout="secret-body", stderr="secret-body"), - .agents/skills/llm-stats/tests/test_report.py, line 765
subprocess.TimeoutExpired("op", 60, output="secret-body"), - .agents/skills/llm-stats/tests/test_report.py, line 776
with patch("report.subprocess.run", **kwargs), pytest.raises(DataError) as error: - .agents/skills/llm-stats/tests/test_report.py, line 794
with patch("report.subprocess.run") as command, pytest.raises(DataError): - .agents/skills/llm-stats/tests/test_report.py, line 801
with patch("report.subprocess.run") as command: - .agents/skills/llm-stats/tests/test_report.py, line 818
with patch("report.subprocess.run") as command: - .agents/skills/llm-stats/tests/test_report.py, line 839
"report.subprocess.run", - .agents/skills/llm-stats/tests/test_report.py, line 840
return_value=subprocess.CompletedProcess([], returncode), - .agents/skills/llm-stats/tests/test_report.py, line 856
patch("report.subprocess.run", side_effect=OSError("not available")),
Connects to the internet
The author does not mention this.
Found in 16 places.
Show 13 more
- .agents/skills/llm-stats/tests/test_report.py, line 265
with patch("urllib.request.urlopen", return_value=response) as request: - .agents/skills/llm-stats/tests/test_report.py, line 277
patch("urllib.request.urlopen", side_effect=error), - .agents/skills/llm-stats/tests/test_report.py, line 286
patch("urllib.request.urlopen", side_effect=URLError("offline")), - .agents/skills/llm-stats/tests/test_report.py, line 296
patch("urllib.request.urlopen", return_value=io.BytesIO(b'{"data": []}')), - .agents/skills/llm-stats/tests/test_report.py, line 447
"urllib.request.urlopen", - .agents/skills/llm-stats/tests/test_report.py, line 463
with patch("urllib.request.urlopen") as request: - .agents/skills/llm-stats/tests/test_report.py, line 473
"urllib.request.urlopen", return_value=io.BytesIO(json.dumps(api_page).encode()) - .agents/skills/llm-stats/tests/test_report.py, line 488
"urllib.request.urlopen", - .agents/skills/llm-stats/tests/test_report.py, line 516
"urllib.request.urlopen", - .agents/skills/llm-stats/tests/test_report.py, line 536
"urllib.request.urlopen", - .agents/skills/llm-stats/tests/test_report.py, line 617
with patch("urllib.request.urlopen") as request, pytest.raises(DataError) as error: - .agents/skills/llm-stats/tests/test_report.py, line 627
patch("urllib.request.urlopen", return_value=io.BytesIO(content)), - .agents/skills/llm-stats/tests/test_report.py, line 637
"urllib.request.urlopen",
Safer alternatives
Low-risk skills in the same category (other) 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/'llm-stats' ] || [ -L ~/.agents/skills/'llm-stats' ]; then echo 'A skill folder named llm-stats already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/Integralist/agent-skills' "$d" && git -C "$d" checkout --quiet '29796755244a6ede32c118686eb7a6a374055099' -- '.agents/skills/llm-stats' && mkdir -p ~/.agents/skills && cp -R "$d"/'.agents/skills/llm-stats' ~/.agents/skills/'llm-stats' && 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/'llm-stats' ~/.claude/skills/'llm-stats' (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 Integralist/agent-skills shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/Integralist/agent-skills/)
Score history
| Date | Version | Score |
|---|
| 2026-11-12 | 2979675 | 75 |
| 2026-11-08 | 9ed9a4c | 75 |