← All skills
evaluating-llms
65 / 100 · Review before installing
Check before installing.
By ancoleman/ai-design-components (GitHub) · design · 530 stars · scanned at commit 76551b7
Evaluate LLM systems using automated metrics, LLM-as-judge, and benchmarks. Use when testing prompt quality, validating RAG pipelines, measuring safety (hallucinations, bias), or comparing models for production deployment.
Works with any agent that supports SKILL.md skills.
What this skill can do
Can call paid AI services billed to you
The author does not mention this.
Found in 11 places.
Show 8 more
Sends data to these websites: api.openai.com
The author does not mention this.
Found in 13 places.
Show 10 more
- skills/evaluating-llms/examples/python/llm_as_judge.py, line 19
from openai import OpenAI - skills/evaluating-llms/examples/python/ragas_example.py, line 23
import openai - skills/evaluating-llms/examples/python/unit_evaluation.py, line 20
from openai import OpenAI - skills/evaluating-llms/examples/typescript/llm-as-judge.ts, line 15
import OpenAI from "openai"; - skills/evaluating-llms/examples/typescript/unit-evaluation.ts, line 17
import OpenAI from "openai"; - skills/evaluating-llms/references/safety-evaluation.md, line 71
from openai import OpenAI - skills/evaluating-llms/references/safety-evaluation.md, line 126
response = requests.get(url, params=params) - skills/evaluating-llms/references/safety-evaluation.md, line 140
from openai import OpenAI - skills/evaluating-llms/references/safety-evaluation.md, line 419
response = requests.post( - skills/evaluating-llms/references/safety-evaluation.md, line 487
from openai import OpenAI
Downloads and installs other software
The author does not mention this.
Found in 24 places.
Show 17 more
- skills/evaluating-llms/SKILL.md, line 385
| **LangSmith** | Production monitoring, A/B testing | `pip install langsmith` | - skills/evaluating-llms/SKILL.md, line 386
| **lm-eval** | Benchmark testing (MMLU, HumanEval) | `pip install lm-eval` | - skills/evaluating-llms/SKILL.md, line 387
| **scikit-learn** | Classification metrics | `pip install scikit-learn` | - skills/evaluating-llms/examples/python/benchmark_testing.py, line 8
pip install openai datasets - skills/evaluating-llms/examples/python/classification_metrics.py, line 8
pip install scikit-learn numpy matplotlib seaborn - skills/evaluating-llms/examples/python/deepeval_example.py, line 8
pip install deepeval openai - skills/evaluating-llms/examples/python/llm_as_judge.py, line 8
pip install openai anthropic - skills/evaluating-llms/examples/python/ragas_example.py, line 8
pip install ragas datasets openai langchain - skills/evaluating-llms/examples/python/ragas_example.py, line 260
print("2. Install dependencies: pip install ragas datasets openai") - skills/evaluating-llms/examples/python/unit_evaluation.py, line 8
pip install pytest openai sentence-transformers scikit-learn - skills/evaluating-llms/examples/typescript/unit-evaluation.ts, line 430
console.log(" npx vitest run unit-evaluation.ts\n"); - skills/evaluating-llms/outputs.yaml, line 227
install: "pip install ragas" - skills/evaluating-llms/outputs.yaml, line 231
install: "pip install deepeval" - skills/evaluating-llms/outputs.yaml, line 235
install: "pip install lm-eval" - skills/evaluating-llms/outputs.yaml, line 239
install: "pip install langsmith" - skills/evaluating-llms/outputs.yaml, line 243
install: "pip install scikit-learn" - skills/evaluating-llms/references/benchmarks.md, line 78
pip install lm-eval
and 4 more places
Runs commands on your computer
The author does not mention this.
Found in 3 places.
Safer alternatives
Low-risk skills in the same category (design) 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/'evaluating-llms' ] || [ -L ~/.agents/skills/'evaluating-llms' ]; then echo 'A skill folder named evaluating-llms already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/ancoleman/ai-design-components' "$d" && git -C "$d" checkout --quiet '76551b7b19ebc667764ec75da14990d0aef8b6e5' -- 'skills/evaluating-llms' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/evaluating-llms' ~/.agents/skills/'evaluating-llms' && 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/'evaluating-llms' ~/.claude/skills/'evaluating-llms' (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 ancoleman/ai-design-components shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/ancoleman/ai-design-components/)
Score history
| Date | Version | Score |
|---|
| 2026-11-08 | 76551b7 | 100 |
| 2026-11-07 | 76551b7 | 45 |