← All skills
eval-skills
37 / 100 · High risk
Only if you trust the author. Some of what it can do is expected: a coding skill usually runs build and test commands.
By LeoYeAI/agent-master-skills (GitHub) · coding · 2,186 stars · scanned at commit 8f88f9a
AI Agent Skill unit testing framework. A framework-agnostic toolkit for discovering, scaffolding, selecting, evaluating, and reporting on AI skills. Use this skill to assess skill quality before production, compare candidate skills on the same benchmark, enforce quality gates in CI/CD, and generate human-readable evaluation reports.
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
The author does not mention this. Expected for a coding skill.
Found in 23 places.
Show 17 more
- skills/eval-skills/SKILL.md, line 136
eval-skills select \ - skills/eval-skills/SKILL.md, line 175
eval-skills run \ - skills/eval-skills/SKILL.md, line 196
eval-skills report convert \ - skills/eval-skills/SKILL.md, line 207
eval-skills report diff \ - skills/eval-skills/SKILL.md, line 218
eval-skills init --dir . - skills/eval-skills/SKILL.md, line 231
eval-skills config list - skills/eval-skills/SKILL.md, line 320
eval-skills eval --skills ./my-skill/ --benchmark ./my-benchmark.json - skills/eval-skills/SKILL.md, line 339
eval-skills create --name my_calc --from-template python_script - skills/eval-skills/SKILL.md, line 358
eval-skills find --query "weather" --skills-dir ./skills - skills/eval-skills/SKILL.md, line 382
eval-skills run \ - skills/eval-skills/SKILL.md, line 395
eval-skills eval \ - skills/eval-skills/SKILL.md, line 407
eval-skills report diff \ - skills/eval-skills/packages/cli/src/commands/__tests__/eval.test.ts, line 2
import { execSync } from "child_process"; - skills/eval-skills/packages/cli/src/commands/__tests__/eval.test.ts, line 44
const result = execSync( - skills/eval-skills/packages/cli/src/commands/__tests__/eval.test.ts, line 61
execSync(`${CLI} eval`, { stdio: "ignore" }); - skills/eval-skills/packages/cli/src/commands/__tests__/eval.test.ts, line 67
execSync( - skills/eval-skills/packages/core/src/adapters/SubprocessAdapter.test.ts, line 4
import { spawn } from "node:child_process";
and 3 more places
Sends data to these websites: api.openai.com, evil.com
This is disclosed by the author in the skill's SKILL.md or README.
Found in 7 places.
Show 4 more
Can call paid AI services billed to you
The author does not mention this.
Found in 4 places.
Show 1 more
Downloads and installs other software
The author does not mention this.
Found in 1 place.
Reads your saved credentials, such as SSH keys or .env files
The author does not mention this.
Found in 1 place.
Changes files outside its own folder
The author does not mention this.
Found in 1 place.
Safer alternatives
Low-risk skills in the same category (coding) that look related. Check that one does what you need.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'eval-skills' ] || [ -L ~/.agents/skills/'eval-skills' ]; then echo 'A skill folder named eval-skills already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/LeoYeAI/agent-master-skills' "$d" && git -C "$d" checkout --quiet '8f88f9a0dd5a1075d4f0c7626f9d960844d57575' -- 'skills/eval-skills' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/eval-skills' ~/.agents/skills/'eval-skills' && rm -rf "$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/'eval-skills' ~/.claude/skills/'eval-skills' (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 LeoYeAI/agent-master-skills shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/LeoYeAI/agent-master-skills/)
Score history
| Date | Version | Score |
|---|
| 2026-11-08 | 8f88f9a | 37 |
| 2026-11-07 | 8f88f9a | 62 |