datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
agentskillos-benchmark
AgentSkillOS Benchmark
Official benchmark release for Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale.
GitHub project: https://github.com/ynulihao/AgentSkillOS
This release is a file-based benchmark package. It contains the original task definitions and the bundled task assets that are needed by tasks with local input files.
Contents
data/tasks.jsonl: normalized task index for load_dataset(...)
tasks/: the original 30 benchmark task… See the full description on the dataset page: https://huggingface.co/datasets/NPULH/agentskillos-benchmark.agent-skills
Index — Lucio's Agent Skills & Projects
Each project now lives in its own repo, so you get its full README, its own licence, and its own version history. This page is just the map.
This repo also keeps a full snapshot of every skill for anyone who wants them all in one download — see the Files and versions tab. The individual repos below are the canonical ones.
Agent Skills
Skill
What it does
Licence
relic
Portable AI personality & memory, in pure… See the full description on the dataset page: https://huggingface.co/datasets/LucioLiu/agent-skills.claude-agent-skills-benchmark
Claude Agent Skills Benchmark
Claude Agent Skills 评测数据集
Description
A benchmark dataset for evaluating whether LLMs can accurately trigger and execute domain-specific Skills on the Claude Code platform. Skills are designed by vertical domain experts with varying complexity levels (based on attachments: scripts, references, assets, and reference markdown files).
Evaluation Scenarios Cover:
Office automation, coding, investment promotion, financial services, industrial… See the full description on the dataset page: https://huggingface.co/datasets/obaydata/claude-agent-skills-benchmark.agent-skill-vulnerabilities
Agent Skill Vulnerability Scenarios (defanged, teaching)
from datasets import load_dataset
ds = load_dataset("fevziegeyurtsevenler/agent-skill-vulnerabilities")
Deliberately-vulnerable, defanged agent-extension artifacts — for training detectors & hands-on learning.
Schema
column
meaning
id
scenario
artifact_type
SKILL.md / mcp.json
content, walkthrough
artifact + defense
Related AltaySec resources
🕵️ uncloak scanner:… See the full description on the dataset page: https://huggingface.co/datasets/fevziegeyurtsevenler/agent-skill-vulnerabilities.agent-skills-security-grades
Agent Skills Security Grades
Security grades and quality scores for 130,173 open-source AI agent skills and
MCP servers collected from GitHub, from Agent Skills Hub.
Each row is one skill/server with a rule-based security grade
(SAFE / CAUTION / UNSAFE / REJECT / UNAUDITED), red-flag identifiers, and a
0–100 quality score.
Why this exists
AI coding agents install third-party skills that run with the agent's full
permissions and credentials, but marketplaces rank… See the full description on the dataset page: https://huggingface.co/datasets/jasonzhuyansen/agent-skills-security-grades.agent-skills
Agent Skills Dataset
61,650 agent skills collected from GitHub repositories. Each skill contains name, description, and full markdown content. Useful for skill retrieval and agent training.
Dataset Structure
id: Unique identifier for the skill
name: Skill name
description: Skill description and usage instructions
owner: Repository owner
repo: Repository name
skill_md_path: Path to the skill markdown file
content: Full skill content in markdown format
Usage… See the full description on the dataset page: https://huggingface.co/datasets/LittleDinoC/agent-skills.atr-skill-benchmark
ATR Skill-Security Benchmark
A labeled corpus of SKILL.md files for evaluating detection of malicious agent
skills — prompt injection, tool poisoning, credential theft, malware droppers
and supply-chain attacks hidden inside natural-language agent instructions.
Published as part of Agent Threat Rules (ATR),
an open, vendor-neutral detection standard for AI agents (like Sigma, but for
agent attacks).
Why this exists
SKILL.md files are natural-language instructions… See the full description on the dataset page: https://huggingface.co/datasets/Agent-Threat-Rule/atr-skill-benchmark.agent-skill-malware
Agent Skill Malware: Malicious vs Benign Agent Skills
Binary classification dataset of OpenClaw agent skill files (SKILL.md).
127 malicious + 223 benign = 350 samples, deduplicated by content hash.
Source
Malicious: Real skills from malicious campaigns targeting ClawHub (Feb 2026), extracted from the openclaw/skills GitHub archive. They use social engineering in markdown instructions to trick agents/users into running malware -- primarily AMOS (Atomic macOS Stealer)… See the full description on the dataset page: https://huggingface.co/datasets/yoonholee/agent-skill-malware.SkillLeakBench
SkillLeakBench
A credential-leakage benchmark for LLM agent skills, from the ASE 2026 paper How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study.
📄 Paper: https://arxiv.org/abs/2604.03070
💻 Code & detection pipeline: https://github.com/AgentSkillsPrivacy/SkillLeakBench
📦 Archive: https://doi.org/10.5281/zenodo.19367969
Dataset summary
We collected 170,226 skills from SkillsMP and analyzed a 17,022-skill sample with static secret extraction… See the full description on the dataset page: https://huggingface.co/datasets/AgentSkillPrivacy/SkillLeakBench.FORTIS_Agent_Skill_Safety
FORTIS: Benchmarking Agent Skill Safety
FORTIS is a benchmark for evaluating AI agent safety in skill and tool selection. It measures whether LLM agents select minimally-privileged capabilities when multiple valid options exist.
Overview
Modern LLM agents operate through a skill layer that mediates between user intent and task execution. FORTIS evaluates two critical safety questions:
Task 1: Skill Selection - Does the agent select the minimally sufficient skill… See the full description on the dataset page: https://huggingface.co/datasets/ShawnLi02/FORTIS_Agent_Skill_Safety.AgentSkiller-11Ktesttau-agent-skill
TestTau Agent Skill
TestTau gives AI agents disposable email inboxes and webhook capture endpoints for QA, CI, signup, checkout, and integration tests.
Agents can:
create public disposable inboxes at <inbox>@mail.testtau.com;
wait for email and fetch parsed JSON;
use private API-key protected inboxes for signed-in users;
capture HTTP requests at https://hook.testtau.com/<hookId>;
inspect, replay, and assert webhook captures with JSON Schema.
Best-fit workflows:
signup, magic-link… See the full description on the dataset page: https://huggingface.co/datasets/testtau/testtau-agent-skill.han-cross-agent-skill-transfer-benchmark-dataset-v1
Humanoid Cross-Agent Skill Transfer Benchmark Dataset
This dataset benchmarks how effectively
skills learned by one humanoid agent
can be transferred to another agent
within a decentralized cognitive network.
Objective
To measure cross-agent generalization,
adaptation speed, and transfer efficiency.
Data Fields
source_agent_skill_profile
target_agent_initial_profile
transferred_skill_vector
adaptation_steps
performance_improvement_percentage… See the full description on the dataset page: https://huggingface.co/datasets/achiepatricia/han-cross-agent-skill-transfer-benchmark-dataset-v1.Agent-Skills-Retrieveragent-skill-malware
Agent Skill Malware: Malicious vs Benign Agent Skills
Binary classification dataset of OpenClaw agent skill files (SKILL.md).
127 malicious + 223 benign = 350 samples, deduplicated by content hash.
Source
Malicious: Real skills from malicious campaigns targeting ClawHub (Feb 2026), extracted from the openclaw/skills GitHub archive. They use social engineering in markdown instructions to trick agents/users into running malware -- primarily AMOS (Atomic macOS Stealer)… See the full description on the dataset page: https://huggingface.co/datasets/TongxiQu/agent-skill-malware.agent-skillsaif-agent-skills
AIF Agent Skills
Reusable, versioned agent skill definitions with dependency resolution and provenance tracking.
Skill Format
{
"skill_id": "string",
"name": "string",
"version": "semver",
"description": "string",
"category": "coding|planning|review|deployment|analysis",
"dependencies": ["skill_id"],
"input_schema": {},
"output_schema": {},
"provenance": {"author": "string", "created": "iso8601"}
}
Categories
Coding: Code… See the full description on the dataset page: https://huggingface.co/datasets/FrostyJay7813/aif-agent-skills.agent_skills_mdpi_2026AgentSkiller-11K