Agent Skills Eval
by darkrishabhA test runner for agentskills.io-style AI agent skills
Agent Skills Eval is an open-source agent skill by darkrishabh, written mainly in TypeScript, with 809 GitHub stars and the MIT license. Its code was last updated Oct 21, 2026. The latest npm release is agent-skills-eval 0.1.1, published May 7, 2026, with 6,383 downloads last week.
Scan summary: scanned Nov 5, 2026 at commit f10ae2b. No capabilities flagged by our checks. Scan policy
What Agent Skills Eval can touch
- Our checks did not find this. The tool may still do it.Run shell commandsNot seen in this scan
- Our checks did not find this. The tool may still do it.Run dynamic codeNot seen in this scan
- Our checks did not find this. The tool may still do it.Read or write filesNot seen in this scan
- Our checks did not find this. The tool may still do it.Read environment and secretsNot seen in this scan
- Our checks did not find this. The tool may still do it.Control a web browserNot seen in this scan
- Our checks did not find this. The tool may still do it.Connect to databasesNot seen in this scan
- Our checks did not find this. The tool may still do it.Read or send messagesNot seen in this scan
- Our checks did not find this. The tool may still do it.Touch money or tradingNot seen in this scan
- Our checks did not find this. The tool may still do it.Connect to the internetNot run in this scan
"Not seen" means our checks did not find it, and the tool may still do it. Covers commit f10ae2b, Nov 5, 2026. See the scan policy.
Before you install Agent Skills Eval
AgenticMart scanned Agent Skills Eval on Nov 5, 2026 with automated checks for hidden code, known-malicious packages, leaked secrets and vulnerable dependencies. The result covers one commit under our scan policy, so review what access you give it and check any advisories shown here.
What it can access
- A skill is instructions plus optional scripts. The instructions steer your agent; any scripts run on your machine when the agent uses the skill.
Before you install
- Pin the version you reviewed instead of always installing the latest release.
- Read the tool list or scripts before the first run, and keep approval prompts on for actions that write, send or delete.
- Maintained by darkrishabh on GitHub, 809 stars and 45 forks. Popularity is not proof of safety.
- Last code change: Oct 21, 2026.
- Open-source license: MIT.
Agent Skills Eval is an open-source agent skill by darkrishabh, written mainly in TypeScript. A test runner for agentskills.io-style AI agent skills
At a glance
- Stars
- 809
- Forks
- 45
- Language
- TypeScript
- License
- MIT
- Created
- May 2026
- Last update
- Oct 21, 2026
- Type
- Agent Skill
- Price
- Free
Topics
Questions about Agent Skills Eval
What is Agent Skills Eval?
A test runner for agentskills.io-style AI agent skills
Who maintains Agent Skills Eval?
Agent Skills Eval is maintained by darkrishabh on GitHub (darkrishabh/agent-skills-eval). AgenticMart lists it from public repository data.
Is Agent Skills Eval safe to use?
AgenticMart scanned Agent Skills Eval on Nov 5, 2026 with automated checks for hidden code, known-malicious packages, leaked secrets and vulnerable dependencies. The result covers one commit under our scan policy, so review what access you give it and check any advisories shown here.
What license does Agent Skills Eval use?
It is published under the MIT license.
Agent Skills Eval alternatives
View more →Similar agent skills in Security & Testing, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.
| Name | Stars | Licence | Last updated | Scan |
|---|---|---|---|---|
| Agent Skills Eval (this page) darkrishabh | 809 | MIT | Oct 21, 2026 | Scanned, no flagged issues |
| SkillSpector NVIDIA | 24k | Apache-2.0 | Oct 31, 2026 | Scanned, no flagged issues |
| Claude Red SnailSploit | 10k | MIT | Oct 12, 2026 | Scanned, no flagged issues |
| Skills trailofbits | 7.9k | CC-BY-SA-4.0 | Oct 28, 2026 | Scanned, no flagged issues |
| Replica Skill Jakeschincariol | 6.9k | MIT | Oct 3, 2026 | Scanned, no flagged issues |
| Claude BugHunter elementalsouls | 5.4k | MIT | Nov 1, 2026 | Scanned, no flagged issues |