1. wildclawbench
531 stars
An in-the-wild benchmark for AI agents in the production harness.
Flowy lists 77 other Testing plugins like kicad-happy, ranked by shared technologies, then GitHub stars; nothing in this list is paid.
Published · Updated · By Flowy
| Plugin | Stars | 7 days | Updated | License | Contains |
|---|---|---|---|---|---|
| kicad-happyThis page | 1,504 | +56 | Oct 25, 2026 | MIT | 11 skills |
| 1wildclawbench | 531 | not available | Sep 18, 2026 | MIT | 27 skills |
| 2lhtb | 566 | +4 | Oct 12, 2026 | Apache-2.0 | 5 skills |
| 3superpowers-lab | 434 | 0 | Jun 1, 2026 | MIT | 4 skills |
| 4coder-eval | 155 | +1 | Oct 28, 2026 | Apache-2.0 | 6 skills, 6 commands |
| 5web-perf-audit | 3 | 0 | Jul 18, 2026 | MIT | 1 skill |
| 6vibium | 2,937 | -3 | Oct 27, 2026 | Apache-2.0 | 2 skills |
| 7skill-up | 1,381 | +128 | Oct 27, 2026 | Apache-2.0 | 3 skills, 1 MCP server |
| 8paperjury | 1,214 | +4 | Aug 14, 2026 | MIT | 1 skill |
| 9skillgrade | 730 | +5 | Oct 11, 2026 | MIT | 2 skills |
| 10agentic-qe | 515 | +7 | Oct 25, 2026 | MIT | 119 skills, 169 agents, 149 commands, 1 MCP server |
| 11awizemann-harness | 359 | +3 | Sep 2, 2026 | MIT | 2 MCP servers |
| 12swingerman-atdd | 162 | +3 | Oct 27, 2026 | MIT | 28 skills, 8 agents, 4 commands, 2 hooks |
531 stars
An in-the-wild benchmark for AI agents in the production harness.
566 stars+4 this week
Long-Horizon Terminal-Bench is a benchmark for measuring how well LLM agents sustain useful work in a containerized terminal over hundreds…
434 stars0 this week
Experimental skills for Claude Code Superpowers - new techniques and tools under active development.
155 stars+1 this week
Playwright for coding agents — one declarative test file, any agent runtime, a real sandbox, and a pass/fail gate in CI.
3 stars0 this week
A Claude Skill that automates web performance audits (LCP, CLS, INP) using web.dev guidelines, delivers structured reports, actionable fix…
2,937 stars-3 this week
The verification layer for coding agents.
1,381 stars+128 this week
An evaluation and evolution tool for Agent Skills.
1,214 stars+4 this week
Pre-submission AI review stress-test for research papers.
730 stars+5 this week
An eval harness for AI coding agents.
515 stars+7 this week
Quality engineering tools for your coding agent.
359 stars+3 this week
macOS 14+ · Apple Silicon & Intel · ~12 MB awizemann.github.io/harness · Wiki · All releases A native macOS…
162 stars+3 this week
A methodology kit for engineering-led AI development — spec-driven, test-driven, charter-bound.
wildclawbench is the first of 12 alternatives to kicad-happy by shared technologies: it has 531 stars (behind kicad-happy) and ships 27 skills against 11 for kicad-happy.
agentic-qe has the most, with 119 skills of the 12 alternatives listed. kicad-happy has 11.
Yes. kicad-happy is published under the MIT license, so it is free to use.