#benchmark

ADR: Enterprise AI Agent Security

ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.

Eval Design

Turn "does this AI feature work?" into a scorecard someone can argue with. Rubrics, failure taxonomies, gates and confidence intervals — ren...

Qa Skills

让 AI 像资深测试工程师一样工作：全生命周期 QA Agent Skills 框架——方法论 + 10 Skills + 可复现 Benchmark（Claude Code 等 Agent 可用）

Embodied Eval Automation

A permission-aware Agent Skill for reproducible, auditable batch episode collection across VLA, policy, world-model, and embodied benchmark...

Agent Ste

Agent Skill for ASD-STE100 Simplified Technical English. Makes LLMs write text that survives one read. Benchmarked on 12 models: 95.5% fewer...

Skill Receipts

Claude Code skills where every entry ships receipts — accuracy-gated benchmarks against baseline and placebo, rejects published

Xorcise Skills

Agent skills for XORCISE — benchmark AI models on hands-on cyber missions and get an eval-card report.

Many Ppt Skills

Every AI slide-deck skill worth knowing, on one page — both the HTML and native-PPTX routes, compared on what actually decides the choice ra...

Slopkit: Anti-Slop Writing Skills for Agents

Anti-slop writing skill that preserves facts, voice, and density, with public benchmarks.

Task Compass Skill

Task Compass Skill: deterministic, auditable task routing for AI agents and OpenClaw

AI Shakespii

Workbench for Agent Skills — lint, test, benchmark, and gate-install SKILL.md skills for Claude Code, Codex, Cursor, Gemini, and more