Agent-facing conventions for this repo live in [**CLAUDE.md**](./CLAUDE.md) — read it first regardless of which agent or tool you are. This file is a pointer kept here so tools that follow the [agents
Free account. Installing gives you the manifest plus copy-paste snippets.
See reviewsImported from awslabs/llm-evaluation-system (
AGENTS.md). Install upstream withnpx skills add awslabs/llm-evaluation-system. Copyright stays with the author.
Agent-facing conventions for this repo live in CLAUDE.md — read it first regardless of which agent or tool you are. This file is a pointer kept here so tools that follow the agents.md convention (Codex, Cursor, others) land in the same place Claude Code does.
For the full system architecture and diagrams, see ARCHITECTURE.md.
Copy one of these into your project. Installing also returns the manifest and these snippets.
targets:
- https://api.opensmartroute.ai/api/v1/registry/awslabs-llm-evaluation-system-llm-evaluation-system/manifest # or paste the manifest belowAn Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
{
"ocm": "1",
"id": "awslabs-llm-evaluation-system-llm-evaluation-system",
"kind": "skill",
"name": "llm-evaluation-system",
"description": "Agent-facing conventions for this repo live in [**CLAUDE.md**](./CLAUDE.md) — read it first regardless of which agent or tool you are. This file is a pointer kept here so tools that follow the [agents.md](https://agents.md) convention (Codex, Cursor, others) land in the same place Claude Code does.",
"publisher": "awslabs",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"skill-md",
"github-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Agent-facing conventions for this repo live in [**CLAUDE.md**](./CLAUDE.md) — read it first regardless of which agent or tool you are. This file is a pointer kept here so tools that follow the [agents.md](https://agents.md) convention (Codex, Cursor, others) land in the same place Claude Code does."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-agents",
"repository": "https://github.com/awslabs/llm-evaluation-system",
"path": "AGENTS.md",
"ref": "4165ea11afcce47e48b7eee772362b872f8c6c8f",
"url": "https://github.com/awslabs/llm-evaluation-system/blob/4165ea11afcce47e48b7eee772362b872f8c6c8f/AGENTS.md",
"key": "awslabs/llm-evaluation-system/AGENTS.md"
}
},
"instructions": "# AGENTS.md\n\nAgent-facing conventions for this repo live in [**CLAUDE.md**](./CLAUDE.md) — read it first regardless of which agent or tool you are. This file is a pointer kept here so tools that follow the [agents.md](https://agents.md) convention (Codex, Cursor, others) land in the same place Claude Code does.\n\nFor the full system architecture and diagrams, see [ARCHITECTURE.md](./ARCHITECTURE.md).",
"cost": {
"context_tokens": 100
}
}Fetch it by URL: GET /api/v1/registry/awslabs-llm-evaluation-system-llm-evaluation-system/manifest?version=1.0.0
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.