Add Gemini Agent Skill for Benchmarks CLI (#994)

## Add Agent Skill for Benchmarks CLI

Adds agent skill documentation for the Kaggle Benchmarks CLI workflow,
following the [Playwright CLI
pattern](https://github.com/microsoft/playwright-cli/blob/main/skills/playwright-cli/SKILL.md).

### Structure

```
skills/
├── SKILL.md                  ← Top-level skill for the entire kaggle CLI
└── references/
    └── benchmarks.md         ← Detailed benchmarks workflow reference
```

- **`SKILL.md`** is a lightweight entry point (~45 lines) covering all
CLI command groups, with links to detailed references.
- **`references/benchmarks.md`** is the detailed reference (~420 lines)
for the benchmarks workflow: setup, push, run, status, download, error
handling, and common workflows.

This structure allows future reference files (datasets.md,
competitions.md, etc.) to be added without bloating the entry point.

### Using with AI Coding Agents

The `skills/` directory is agent-agnostic. To integrate with a specific
tool:

| Tool | Integration |
|------|-------------|
| **Gemini CLI** | Symlink: `.gemini/skills/kaggle-cli/ → ../../skills/`
|
| **Claude Code** | Reference in `CLAUDE.md`: `See
skills/references/benchmarks.md` |
| **Cursor** | Add to `.cursor/rules/` |
| **Other agents** | Point at `skills/SKILL.md` or
`skills/references/benchmarks.md` directly |

### Tested

- auto test https://paste.googleplex.com/4609226241605632
- trajectory with gemini: https://paste.googleplex.com/4861956914806784

### Changes

- `skills/SKILL.md` — **[NEW]** Top-level CLI skill
- `skills/references/benchmarks.md` — **[NEW]** Benchmarks reference

Author: dolaameng

skills/SKILL.md

@@ -0,0 +1,44 @@
+---
+name: kaggle-cli
+description: >
+  How to use the kaggle CLI — managing datasets, competitions, notebooks,
+  models, and benchmarks. Activate this skill when the user asks about
+  kaggle CLI commands, workflows, or troubleshooting.
+---
+
+# Kaggle CLI
+
+The `kaggle` command-line tool provides access to Kaggle's platform features.
+
+## Installation
+
+```bash
+pip install kaggle
+```
+
+## Authentication
+
+```bash
+# Browser-based OAuth login
+kaggle auth login
+
+# Or set KAGGLE_API_TOKEN environment variable
+# Or place token in ~/.kaggle/access_token
+```
+
+## Command Groups
+
+```
+kaggle
+├── competitions (alias: c)  — Join and submit to competitions
+├── datasets (alias: d)      — Create, download, and manage datasets
+├── kernels (alias: k)       — Run and manage notebooks/scripts
+├── models (alias: m)        — Upload and version models
+└── benchmarks (alias: b)    — Benchmark LLM models on tasks
+```
+
+## Specific Tasks
+
+For detailed reference on specific command groups, see:
+
+- [Benchmarks](references/benchmarks.md) — Push tasks, run against LLM models, check status, download results