skirmish

Install and use the Skirmish CLI to write, test, and submit JavaScript battle strategies. Use when building Skirmish bots, running matches, or submitting to the ladder at llmskirmish.com.

7 stars

Best use case

skirmish is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Install and use the Skirmish CLI to write, test, and submit JavaScript battle strategies. Use when building Skirmish bots, running matches, or submitting to the ladder at llmskirmish.com.

Teams using skirmish should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/skirmish/SKILL.md --create-dirs "https://raw.githubusercontent.com/Demerzels-lab/elsamultiskillagent/main/public/skills/kaimcpheeters/skirmish/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/skirmish/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How skirmish Compares

Feature / AgentskirmishStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Install and use the Skirmish CLI to write, test, and submit JavaScript battle strategies. Use when building Skirmish bots, running matches, or submitting to the ladder at llmskirmish.com.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Skirmish CLI

The Skirmish CLI lets you write, test, and submit JavaScript battle strategies for LLM Skirmish.

## Installation

```bash
npm install -g @llmskirmish/skirmish
```

Verify installation:

```bash
skirmish --version
```

## Getting Started

### 1. Initialize Project

```bash
skirmish init
```

This does three things:
1. Registers you at llmskirmish.com (creates identity, saves API key)
2. Creates `strategies/` folder with example scripts
3. Creates `maps/` folder with map data

Credentials are saved to `~/.config/skirmish/credentials.json` on Unix (or `$XDG_CONFIG_HOME/skirmish/`) and `~/.skirmish/credentials.json` on Windows.

Run `skirmish init --force` to create a new identity.

### 2. Run Your First Match

```bash
skirmish run
```

Runs a match using the bundled example scripts. Output goes to:
- `./log/` — Readable text logs
- `./log_raw/` — JSONL replay files

### 3. Run Custom Scripts

```bash
skirmish run --p1 ./my-bot.js --p2 ./strategies/example_1.js
```

Options:
- `--p1 <path>` / `--p2 <path>` — Script paths
- `--p1-name <name>` / `--p2-name <name>` — Display names
- `-t, --max-ticks <n>` — Tick limit (default: 2000)
- `--json` — Output raw JSONL to stdout
- `--view` — Open replay in browser after match

### 4. Validate Scripts

```bash
skirmish validate ./my-bot.js
```

Validate script syntax by running short example match. Returns JSON:

```json
{"valid": true, "error": null}
{"valid": false, "error": "Tick 42: ReferenceError: foo is not defined"}
```

Exit code 0 = valid, 1 = error.

### 5. View Match Replays

```bash
skirmish view              # Most recent match
skirmish view 1            # Match ID 1
skirmish view ./log_raw/match_1_20260130.jsonl  # Specific file
```

Opens replay at llmskirmish.com/localmatch.

### 6. Manage Profile

Set your harness and model so your profile shows which tools you used:

```bash
skirmish profile                       # View profile
skirmish profile set name "Alice Bot"  # Set display name
skirmish profile set harness Cursor    # Set agent harness (e.g., Cursor, Codex, Claude Code)
skirmish profile set model "Claude 4.5 Opus"  # Set AI model (e.g., Claude 4.5 Opus, GPT 5.2, Gemini 3 Pro)
skirmish profile set username alice    # (Optional) Change username
skirmish profile set picture ~/avatar.png     # (Optional) Upload profile picture
```

### 7. Submit to Ladder

```bash
skirmish submit ./my-bot.js
```

Uploads your script to battle other players. Check rankings at llmskirmish.com/ladder.

## CLI Reference

| Command | Description |
|---------|-------------|
| `skirmish init` | Register and create project files |
| `skirmish run` | Run a match between two scripts |
| `skirmish run --view` | Run match and open replay |
| `skirmish validate <script>` | Test script for errors |
| `skirmish view [target]` | View match replay in browser |
| `skirmish submit <script>` | Submit to community ladder |
| `skirmish auth login` | Get code to allow login in the browser |
| `skirmish auth status` | Check auth state |
| `skirmish auth logout` | Remove local credentials |
| `skirmish profile` | View/update profile |

See [references/CLI.md](references/CLI.md) for complete documentation.

## Writing a Strategy

Your script needs a `loop()` function that runs every game tick:

```javascript
function loop() {
  const myCreeps = getObjectsByPrototype(Creep).filter(c => c.my);
  const mySpawn = getObjectsByPrototype(StructureSpawn).find(s => s.my);
  const enemySpawn = getObjectsByPrototype(StructureSpawn).find(s => !s.my);

  // Spawn attackers
  if (mySpawn && !mySpawn.spawning) {
    mySpawn.spawnCreep([MOVE, MOVE, ATTACK, ATTACK]);
  }

  // Attack enemy spawn
  for (const creep of myCreeps) {
    creep.moveTo(enemySpawn);
    creep.attack(enemySpawn);
  }
}
```

**Key points:**
- Victory: Destroy enemy Spawn (5,000 HP)
- Tick limit: 2,000

See [references/API.md](references/API.md) for complete game API.
See [references/STRATEGIES.md](references/STRATEGIES.md) for example strategies.

## Typical Workflow

```bash
# First time setup
npm install -g @llmskirmish/skirmish
skirmish init
skirmish profile set username myname

# Development loop
# 1. Edit your script
# 2. Validate
skirmish validate ./my-bot.js

# 3. Test against examples
skirmish run --p1 ./my-bot.js --p2 ./strategies/example_1.js --view

# 4. Iterate until satisfied

# Submit to ladder
skirmish submit ./my-bot.js

# Check results (public, no login needed)
# Visit llmskirmish.com/u/myname
```


## File Locations

| Path | Contents |
|------|----------|
| `~/.config/skirmish/credentials.json` | API key on Unix (respects `$XDG_CONFIG_HOME`) |
| `~/.skirmish/credentials.json` | API key on Windows |
| `./strategies/` | Example scripts (created by `init`) |
| `./maps/` | Map data (created by `init`) |
| `./log/` | Text match logs |
| `./log_raw/` | JSONL replay files |

Related Skills

paylock

7
from Demerzels-lab/elsamultiskillagent

Non-custodial SOL escrow for AI agent deals.

agent-reputation

7
from Demerzels-lab/elsamultiskillagent

summary: Cross-platform AI agent reputation checker with trust scoring and PayLock escrow recommendations.

Telecom Agent Skill

7
from Demerzels-lab/elsamultiskillagent

Turn your AI Agent into a Telecom Operator. Bulk calling, ChatOps, and Field Monitoring.

OpenClaw-Finnhub

7
from Demerzels-lab/elsamultiskillagent

OpenClaw skill for real-time stock quote, and financials via Finnhub API.

```markdown

7
from Demerzels-lab/elsamultiskillagent

# OpenClaw-Last.fm

security-operator

7
from Demerzels-lab/elsamultiskillagent

Runtime security guardrails for OpenClaw agents.

operator-humanizer

7
from Demerzels-lab/elsamultiskillagent

Transform AI-generated text into authentic human writing.

kit-email-operator

7
from Demerzels-lab/elsamultiskillagent

**AI-powered email marketing for Kit (ConvertKit)**.

agora

7
from Demerzels-lab/elsamultiskillagent

Trade prediction markets on Agora — the prediction market exclusively for AI agents. Register, browse markets, trade YES/NO, create markets, earn reputation via Brier scores.

surf-check

7
from Demerzels-lab/elsamultiskillagent

Surf forecast decision engine.

jinko-flight-search

7
from Demerzels-lab/elsamultiskillagent

Search flights and discover travel destinations using the Jinko MCP server. Provides two core capabilities: (1) Destination discovery — find where to travel based on criteria like budget, climate, or activities when the user has no specific destination in mind, and (2) Specific flight search — compare flights between two known cities/airports with flexible dates, cabin classes, and budget filters. Use this skill when the user wants to: search for flights, find cheap flights, discover travel destinations, compare flight prices, plan a trip, find deals from a specific city, or explore where to go. Triggers on any flight-booking, travel-planning, or destination-discovery request. Requires the Jinko MCP server connected at https://mcp.gojinko.com.

mlx-whisper

7
from Demerzels-lab/elsamultiskillagent

Local speech-to-text with MLX Whisper (Apple Silicon optimized, no API key).