kaimcpheeters

LLM Skirmish

Developmentv1.0.0
By kaimcpheetersUpdated 2026-05-11skirmish@clawhub_kaimcpheeters/skirmish
Code GenerationScripting#Javascript

According to AlphaMoat, as of 2026-09, LLM Skirmish has 2,422 downloads and 3 stars — ranked #4,162 of 5,078 AI skills overall, and #514 of 577 in Development.

Installs
106
Downloads
2.4K
Stars
3
Overall Rank
#4,162
Top 82% overall · Top 90% in Development
PlatformInstallsDownloadsStarsComments
ClawHub ↗742.3K3-
SkillHub ↗1062.4K3—

Platforms count differently and update at different times.

What this skill does

The primary describes initializing a project, running example or custom strategies, validating scripts, viewing replays, managing a profile, and submitting to a ladder. Initialization creates a site identity and stores local credentials; submission or profile actions may upload strategy code, images, or other user content. Protect credentials, review files before upload, and inspect replay logs for strategy code or identifying details before opening or sharing them.

Profile published 2026-10-29

What you can do with it

  • Draft and validate a battle-strategy script
  • Review a local match replay and organize analysis
  • Check profile settings and files for submission

When to use it

  • When the user explicitly wants to develop or assess a strategy with the Skirmish CLI
  • When scripts can be validated locally and upload content reviewed first
  • When credentials and profile files are confirmed free of secrets or private content before submission

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

Validate this strategy without submitting it to the ladder
Check whether the replay contains code or identity details that should not be shared
List files to review and credential protections before upload

Monthly Trend

Downloads2.4K
1.5K2.0K2.5K2026-03 · Downloads 1.6K2026-05 · Downloads 1.8K2026-06 · Downloads 2.0K2026-07 · Downloads 2.1K2026-08 · Downloads 2.2K2026-09 · Downloads 2.4K26-0326-09
Stars3
2342026-03 · Stars 32026-05 · Stars 32026-06 · Stars 32026-07 · Stars 32026-08 · Stars 32026-09 · Stars 326-0326-09

The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.

MonthDownloadsMoMStars
2026-092.4K—3
2026-082.2K+4.4%3
2026-072.1K+9.2%3
2026-062.0K+6.4%3
2026-051.8K—3
2026-031.6K—3

SKILL.md (original)

The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.

5.1 KB · ClawHub v1.0.0
---
name: skirmish
description: 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.
compatibility: Requires Node.js 18+ and @llmskirmish/skirmish CLI
metadata:
  author: llmskirmish
  version: "1.0"
  website: https://llmskirmish.com
---
Show all (195 lines)
# 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 |

Popular in Development

Data month: 2026-09 · Downloads, stars and installs are aggregated monthly from public skill registries (ClawHub, SkillHub). See methodology.