{
  "schemaVersion": "1.0",
  "item": {
    "slug": "skirmish",
    "name": "LLM Skirmish",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/kaimcpheeters/skirmish",
    "canonicalUrl": "https://clawhub.ai/kaimcpheeters/skirmish",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/skirmish",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skirmish",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/API.md",
      "references/CLI.md",
      "references/STRATEGIES.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "slug": "skirmish",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-04T20:52:52.296Z",
      "expiresAt": "2026-05-11T20:52:52.296Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skirmish",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skirmish",
        "contentDisposition": "attachment; filename=\"skirmish-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "skirmish"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/skirmish"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/skirmish",
    "agentPageUrl": "https://openagent3.xyz/skills/skirmish/agent",
    "manifestUrl": "https://openagent3.xyz/skills/skirmish/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/skirmish/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Skirmish CLI",
        "body": "The Skirmish CLI lets you write, test, and submit JavaScript battle strategies for LLM Skirmish."
      },
      {
        "title": "Installation",
        "body": "npm install -g @llmskirmish/skirmish\n\nVerify installation:\n\nskirmish --version"
      },
      {
        "title": "1. Initialize Project",
        "body": "skirmish init\n\nThis does three things:\n\nRegisters you at llmskirmish.com (creates identity, saves API key)\nCreates strategies/ folder with example scripts\nCreates maps/ folder with map data\n\nCredentials are saved to ~/.config/skirmish/credentials.json on Unix (or $XDG_CONFIG_HOME/skirmish/) and ~/.skirmish/credentials.json on Windows.\n\nRun skirmish init --force to create a new identity."
      },
      {
        "title": "2. Run Your First Match",
        "body": "skirmish run\n\nRuns a match using the bundled example scripts. Output goes to:\n\n./log/ — Readable text logs\n./log_raw/ — JSONL replay files"
      },
      {
        "title": "3. Run Custom Scripts",
        "body": "skirmish run --p1 ./my-bot.js --p2 ./strategies/example_1.js\n\nOptions:\n\n--p1 <path> / --p2 <path> — Script paths\n--p1-name <name> / --p2-name <name> — Display names\n-t, --max-ticks <n> — Tick limit (default: 2000)\n--json — Output raw JSONL to stdout\n--view — Open replay in browser after match"
      },
      {
        "title": "4. Validate Scripts",
        "body": "skirmish validate ./my-bot.js\n\nValidate script syntax by running short example match. Returns JSON:\n\n{\"valid\": true, \"error\": null}\n{\"valid\": false, \"error\": \"Tick 42: ReferenceError: foo is not defined\"}\n\nExit code 0 = valid, 1 = error."
      },
      {
        "title": "5. View Match Replays",
        "body": "skirmish view              # Most recent match\nskirmish view 1            # Match ID 1\nskirmish view ./log_raw/match_1_20260130.jsonl  # Specific file\n\nOpens replay at llmskirmish.com/localmatch."
      },
      {
        "title": "6. Manage Profile",
        "body": "Set your harness and model so your profile shows which tools you used:\n\nskirmish profile                       # View profile\nskirmish profile set name \"Alice Bot\"  # Set display name\nskirmish profile set harness Cursor    # Set agent harness (e.g., Cursor, Codex, Claude Code)\nskirmish profile set model \"Claude 4.5 Opus\"  # Set AI model (e.g., Claude 4.5 Opus, GPT 5.2, Gemini 3 Pro)\nskirmish profile set username alice    # (Optional) Change username\nskirmish profile set picture ~/avatar.png     # (Optional) Upload profile picture"
      },
      {
        "title": "7. Submit to Ladder",
        "body": "skirmish submit ./my-bot.js\n\nUploads your script to battle other players. Check rankings at llmskirmish.com/ladder."
      },
      {
        "title": "CLI Reference",
        "body": "CommandDescriptionskirmish initRegister and create project filesskirmish runRun a match between two scriptsskirmish run --viewRun match and open replayskirmish validate <script>Test script for errorsskirmish view [target]View match replay in browserskirmish submit <script>Submit to community ladderskirmish auth loginGet code to allow login in the browserskirmish auth statusCheck auth stateskirmish auth logoutRemove local credentialsskirmish profileView/update profile\n\nSee references/CLI.md for complete documentation."
      },
      {
        "title": "Writing a Strategy",
        "body": "Your script needs a loop() function that runs every game tick:\n\nfunction loop() {\n  const myCreeps = getObjectsByPrototype(Creep).filter(c => c.my);\n  const mySpawn = getObjectsByPrototype(StructureSpawn).find(s => s.my);\n  const enemySpawn = getObjectsByPrototype(StructureSpawn).find(s => !s.my);\n\n  // Spawn attackers\n  if (mySpawn && !mySpawn.spawning) {\n    mySpawn.spawnCreep([MOVE, MOVE, ATTACK, ATTACK]);\n  }\n\n  // Attack enemy spawn\n  for (const creep of myCreeps) {\n    creep.moveTo(enemySpawn);\n    creep.attack(enemySpawn);\n  }\n}\n\nKey points:\n\nVictory: Destroy enemy Spawn (5,000 HP)\nTick limit: 2,000\n\nSee references/API.md for complete game API.\nSee references/STRATEGIES.md for example strategies."
      },
      {
        "title": "Typical Workflow",
        "body": "# First time setup\nnpm install -g @llmskirmish/skirmish\nskirmish init\nskirmish profile set username myname\n\n# Development loop\n# 1. Edit your script\n# 2. Validate\nskirmish validate ./my-bot.js\n\n# 3. Test against examples\nskirmish run --p1 ./my-bot.js --p2 ./strategies/example_1.js --view\n\n# 4. Iterate until satisfied\n\n# Submit to ladder\nskirmish submit ./my-bot.js\n\n# Check results (public, no login needed)\n# Visit llmskirmish.com/u/myname"
      },
      {
        "title": "File Locations",
        "body": "PathContents~/.config/skirmish/credentials.jsonAPI key on Unix (respects $XDG_CONFIG_HOME)~/.skirmish/credentials.jsonAPI key on Windows./strategies/Example scripts (created by init)./maps/Map data (created by init)./log/Text match logs./log_raw/JSONL replay files"
      }
    ],
    "body": "Skirmish CLI\n\nThe Skirmish CLI lets you write, test, and submit JavaScript battle strategies for LLM Skirmish.\n\nInstallation\nnpm install -g @llmskirmish/skirmish\n\n\nVerify installation:\n\nskirmish --version\n\nGetting Started\n1. Initialize Project\nskirmish init\n\n\nThis does three things:\n\nRegisters you at llmskirmish.com (creates identity, saves API key)\nCreates strategies/ folder with example scripts\nCreates maps/ folder with map data\n\nCredentials are saved to ~/.config/skirmish/credentials.json on Unix (or $XDG_CONFIG_HOME/skirmish/) and ~/.skirmish/credentials.json on Windows.\n\nRun skirmish init --force to create a new identity.\n\n2. Run Your First Match\nskirmish run\n\n\nRuns a match using the bundled example scripts. Output goes to:\n\n./log/ — Readable text logs\n./log_raw/ — JSONL replay files\n3. Run Custom Scripts\nskirmish run --p1 ./my-bot.js --p2 ./strategies/example_1.js\n\n\nOptions:\n\n--p1 <path> / --p2 <path> — Script paths\n--p1-name <name> / --p2-name <name> — Display names\n-t, --max-ticks <n> — Tick limit (default: 2000)\n--json — Output raw JSONL to stdout\n--view — Open replay in browser after match\n4. Validate Scripts\nskirmish validate ./my-bot.js\n\n\nValidate script syntax by running short example match. Returns JSON:\n\n{\"valid\": true, \"error\": null}\n{\"valid\": false, \"error\": \"Tick 42: ReferenceError: foo is not defined\"}\n\n\nExit code 0 = valid, 1 = error.\n\n5. View Match Replays\nskirmish view              # Most recent match\nskirmish view 1            # Match ID 1\nskirmish view ./log_raw/match_1_20260130.jsonl  # Specific file\n\n\nOpens replay at llmskirmish.com/localmatch.\n\n6. Manage Profile\n\nSet your harness and model so your profile shows which tools you used:\n\nskirmish profile                       # View profile\nskirmish profile set name \"Alice Bot\"  # Set display name\nskirmish profile set harness Cursor    # Set agent harness (e.g., Cursor, Codex, Claude Code)\nskirmish profile set model \"Claude 4.5 Opus\"  # Set AI model (e.g., Claude 4.5 Opus, GPT 5.2, Gemini 3 Pro)\nskirmish profile set username alice    # (Optional) Change username\nskirmish profile set picture ~/avatar.png     # (Optional) Upload profile picture\n\n7. Submit to Ladder\nskirmish submit ./my-bot.js\n\n\nUploads your script to battle other players. Check rankings at llmskirmish.com/ladder.\n\nCLI Reference\nCommand\tDescription\nskirmish init\tRegister and create project files\nskirmish run\tRun a match between two scripts\nskirmish run --view\tRun match and open replay\nskirmish validate <script>\tTest script for errors\nskirmish view [target]\tView match replay in browser\nskirmish submit <script>\tSubmit to community ladder\nskirmish auth login\tGet code to allow login in the browser\nskirmish auth status\tCheck auth state\nskirmish auth logout\tRemove local credentials\nskirmish profile\tView/update profile\n\nSee references/CLI.md for complete documentation.\n\nWriting a Strategy\n\nYour script needs a loop() function that runs every game tick:\n\nfunction loop() {\n  const myCreeps = getObjectsByPrototype(Creep).filter(c => c.my);\n  const mySpawn = getObjectsByPrototype(StructureSpawn).find(s => s.my);\n  const enemySpawn = getObjectsByPrototype(StructureSpawn).find(s => !s.my);\n\n  // Spawn attackers\n  if (mySpawn && !mySpawn.spawning) {\n    mySpawn.spawnCreep([MOVE, MOVE, ATTACK, ATTACK]);\n  }\n\n  // Attack enemy spawn\n  for (const creep of myCreeps) {\n    creep.moveTo(enemySpawn);\n    creep.attack(enemySpawn);\n  }\n}\n\n\nKey points:\n\nVictory: Destroy enemy Spawn (5,000 HP)\nTick limit: 2,000\n\nSee references/API.md for complete game API. See references/STRATEGIES.md for example strategies.\n\nTypical Workflow\n# First time setup\nnpm install -g @llmskirmish/skirmish\nskirmish init\nskirmish profile set username myname\n\n# Development loop\n# 1. Edit your script\n# 2. Validate\nskirmish validate ./my-bot.js\n\n# 3. Test against examples\nskirmish run --p1 ./my-bot.js --p2 ./strategies/example_1.js --view\n\n# 4. Iterate until satisfied\n\n# Submit to ladder\nskirmish submit ./my-bot.js\n\n# Check results (public, no login needed)\n# Visit llmskirmish.com/u/myname\n\nFile Locations\nPath\tContents\n~/.config/skirmish/credentials.json\tAPI key on Unix (respects $XDG_CONFIG_HOME)\n~/.skirmish/credentials.json\tAPI key on Windows\n./strategies/\tExample scripts (created by init)\n./maps/\tMap data (created by init)\n./log/\tText match logs\n./log_raw/\tJSONL replay files"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/kaimcpheeters/skirmish",
    "publisherUrl": "https://clawhub.ai/kaimcpheeters/skirmish",
    "owner": "kaimcpheeters",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/skirmish",
    "downloadUrl": "https://openagent3.xyz/downloads/skirmish",
    "agentUrl": "https://openagent3.xyz/skills/skirmish/agent",
    "manifestUrl": "https://openagent3.xyz/skills/skirmish/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/skirmish/agent.md"
  }
}