{
  "schemaVersion": "1.0",
  "item": {
    "slug": "zellij",
    "name": "Zellij Terminal Workspace",
    "source": "tencent",
    "type": "skill",
    "category": "效率提升",
    "sourceUrl": "https://clawhub.ai/Jivvei/zellij",
    "canonicalUrl": "https://clawhub.ai/Jivvei/zellij",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/zellij",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=zellij",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/cleanup-sessions.sh",
      "scripts/find-panes.sh",
      "scripts/find-sessions.sh",
      "scripts/wait-for-text.sh"
    ],
    "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",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/zellij"
    },
    "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/zellij",
    "agentPageUrl": "https://openagent3.xyz/skills/zellij/agent",
    "manifestUrl": "https://openagent3.xyz/skills/zellij/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/zellij/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": "zellij Skill (Moltbot)",
        "body": "Use zellij only when you need an interactive TTY. Prefer exec background mode for long-running, non-interactive tasks."
      },
      {
        "title": "Quickstart (data dir, exec tool)",
        "body": "DATA_DIR=\"${CLAWDBOT_ZELLIJ_DATA_DIR:-${TMPDIR:-/tmp}/moltbot-zellij-data}\"\nmkdir -p \"$DATA_DIR\"\nSESSION=moltbot-python\n\nzellij --data-dir \"$DATA_DIR\" new-session --session \"$SESSION\" --layout \"default\" --detach\nzellij --data-dir \"$DATA_DIR\" run --session \"$SESSION\" --name repl -- python3 -q\nzellij --data-dir \"$DATA_DIR\" pipe --session \"$SESSION\" --pane-id 0\n\nAfter starting a session, always print monitor commands:\n\nTo monitor:\n  zellij --data-dir \"$DATA_DIR\" attach --session \"$SESSION\"\n  zellij --data-dir \"$DATA_DIR\" pipe --session \"$SESSION\" --pane-id 0"
      },
      {
        "title": "Data directory convention",
        "body": "Use CLAWDBOT_ZELLIJ_DATA_DIR (default ${TMPDIR:-/tmp}/moltbot-zellij-data).\nZellij stores state (sessions, plugins, etc.) in this directory."
      },
      {
        "title": "Targeting panes and naming",
        "body": "Zellij uses pane-id (numeric) to target specific panes.\nFind pane IDs: zellij --data-dir \"$DATA_DIR\" list-sessions --long or use list-panes.sh.\nKeep session names short; avoid spaces."
      },
      {
        "title": "Finding sessions",
        "body": "List sessions on your data dir: zellij --data-dir \"$DATA_DIR\" list-sessions.\nList sessions across all data dirs: {baseDir}/scripts/find-sessions.sh --all (uses CLAWDBOT_ZELLIJ_DATA_DIR)."
      },
      {
        "title": "Sending input safely",
        "body": "Use zellij action to send keystrokes: zellij --data-dir \"$DATA_DIR\" action --session \"$SESSION\" write-chars --chars \"$cmd\".\nControl keys: zellij --data-dir \"$DATA_DIR\" action --session \"$SESSION\" write 2 (Ctrl+C)."
      },
      {
        "title": "Watching output",
        "body": "Capture pane output: zellij --data-dir \"$DATA_DIR\" pipe --session \"$SESSION\" --pane-id 0.\nWait for prompts: {baseDir}/scripts/wait-for-text.sh -s \"$SESSION\" -p 0 -p 'pattern'.\nAttaching is OK; detach with Ctrl+p d (zellij default detach)."
      },
      {
        "title": "Spawning processes",
        "body": "For python REPLs, zellij works well with standard python3 -q.\nNo special flags needed like tmux's PYTHON_BASIC_REPL=1."
      },
      {
        "title": "Windows / WSL",
        "body": "zellij is supported on macOS/Linux. On Windows, use WSL and install zellij inside WSL.\nThis skill is gated to darwin/linux and requires zellij on PATH."
      },
      {
        "title": "Orchestrating Coding Agents (Codex, Claude Code)",
        "body": "zellij excels at running multiple coding agents in parallel:\n\nDATA_DIR=\"${TMPDIR:-/tmp}/codex-army-data\"\n\n# Create multiple sessions\nfor i in 1 2 3 4 5; do\n  zellij --data-dir \"$DATA_DIR\" new-session --session \"agent-$i\" --layout \"compact\" --detach\ndone\n\n# Launch agents in different workdirs\nzellij --data-dir \"$DATA_DIR\" action --session \"agent-1\" write-chars --chars \"cd /tmp/project1 && codex --yolo 'Fix bug X'\\n\"\nzellij --data-dir \"$DATA_DIR\" action --session \"agent-2\" write-chars --chars \"cd /tmp/project2 && codex --yolo 'Fix bug Y'\\n\"\n\n# Poll for completion (check if prompt returned)\nfor sess in agent-1 agent-2; do\n  pane_id=$(zellij --data-dir \"$DATA_DIR\" list-sessions --long | grep \"\\\"$sess\\\"\" | jq -r '.tabs[0].panes[0].id')\n  if zellij --data-dir \"$DATA_DIR\" pipe --session \"$sess\" --pane-id \"$pane_id\" | grep -q \"❯\"; then\n    echo \"$sess: DONE\"\n  else\n    echo \"$sess: Running...\"\n  fi\ndone\n\n# Get full output from completed session\nzellij --data-dir \"$DATA_DIR\" pipe --session \"agent-1\" --pane-id 0\n\nTips:\n\nUse separate git worktrees for parallel fixes (no branch conflicts)\npnpm install first before running codex in fresh clones\nCheck for shell prompt (❯ or $) to detect completion\nCodex needs --yolo or --full-auto for non-interactive fixes"
      },
      {
        "title": "Cleanup",
        "body": "Kill a session: zellij --data-dir \"$DATA_DIR\" delete-session --session \"$SESSION\".\nKill all sessions on a data dir: use {baseDir}/scripts/cleanup-sessions.sh \"$DATA_DIR\"."
      },
      {
        "title": "Zellij vs Tmux Quick Reference",
        "body": "TasktmuxzellijList sessionslist-sessionslist-sessionsCreate sessionnew-session -dnew-session --detachAttachattach -tattach --sessionSend keyssend-keysaction write-charsCapture panecapture-panepipeKill sessionkill-sessiondelete-sessionDetachCtrl+b dCtrl+p d"
      },
      {
        "title": "Helper: wait-for-text.sh",
        "body": "{baseDir}/scripts/wait-for-text.sh polls a pane for a regex (or fixed string) with a timeout.\n\n{baseDir}/scripts/wait-for-text.sh -s session -p pane-id -r 'pattern' [-F] [-T 20] [-i 0.5]\n\n-s/--session session name (required)\n-p/--pane-id pane ID (required)\n-r/--pattern regex to match (required); add -F for fixed string\n-T timeout seconds (integer, default 15)\n-i poll interval seconds (default 0.5)"
      },
      {
        "title": "Helper: find-panes.sh",
        "body": "{baseDir}/scripts/find-panes.sh lists panes for a given session.\n\n{baseDir}/scripts/find-panes.sh -s session [-d data-dir]\n\n-s/--session session name (required)\n-d/--data-dir zellij data dir (uses CLAWDBOT_ZELLIJ_DATA_DIR if not specified)"
      }
    ],
    "body": "zellij Skill (Moltbot)\n\nUse zellij only when you need an interactive TTY. Prefer exec background mode for long-running, non-interactive tasks.\n\nQuickstart (data dir, exec tool)\nDATA_DIR=\"${CLAWDBOT_ZELLIJ_DATA_DIR:-${TMPDIR:-/tmp}/moltbot-zellij-data}\"\nmkdir -p \"$DATA_DIR\"\nSESSION=moltbot-python\n\nzellij --data-dir \"$DATA_DIR\" new-session --session \"$SESSION\" --layout \"default\" --detach\nzellij --data-dir \"$DATA_DIR\" run --session \"$SESSION\" --name repl -- python3 -q\nzellij --data-dir \"$DATA_DIR\" pipe --session \"$SESSION\" --pane-id 0\n\n\nAfter starting a session, always print monitor commands:\n\nTo monitor:\n  zellij --data-dir \"$DATA_DIR\" attach --session \"$SESSION\"\n  zellij --data-dir \"$DATA_DIR\" pipe --session \"$SESSION\" --pane-id 0\n\nData directory convention\nUse CLAWDBOT_ZELLIJ_DATA_DIR (default ${TMPDIR:-/tmp}/moltbot-zellij-data).\nZellij stores state (sessions, plugins, etc.) in this directory.\nTargeting panes and naming\nZellij uses pane-id (numeric) to target specific panes.\nFind pane IDs: zellij --data-dir \"$DATA_DIR\" list-sessions --long or use list-panes.sh.\nKeep session names short; avoid spaces.\nFinding sessions\nList sessions on your data dir: zellij --data-dir \"$DATA_DIR\" list-sessions.\nList sessions across all data dirs: {baseDir}/scripts/find-sessions.sh --all (uses CLAWDBOT_ZELLIJ_DATA_DIR).\nSending input safely\nUse zellij action to send keystrokes: zellij --data-dir \"$DATA_DIR\" action --session \"$SESSION\" write-chars --chars \"$cmd\".\nControl keys: zellij --data-dir \"$DATA_DIR\" action --session \"$SESSION\" write 2 (Ctrl+C).\nWatching output\nCapture pane output: zellij --data-dir \"$DATA_DIR\" pipe --session \"$SESSION\" --pane-id 0.\nWait for prompts: {baseDir}/scripts/wait-for-text.sh -s \"$SESSION\" -p 0 -p 'pattern'.\nAttaching is OK; detach with Ctrl+p d (zellij default detach).\nSpawning processes\nFor python REPLs, zellij works well with standard python3 -q.\nNo special flags needed like tmux's PYTHON_BASIC_REPL=1.\nWindows / WSL\nzellij is supported on macOS/Linux. On Windows, use WSL and install zellij inside WSL.\nThis skill is gated to darwin/linux and requires zellij on PATH.\nOrchestrating Coding Agents (Codex, Claude Code)\n\nzellij excels at running multiple coding agents in parallel:\n\nDATA_DIR=\"${TMPDIR:-/tmp}/codex-army-data\"\n\n# Create multiple sessions\nfor i in 1 2 3 4 5; do\n  zellij --data-dir \"$DATA_DIR\" new-session --session \"agent-$i\" --layout \"compact\" --detach\ndone\n\n# Launch agents in different workdirs\nzellij --data-dir \"$DATA_DIR\" action --session \"agent-1\" write-chars --chars \"cd /tmp/project1 && codex --yolo 'Fix bug X'\\n\"\nzellij --data-dir \"$DATA_DIR\" action --session \"agent-2\" write-chars --chars \"cd /tmp/project2 && codex --yolo 'Fix bug Y'\\n\"\n\n# Poll for completion (check if prompt returned)\nfor sess in agent-1 agent-2; do\n  pane_id=$(zellij --data-dir \"$DATA_DIR\" list-sessions --long | grep \"\\\"$sess\\\"\" | jq -r '.tabs[0].panes[0].id')\n  if zellij --data-dir \"$DATA_DIR\" pipe --session \"$sess\" --pane-id \"$pane_id\" | grep -q \"❯\"; then\n    echo \"$sess: DONE\"\n  else\n    echo \"$sess: Running...\"\n  fi\ndone\n\n# Get full output from completed session\nzellij --data-dir \"$DATA_DIR\" pipe --session \"agent-1\" --pane-id 0\n\n\nTips:\n\nUse separate git worktrees for parallel fixes (no branch conflicts)\npnpm install first before running codex in fresh clones\nCheck for shell prompt (❯ or $) to detect completion\nCodex needs --yolo or --full-auto for non-interactive fixes\nCleanup\nKill a session: zellij --data-dir \"$DATA_DIR\" delete-session --session \"$SESSION\".\nKill all sessions on a data dir: use {baseDir}/scripts/cleanup-sessions.sh \"$DATA_DIR\".\nZellij vs Tmux Quick Reference\nTask\ttmux\tzellij\nList sessions\tlist-sessions\tlist-sessions\nCreate session\tnew-session -d\tnew-session --detach\nAttach\tattach -t\tattach --session\nSend keys\tsend-keys\taction write-chars\nCapture pane\tcapture-pane\tpipe\nKill session\tkill-session\tdelete-session\nDetach\tCtrl+b d\tCtrl+p d\nHelper: wait-for-text.sh\n\n{baseDir}/scripts/wait-for-text.sh polls a pane for a regex (or fixed string) with a timeout.\n\n{baseDir}/scripts/wait-for-text.sh -s session -p pane-id -r 'pattern' [-F] [-T 20] [-i 0.5]\n\n-s/--session session name (required)\n-p/--pane-id pane ID (required)\n-r/--pattern regex to match (required); add -F for fixed string\n-T timeout seconds (integer, default 15)\n-i poll interval seconds (default 0.5)\nHelper: find-panes.sh\n\n{baseDir}/scripts/find-panes.sh lists panes for a given session.\n\n{baseDir}/scripts/find-panes.sh -s session [-d data-dir]\n\n-s/--session session name (required)\n-d/--data-dir zellij data dir (uses CLAWDBOT_ZELLIJ_DATA_DIR if not specified)"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Jivvei/zellij",
    "publisherUrl": "https://clawhub.ai/Jivvei/zellij",
    "owner": "Jivvei",
    "version": "1.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/zellij",
    "downloadUrl": "https://openagent3.xyz/downloads/zellij",
    "agentUrl": "https://openagent3.xyz/skills/zellij/agent",
    "manifestUrl": "https://openagent3.xyz/skills/zellij/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/zellij/agent.md"
  }
}