{
  "schemaVersion": "1.0",
  "item": {
    "slug": "solo-pipeline",
    "name": "Pipeline",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/fortunto2/solo-pipeline",
    "canonicalUrl": "https://clawhub.ai/fortunto2/solo-pipeline",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/solo-pipeline",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=solo-pipeline",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.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",
      "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/solo-pipeline"
    },
    "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/solo-pipeline",
    "agentPageUrl": "https://openagent3.xyz/skills/solo-pipeline/agent",
    "manifestUrl": "https://openagent3.xyz/skills/solo-pipeline/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/solo-pipeline/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": "/pipeline",
        "body": "Launch an automated multi-skill pipeline. The Stop hook chains skills automatically — no manual invocation needed between stages."
      },
      {
        "title": "Research Pipeline",
        "body": "/pipeline research \"AI therapist app\"\n\nChains: /research -> /validate\nProduces: research.md -> prd.md"
      },
      {
        "title": "Dev Pipeline",
        "body": "/pipeline dev \"project-name\" \"stack\"\n/pipeline dev \"project-name\" \"stack\" --feature \"user onboarding\"\n\nChains: /scaffold -> /setup -> /plan -> /build\nProduces: full project with workflow, plan, and implementation"
      },
      {
        "title": "1. Parse Arguments",
        "body": "Extract from $ARGUMENTS:\n\nPipeline type: first word (research or dev)\nRemaining args: passed to the launcher script\n\nIf no arguments or unclear, ask:\n\nWhich pipeline do you want to run?\n\n1. Research Pipeline — /research → /validate (idea to PRD)\n2. Dev Pipeline — /scaffold → /setup → /plan → /build (PRD to running code)"
      },
      {
        "title": "2. Confirm with User",
        "body": "Show what will happen:\n\nPipeline: {type}\nStages: {stage1} → {stage2} → ...\nIdea/Project: {name}\n\nThis will run multiple skills automatically. Continue?\n\nAsk via AskUserQuestion."
      },
      {
        "title": "3. Start First Stage",
        "body": "Run the first skill in the pipeline directly:\n\nFor research pipeline: Run /research \"idea name\"\nFor dev pipeline: Run /scaffold project-name stack\n\nThe Stop hook (if configured) will handle subsequent stages automatically.\nWithout a Stop hook, manually invoke each skill in sequence."
      },
      {
        "title": "3b. Launcher Scripts (optional, Claude Code plugin only)",
        "body": "If you have the solo-factory plugin installed, launcher scripts provide tmux dashboard and logging:\n\n# Only available with Claude Code plugin — skip if not installed\nsolo-research.sh \"idea name\" [--project name]\nsolo-dev.sh \"project-name\" \"stack\" [--feature \"desc\"]\n\nPass --no-dashboard when running from within a skill context."
      },
      {
        "title": "5. Pipeline Completion",
        "body": "When all stages are done, output:\n\n<solo:done/>\n\nThe Stop hook checks for this signal and cleans up the state file."
      },
      {
        "title": "State File",
        "body": "Location: .solo/pipelines/solo-pipeline-{project}.local.md (project-local) or ~/.solo/pipelines/solo-pipeline-{project}.local.md (global fallback)\nLog file: .solo/pipelines/solo-pipeline-{project}.log\n\nFormat: YAML frontmatter with stages list, project_root, and log_file fields.\nThe Stop hook reads this file on every session exit attempt.\n\nTo cancel a pipeline manually: delete the state file solo-pipeline-{project}.local.md"
      },
      {
        "title": "tmux Dashboard (terminal use)",
        "body": "When launched from terminal (without --no-dashboard), a tmux dashboard opens automatically with:\n\nPane 0: work area\nPane 1: tail -f on log file\nPane 2: live status display (refreshes every 2s)"
      },
      {
        "title": "Manual Monitoring",
        "body": "Monitor pipeline progress with standard tools:\n\n# Watch log file\ntail -f .solo/pipelines/solo-pipeline-<project>.log\n\n# Check pipeline state\n\n# Auto-refresh\nwatch -n2 -c solo-pipeline-status.sh\n\nOtherwise, use standard tools:\n\n# Log tail\ntail -f .solo/pipelines/solo-pipeline-<project>.log\n\n# Check state file\ncat .solo/pipelines/solo-pipeline-<project>.local.md"
      },
      {
        "title": "Session Reuse",
        "body": "Re-running a pipeline reuses any existing state — completed stages are skipped automatically.\n\nNo need to close/recreate — just run the same command again"
      },
      {
        "title": "Log Format",
        "body": "[22:30:15] START    | my-app | stages: research -> validate | max: 5\n[22:30:16] STAGE    | iter 1/5 | stage 1/2: research\n[22:30:16] INVOKE   | /research \"AI therapist app\"\n[22:35:42] CHECK    | research | .../research.md -> FOUND\n[22:35:42] STAGE    | iter 2/5 | stage 2/2: validate\n[22:35:42] INVOKE   | /validate \"AI therapist app\"\n[22:40:10] CHECK    | validate | .../prd.md -> FOUND\n[22:40:10] DONE     | All stages complete! Promise detected.\n[22:40:10] FINISH   | Duration: 10m"
      },
      {
        "title": "Critical Rules",
        "body": "Always confirm before starting a pipeline.\nDon't skip stages — the hook handles progression.\nCancel = delete state file — tell users this if they want to stop.\nMax iterations prevent infinite loops (default 5 for research, 15 for dev).\nUse --no-dashboard when running from within Claude Code skill context."
      }
    ],
    "body": "/pipeline\n\nLaunch an automated multi-skill pipeline. The Stop hook chains skills automatically — no manual invocation needed between stages.\n\nAvailable Pipelines\nResearch Pipeline\n\n/pipeline research \"AI therapist app\"\n\nChains: /research -> /validate Produces: research.md -> prd.md\n\nDev Pipeline\n\n/pipeline dev \"project-name\" \"stack\" /pipeline dev \"project-name\" \"stack\" --feature \"user onboarding\"\n\nChains: /scaffold -> /setup -> /plan -> /build Produces: full project with workflow, plan, and implementation\n\nSteps\n1. Parse Arguments\n\nExtract from $ARGUMENTS:\n\nPipeline type: first word (research or dev)\nRemaining args: passed to the launcher script\n\nIf no arguments or unclear, ask:\n\nWhich pipeline do you want to run?\n\n1. Research Pipeline — /research → /validate (idea to PRD)\n2. Dev Pipeline — /scaffold → /setup → /plan → /build (PRD to running code)\n\n2. Confirm with User\n\nShow what will happen:\n\nPipeline: {type}\nStages: {stage1} → {stage2} → ...\nIdea/Project: {name}\n\nThis will run multiple skills automatically. Continue?\n\n\nAsk via AskUserQuestion.\n\n3. Start First Stage\n\nRun the first skill in the pipeline directly:\n\nFor research pipeline: Run /research \"idea name\" For dev pipeline: Run /scaffold project-name stack\n\nThe Stop hook (if configured) will handle subsequent stages automatically. Without a Stop hook, manually invoke each skill in sequence.\n\n3b. Launcher Scripts (optional, Claude Code plugin only)\n\nIf you have the solo-factory plugin installed, launcher scripts provide tmux dashboard and logging:\n\n# Only available with Claude Code plugin — skip if not installed\nsolo-research.sh \"idea name\" [--project name]\nsolo-dev.sh \"project-name\" \"stack\" [--feature \"desc\"]\n\n\nPass --no-dashboard when running from within a skill context.\n\n5. Pipeline Completion\n\nWhen all stages are done, output:\n\n<solo:done/>\n\n\nThe Stop hook checks for this signal and cleans up the state file.\n\nState File\n\nLocation: .solo/pipelines/solo-pipeline-{project}.local.md (project-local) or ~/.solo/pipelines/solo-pipeline-{project}.local.md (global fallback) Log file: .solo/pipelines/solo-pipeline-{project}.log\n\nFormat: YAML frontmatter with stages list, project_root, and log_file fields. The Stop hook reads this file on every session exit attempt.\n\nTo cancel a pipeline manually: delete the state file solo-pipeline-{project}.local.md\n\nMonitoring\ntmux Dashboard (terminal use)\n\nWhen launched from terminal (without --no-dashboard), a tmux dashboard opens automatically with:\n\nPane 0: work area\nPane 1: tail -f on log file\nPane 2: live status display (refreshes every 2s)\nManual Monitoring\n\nMonitor pipeline progress with standard tools:\n\n# Watch log file\ntail -f .solo/pipelines/solo-pipeline-<project>.log\n\n# Check pipeline state\n\n# Auto-refresh\nwatch -n2 -c solo-pipeline-status.sh\n\n\nOtherwise, use standard tools:\n\n# Log tail\ntail -f .solo/pipelines/solo-pipeline-<project>.log\n\n# Check state file\ncat .solo/pipelines/solo-pipeline-<project>.local.md\n\nSession Reuse\n\nRe-running a pipeline reuses any existing state — completed stages are skipped automatically.\n\nNo need to close/recreate — just run the same command again\nLog Format\n[22:30:15] START    | my-app | stages: research -> validate | max: 5\n[22:30:16] STAGE    | iter 1/5 | stage 1/2: research\n[22:30:16] INVOKE   | /research \"AI therapist app\"\n[22:35:42] CHECK    | research | .../research.md -> FOUND\n[22:35:42] STAGE    | iter 2/5 | stage 2/2: validate\n[22:35:42] INVOKE   | /validate \"AI therapist app\"\n[22:40:10] CHECK    | validate | .../prd.md -> FOUND\n[22:40:10] DONE     | All stages complete! Promise detected.\n[22:40:10] FINISH   | Duration: 10m\n\nCritical Rules\nAlways confirm before starting a pipeline.\nDon't skip stages — the hook handles progression.\nCancel = delete state file — tell users this if they want to stop.\nMax iterations prevent infinite loops (default 5 for research, 15 for dev).\nUse --no-dashboard when running from within Claude Code skill context."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/fortunto2/solo-pipeline",
    "publisherUrl": "https://clawhub.ai/fortunto2/solo-pipeline",
    "owner": "fortunto2",
    "version": "1.4.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/solo-pipeline",
    "downloadUrl": "https://openagent3.xyz/downloads/solo-pipeline",
    "agentUrl": "https://openagent3.xyz/skills/solo-pipeline/agent",
    "manifestUrl": "https://openagent3.xyz/skills/solo-pipeline/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/solo-pipeline/agent.md"
  }
}