{
  "schemaVersion": "1.0",
  "item": {
    "slug": "solo-setup",
    "name": "Setup",
    "source": "tencent",
    "type": "skill",
    "category": "效率提升",
    "sourceUrl": "https://clawhub.ai/fortunto2/solo-setup",
    "canonicalUrl": "https://clawhub.ai/fortunto2/solo-setup",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/solo-setup",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=solo-setup",
    "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",
      "slug": "solo-setup",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-01T05:35:23.070Z",
      "expiresAt": "2026-05-08T05:35:23.070Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=solo-setup",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=solo-setup",
        "contentDisposition": "attachment; filename=\"solo-setup-2.1.1.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "solo-setup"
      },
      "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/solo-setup"
    },
    "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-setup",
    "agentPageUrl": "https://openagent3.xyz/skills/solo-setup/agent",
    "manifestUrl": "https://openagent3.xyz/skills/solo-setup/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/solo-setup/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": "/setup",
        "body": "Auto-generate project workflow config from existing PRD and CLAUDE.md. Zero interactive questions — all answers extracted from project data that already exists after /scaffold."
      },
      {
        "title": "When to use",
        "body": "After /scaffold creates a project, before /plan. Creates docs/workflow.md so /plan and /build can work."
      },
      {
        "title": "MCP Tools (use if available)",
        "body": "project_info(name) — get project details, detected stack\nkb_search(query) — search for dev principles, manifest, stack templates\ncodegraph_query(query) — check project dependencies in code graph\n\nIf MCP tools are not available, fall back to reading local files only."
      },
      {
        "title": "Steps",
        "body": "Detect project root:\n\nIf $ARGUMENTS is provided, look for a project with that name in the current directory or projects_dir from ~/.solo-factory/defaults.yaml.\nOtherwise use current working directory.\nVerify the directory exists and has CLAUDE.md.\nIf not found, ask via AskUserQuestion.\n\n\n\nCheck if already initialized:\n\nIf docs/workflow.md exists, warn and ask whether to regenerate.\n\n\n\nRead project data (parallel — all reads at once):\n\nCLAUDE.md — tech stack, architecture, commands, Do/Don't\ndocs/prd.md — problem, users, solution, features, metrics, pricing\npackage.json or pyproject.toml — exact dependency versions\nMakefile — available commands\nLinter configs (.eslintrc*, eslint.config.*, .swiftlint.yml, ruff.toml, detekt.yml)\n\n\n\nRead ecosystem sources (optional — enhances quality):\n\nDetect stack name from CLAUDE.md (look for \"Stack:\" or the stack name in tech section).\nIf MCP kb_search available: search for stack template and dev-principles.\nOtherwise: look for stacks/<stack>.yaml and dev-principles.md in .solo/ or plugin templates directory (if accessible).\nIf neither available: derive all info from CLAUDE.md + package manifest (sufficient).\n\n\n\nDetect languages from package manifest:\n\npackage.json → TypeScript\npyproject.toml → Python\n*.xcodeproj or Package.swift → Swift\nbuild.gradle.kts → Kotlin\n\n\n\nCreate docs directory if needed:\nmkdir -p docs\n\n\n\nGenerate docs/workflow.md:\nBased on dev-principles (from MCP/KB or built-in defaults):\n# Workflow — {ProjectName}\n\n## TDD Policy\n**Moderate** — Tests encouraged but not blocking. Write tests for:\n- Business logic and validation\n- API route handlers\n- Complex algorithms\nTests optional for: UI components, one-off scripts, prototypes.\n\n## Test Framework\n{from package manifest devDeps: vitest/jest/pytest/xctest}\n\n## Commit Strategy\n**Conventional Commits**\nFormat: `<type>(<scope>): <description>`\nTypes: feat, fix, refactor, test, docs, chore, perf, style\n\n## Verification Checkpoints\n**After each phase completion:**\n1. Run tests — all pass\n2. Run linter — no errors\n3. Run build — successful (if applicable)\n4. Manual smoke test\n\n## Branch Strategy\n- `main` — production-ready\n- `feat/<track-id>` — feature branches\n- `fix/<description>` — hotfixes\n\n\n\nUpdate CLAUDE.md — add workflow reference to Key Documents section if not present.\n\n\nShow summary and suggest next step:\nSetup complete for {ProjectName}!\n\nCreated:\n  docs/workflow.md — TDD moderate, conventional commits\n\nNext: /plan \"Your first feature\""
      },
      {
        "title": "CLAUDE.md not found",
        "body": "Cause: Project not scaffolded or running from wrong directory.\nFix: Run /scaffold first, or ensure you're in the project root with CLAUDE.md."
      },
      {
        "title": "workflow.md already exists",
        "body": "Cause: Previously set up.\nFix: Skill warns and asks whether to regenerate. Existing file is preserved unless you confirm overwrite."
      },
      {
        "title": "Wrong test framework detected",
        "body": "Cause: Multiple test frameworks in devDependencies.\nFix: Skill picks the first found. Edit docs/workflow.md manually to specify the correct framework."
      }
    ],
    "body": "/setup\n\nAuto-generate project workflow config from existing PRD and CLAUDE.md. Zero interactive questions — all answers extracted from project data that already exists after /scaffold.\n\nWhen to use\n\nAfter /scaffold creates a project, before /plan. Creates docs/workflow.md so /plan and /build can work.\n\nMCP Tools (use if available)\nproject_info(name) — get project details, detected stack\nkb_search(query) — search for dev principles, manifest, stack templates\ncodegraph_query(query) — check project dependencies in code graph\n\nIf MCP tools are not available, fall back to reading local files only.\n\nSteps\n\nDetect project root:\n\nIf $ARGUMENTS is provided, look for a project with that name in the current directory or projects_dir from ~/.solo-factory/defaults.yaml.\nOtherwise use current working directory.\nVerify the directory exists and has CLAUDE.md.\nIf not found, ask via AskUserQuestion.\n\nCheck if already initialized:\n\nIf docs/workflow.md exists, warn and ask whether to regenerate.\n\nRead project data (parallel — all reads at once):\n\nCLAUDE.md — tech stack, architecture, commands, Do/Don't\ndocs/prd.md — problem, users, solution, features, metrics, pricing\npackage.json or pyproject.toml — exact dependency versions\nMakefile — available commands\nLinter configs (.eslintrc*, eslint.config.*, .swiftlint.yml, ruff.toml, detekt.yml)\n\nRead ecosystem sources (optional — enhances quality):\n\nDetect stack name from CLAUDE.md (look for \"Stack:\" or the stack name in tech section).\nIf MCP kb_search available: search for stack template and dev-principles.\nOtherwise: look for stacks/<stack>.yaml and dev-principles.md in .solo/ or plugin templates directory (if accessible).\nIf neither available: derive all info from CLAUDE.md + package manifest (sufficient).\n\nDetect languages from package manifest:\n\npackage.json → TypeScript\npyproject.toml → Python\n*.xcodeproj or Package.swift → Swift\nbuild.gradle.kts → Kotlin\n\nCreate docs directory if needed:\n\nmkdir -p docs\n\n\nGenerate docs/workflow.md: Based on dev-principles (from MCP/KB or built-in defaults):\n\n# Workflow — {ProjectName}\n\n## TDD Policy\n**Moderate** — Tests encouraged but not blocking. Write tests for:\n- Business logic and validation\n- API route handlers\n- Complex algorithms\nTests optional for: UI components, one-off scripts, prototypes.\n\n## Test Framework\n{from package manifest devDeps: vitest/jest/pytest/xctest}\n\n## Commit Strategy\n**Conventional Commits**\nFormat: `<type>(<scope>): <description>`\nTypes: feat, fix, refactor, test, docs, chore, perf, style\n\n## Verification Checkpoints\n**After each phase completion:**\n1. Run tests — all pass\n2. Run linter — no errors\n3. Run build — successful (if applicable)\n4. Manual smoke test\n\n## Branch Strategy\n- `main` — production-ready\n- `feat/<track-id>` — feature branches\n- `fix/<description>` — hotfixes\n\n\nUpdate CLAUDE.md — add workflow reference to Key Documents section if not present.\n\nShow summary and suggest next step:\n\nSetup complete for {ProjectName}!\n\nCreated:\n  docs/workflow.md — TDD moderate, conventional commits\n\nNext: /plan \"Your first feature\"\n\nCommon Issues\nCLAUDE.md not found\n\nCause: Project not scaffolded or running from wrong directory. Fix: Run /scaffold first, or ensure you're in the project root with CLAUDE.md.\n\nworkflow.md already exists\n\nCause: Previously set up. Fix: Skill warns and asks whether to regenerate. Existing file is preserved unless you confirm overwrite.\n\nWrong test framework detected\n\nCause: Multiple test frameworks in devDependencies. Fix: Skill picks the first found. Edit docs/workflow.md manually to specify the correct framework."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/fortunto2/solo-setup",
    "publisherUrl": "https://clawhub.ai/fortunto2/solo-setup",
    "owner": "fortunto2",
    "version": "2.1.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/solo-setup",
    "downloadUrl": "https://openagent3.xyz/downloads/solo-setup",
    "agentUrl": "https://openagent3.xyz/skills/solo-setup/agent",
    "manifestUrl": "https://openagent3.xyz/skills/solo-setup/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/solo-setup/agent.md"
  }
}