{
  "schemaVersion": "1.0",
  "item": {
    "slug": "command-creator",
    "name": "Command Creator",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/wpank/command-creator",
    "canonicalUrl": "https://clawhub.ai/wpank/command-creator",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/command-creator",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=command-creator",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "references/best-practices.md",
      "references/examples.md",
      "references/patterns.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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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/command-creator"
    },
    "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/command-creator",
    "agentPageUrl": "https://openagent3.xyz/skills/command-creator/agent",
    "manifestUrl": "https://openagent3.xyz/skills/command-creator/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/command-creator/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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Command Creator",
        "body": "Slash commands are markdown files in .claude/commands/ (project) or ~/.claude/commands/ (global) that expand into prompts when invoked."
      },
      {
        "title": "Command Structure",
        "body": "---\ndescription: Brief description for /help (required)\nargument-hint: <required> or [optional] (if takes arguments)\n---\n\n# Command Title\n\n[Instructions for agent to execute autonomously]"
      },
      {
        "title": "Step 1: Determine Location",
        "body": "Check if in git repo: git rev-parse --is-inside-work-tree\nDefault: Git repo → .claude/commands/, No git → ~/.claude/commands/\nOverride if user explicitly says \"global\" or \"project\"\n\nReport chosen location before proceeding."
      },
      {
        "title": "Step 2: Identify Pattern",
        "body": "Load references/patterns.md and present options:\n\nPatternStructureUse WhenWorkflow AutomationAnalyze → Act → ReportMulti-step with clear sequenceIterative FixingRun → Parse → Fix → RepeatFix issues until passingAgent DelegationContext → Delegate → IterateComplex tasks, user reviewSimple ExecutionParse → Execute → ReturnWrapper for existing tools\n\nAsk: \"Which pattern is closest to what you want?\""
      },
      {
        "title": "Step 3: Gather Information",
        "body": "A. Name and Purpose\n\n\"What should the command be called?\" (kebab-case: my-command)\n\"What does it do?\" (for description field)\n\nB. Arguments\n\n\"Does it take arguments? Required or optional?\"\nRequired: <placeholder>, Optional: [placeholder]\n\nC. Workflow Steps\n\n\"What specific steps should it follow?\"\n\"What tools or commands should it use?\"\n\nD. Constraints\n\n\"Any specific tools to use or avoid?\"\n\"Any files to read for context?\""
      },
      {
        "title": "Step 4: Generate Command",
        "body": "Load references/best-practices.md for:\n\nTemplate structure\nWriting style (imperative form)\nQuality checklist\n\nKey principles:\n\nUse imperative form: \"Run X\", not \"You should run X\"\nBe explicit: \"Run make lint\", not \"Check for errors\"\nInclude expected outcomes\nDefine error handling\nState success criteria"
      },
      {
        "title": "Step 5: Create File",
        "body": "mkdir -p [directory-path]\n\nWrite the command file. Report:\n\nFile location\nWhat the command does\nHow to use: /command-name [args]"
      },
      {
        "title": "Step 6: Test (Optional)",
        "body": "Suggest: \"Test with /command-name [args]\"\n\nIterate based on feedback."
      },
      {
        "title": "Writing Guidelines",
        "body": "Imperative form (verb-first):\n\n✅ \"Run git status\"\n❌ \"You should run git status\"\n\nSpecific, not vague:\n\n✅ \"Run make lint to check for errors\"\n❌ \"Check for errors\"\n\nInclude outcomes:\n\n✅ \"Run git status - should show modified files\"\n❌ \"Run git status\"\n\nRealistic examples:\n\n✅ git commit -m \"Add OAuth2 authentication\"\n❌ git commit -m \"foo bar\""
      },
      {
        "title": "Workflow Automation",
        "body": "1. Check for .PLAN.md\n2. Analyze git status/diff\n3. Perform actions\n4. Report results"
      },
      {
        "title": "Iterative Fixing",
        "body": "1. Run make all-ci (max 10 iterations)\n2. Parse errors by category\n3. Apply targeted fixes\n4. Repeat until success or stuck"
      },
      {
        "title": "Agent Delegation",
        "body": "1. Present context\n2. Invoke subagent with Task tool\n3. Iterate with user feedback\n4. Save output after approval\n\nSee references/examples.md for full command examples."
      },
      {
        "title": "Quality Checklist",
        "body": "Before finalizing:\n\nName is kebab-case (my-command, not my_command)\n Description is action-oriented\n Steps are numbered and specific\n Tool usage explicitly specified\n Error handling defined\n Success criteria stated\n Uses imperative form"
      },
      {
        "title": "NEVER",
        "body": "Use underscores in command names (use hyphens)\nWrite vague instructions (\"fix errors\")\nSkip error handling\nUse second person (\"You should...\")\nCreate commands without testing\nLeave success criteria undefined"
      }
    ],
    "body": "Command Creator\n\nSlash commands are markdown files in .claude/commands/ (project) or ~/.claude/commands/ (global) that expand into prompts when invoked.\n\nCommand Structure\n---\ndescription: Brief description for /help (required)\nargument-hint: <required> or [optional] (if takes arguments)\n---\n\n# Command Title\n\n[Instructions for agent to execute autonomously]\n\nCreation Workflow\nStep 1: Determine Location\nCheck if in git repo: git rev-parse --is-inside-work-tree\nDefault: Git repo → .claude/commands/, No git → ~/.claude/commands/\nOverride if user explicitly says \"global\" or \"project\"\n\nReport chosen location before proceeding.\n\nStep 2: Identify Pattern\n\nLoad references/patterns.md and present options:\n\nPattern\tStructure\tUse When\nWorkflow Automation\tAnalyze → Act → Report\tMulti-step with clear sequence\nIterative Fixing\tRun → Parse → Fix → Repeat\tFix issues until passing\nAgent Delegation\tContext → Delegate → Iterate\tComplex tasks, user review\nSimple Execution\tParse → Execute → Return\tWrapper for existing tools\n\nAsk: \"Which pattern is closest to what you want?\"\n\nStep 3: Gather Information\n\nA. Name and Purpose\n\n\"What should the command be called?\" (kebab-case: my-command)\n\"What does it do?\" (for description field)\n\nB. Arguments\n\n\"Does it take arguments? Required or optional?\"\nRequired: <placeholder>, Optional: [placeholder]\n\nC. Workflow Steps\n\n\"What specific steps should it follow?\"\n\"What tools or commands should it use?\"\n\nD. Constraints\n\n\"Any specific tools to use or avoid?\"\n\"Any files to read for context?\"\nStep 4: Generate Command\n\nLoad references/best-practices.md for:\n\nTemplate structure\nWriting style (imperative form)\nQuality checklist\n\nKey principles:\n\nUse imperative form: \"Run X\", not \"You should run X\"\nBe explicit: \"Run make lint\", not \"Check for errors\"\nInclude expected outcomes\nDefine error handling\nState success criteria\nStep 5: Create File\nmkdir -p [directory-path]\n\n\nWrite the command file. Report:\n\nFile location\nWhat the command does\nHow to use: /command-name [args]\nStep 6: Test (Optional)\n\nSuggest: \"Test with /command-name [args]\"\n\nIterate based on feedback.\n\nWriting Guidelines\n\nImperative form (verb-first):\n\n✅ \"Run git status\"\n❌ \"You should run git status\"\n\nSpecific, not vague:\n\n✅ \"Run make lint to check for errors\"\n❌ \"Check for errors\"\n\nInclude outcomes:\n\n✅ \"Run git status - should show modified files\"\n❌ \"Run git status\"\n\nRealistic examples:\n\n✅ git commit -m \"Add OAuth2 authentication\"\n❌ git commit -m \"foo bar\"\nCommand Patterns Quick Reference\nWorkflow Automation\n1. Check for .PLAN.md\n2. Analyze git status/diff\n3. Perform actions\n4. Report results\n\nIterative Fixing\n1. Run make all-ci (max 10 iterations)\n2. Parse errors by category\n3. Apply targeted fixes\n4. Repeat until success or stuck\n\nAgent Delegation\n1. Present context\n2. Invoke subagent with Task tool\n3. Iterate with user feedback\n4. Save output after approval\n\n\nSee references/examples.md for full command examples.\n\nQuality Checklist\n\nBefore finalizing:\n\n Name is kebab-case (my-command, not my_command)\n Description is action-oriented\n Steps are numbered and specific\n Tool usage explicitly specified\n Error handling defined\n Success criteria stated\n Uses imperative form\nNEVER\nUse underscores in command names (use hyphens)\nWrite vague instructions (\"fix errors\")\nSkip error handling\nUse second person (\"You should...\")\nCreate commands without testing\nLeave success criteria undefined"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/wpank/command-creator",
    "publisherUrl": "https://clawhub.ai/wpank/command-creator",
    "owner": "wpank",
    "version": "0.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/command-creator",
    "downloadUrl": "https://openagent3.xyz/downloads/command-creator",
    "agentUrl": "https://openagent3.xyz/skills/command-creator/agent",
    "manifestUrl": "https://openagent3.xyz/skills/command-creator/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/command-creator/agent.md"
  }
}