{
  "schemaVersion": "1.0",
  "item": {
    "slug": "super-skills",
    "name": "Decomposes complex user requests into executable subtasks, identifies required capabilities, searches for existing skills at skills.sh, and creates new skills when no solution exists. This skill should be used when the user submits a complex multi-step request, wants to automate workflows, or needs help breaking down large tasks into manageable pieces.",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/10e9928a/super-skills",
    "canonicalUrl": "https://clawhub.ai/10e9928a/super-skills",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/super-skills",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=super-skills",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "README_CN.md",
      "SKILL.md",
      "assets/skill_template.md",
      "references/capability_types.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/super-skills"
    },
    "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/super-skills",
    "agentPageUrl": "https://openagent3.xyz/skills/super-skills/agent",
    "manifestUrl": "https://openagent3.xyz/skills/super-skills/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/super-skills/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": "Task Decomposer & Skill Generator",
        "body": "This skill helps decompose complex user requests into executable subtasks, identify required capabilities for each task, search for existing skills from the open skills ecosystem, and automatically create new skills when no existing solution is available."
      },
      {
        "title": "Core Workflow",
        "body": "User Request → Task Decomposition → Capability Identification → Skill Search → Gap Analysis → Skill Creation → Execution Plan"
      },
      {
        "title": "Phase 1: Task Analysis & Decomposition",
        "body": "When receiving a user request, follow these steps:"
      },
      {
        "title": "Step 1: Understand User Intent",
        "body": "Analyze the request to identify:\n\nCore objective: What is the end goal?\nDomains involved: What areas of expertise are needed?\nTrigger mechanism: One-time, scheduled, or event-driven?\n\nExample analysis:\n\nUser Input: \"Help me get email summaries every morning and send them to Slack\"\n\nAnalysis:\n- Core objective: Automated email digest delivery to Slack\n- Domains: Email access, content summarization, messaging\n- Trigger: Scheduled (daily morning)"
      },
      {
        "title": "Step 2: Decompose into Atomic Tasks",
        "body": "Break down the complex task into minimal executable units:\n\nTask Decomposition:\n  - task_id: 1\n    name: \"Access and retrieve email list\"\n    type: \"data_retrieval\"\n    input: \"Email credentials/session\"\n    output: \"List of emails with metadata\"\n    dependencies: []\n    \n  - task_id: 2\n    name: \"Extract key information from emails\"\n    type: \"data_extraction\"\n    input: \"Email list\"\n    output: \"Structured email data\"\n    dependencies: [1]\n    \n  - task_id: 3\n    name: \"Generate email summary\"\n    type: \"content_generation\"\n    input: \"Structured email data\"\n    output: \"Formatted summary text\"\n    dependencies: [2]\n    \n  - task_id: 4\n    name: \"Send message to Slack\"\n    type: \"message_delivery\"\n    input: \"Summary text, Slack webhook/token\"\n    output: \"Delivery confirmation\"\n    dependencies: [3]\n    \n  - task_id: 5\n    name: \"Configure scheduled execution\"\n    type: \"scheduling\"\n    input: \"Workflow script, schedule config\"\n    output: \"Active scheduled job\"\n    dependencies: [4]"
      },
      {
        "title": "Phase 2: Capability Identification",
        "body": "Map each subtask to a capability type from the universal capability taxonomy."
      },
      {
        "title": "Universal Capability Types",
        "body": "CapabilityDescriptionSearch Keywordsbrowser_automationWeb navigation, interaction, scrapingbrowser, selenium, puppeteer, playwright, scrapeweb_searchInternet search and information retrievalsearch, google, bing, duckduckgoapi_integrationThird-party API communicationapi, rest, graphql, webhook, {service-name}data_extractionParse and extract structured dataparse, extract, scrape, ocr, pdfdata_transformationConvert, clean, transform datatransform, convert, format, clean, etlcontent_generationCreate text, images, or other contentgenerate, write, create, summarize, translatefile_operationsRead, write, manipulate filesfile, read, write, csv, excel, json, pdfmessage_deliverySend notifications or messagesnotify, send, email, slack, discord, telegramschedulingTime-based task executionschedule, cron, timer, daily, weeklyauthenticationIdentity and access managementauth, oauth, login, token, credentialsdatabase_operationsDatabase CRUD operationsdatabase, sql, mongodb, query, storecode_executionRun scripts or programsexecute, run, script, shell, pythonversion_controlGit and code repository operationsgit, github, gitlab, commit, pr, reviewtestingAutomated testing and QAtest, jest, pytest, e2e, unitdeploymentApplication deployment and CI/CDdeploy, docker, kubernetes, ci-cd, releasemonitoringSystem and application monitoringmonitor, alert, log, metrics, health"
      },
      {
        "title": "Capability Identification Process",
        "body": "For each subtask:\n\nAnalyze the task description and requirements\nMatch to one or more capability types\nGenerate search keywords for skill discovery\n\nExample:\n\nTask: \"Send message to Slack\"\nCapability: message_delivery\nSearch Keywords: [\"slack\", \"notification\", \"message\", \"webhook\"]"
      },
      {
        "title": "Phase 3: Skill Search",
        "body": "Use the Skills CLI to search for existing skills at https://skills.sh/"
      },
      {
        "title": "Search Process",
        "body": "For each capability need, search using relevant keywords:\n\n# Search for skills matching the capability\nnpx skills find <keyword>\n\n# Examples:\nnpx skills find slack notification\nnpx skills find browser automation\nnpx skills find pdf extract\nnpx skills find github api"
      },
      {
        "title": "Evaluate Search Results",
        "body": "When results are returned:\n\nInstall with npx skills add <owner/repo@skill>\n\nowner/repo@skill-name\n└ https://skills.sh/owner/repo/skill-name\n\nEvaluate each result for:\n\nRelevance: Does it match the required capability?\nCompleteness: Does it cover all needed functionality?\nQuality: Is it well-documented and maintained?"
      },
      {
        "title": "Generate Capability Mapping",
        "body": "Capability Mapping:\n  - task_id: 1\n    capability: browser_automation\n    search_query: \"browser email automation\"\n    found_skills:\n      - name: \"anthropic/claude-skills@browser-use\"\n        url: \"https://skills.sh/anthropic/claude-skills/browser-use\"\n        match_score: high\n    recommendation: \"Install browser-use skill\"\n    \n  - task_id: 4\n    capability: message_delivery\n    search_query: \"slack notification\"\n    found_skills: []\n    recommendation: \"Create new skill: slack-notification\""
      },
      {
        "title": "Phase 4: Gap Analysis",
        "body": "Identify tasks without matching skills:"
      },
      {
        "title": "Built-in Capabilities (No Skill Needed)",
        "body": "These capabilities are typically handled by the agent's native abilities:\n\ncontent_generation - LLM's native text generation\ndata_transformation - Basic data manipulation via code\ncode_execution - Direct script execution\nscheduling - System-level cron/scheduler configuration"
      },
      {
        "title": "Skills Required",
        "body": "For capabilities without built-in support, determine:\n\nSkill exists: Install from skills.sh\nSkill not found: Create new skill"
      },
      {
        "title": "Phase 5: Skill Creation",
        "body": "When no existing skill matches a required capability, create a new skill."
      },
      {
        "title": "Skill Creation Process",
        "body": "Define scope: Determine what the skill should do\nDesign interface: Define inputs, outputs, and usage patterns\nCreate SKILL.md: Write the skill definition file\nAdd resources: Include scripts, references, or assets as needed"
      },
      {
        "title": "Skill Template",
        "body": "---\nname: {skill-name}\ndescription: {Clear description of what the skill does and when to use it. Written in third person.}\n---\n\n# {Skill Title}\n\n{Brief introduction explaining the skill's purpose.}\n\n## When to Use\n\n{Describe scenarios when this skill should be triggered.}\n\n## Prerequisites\n\n{List any required installations, configurations, or credentials.}\n\n## Usage\n\n{Detailed usage instructions with examples.}\n\n### Basic Usage\n\n```bash\n{Basic command or code example}"
      },
      {
        "title": "Advanced Usage",
        "body": "{More complex examples and options.}"
      },
      {
        "title": "Configuration",
        "body": "{Any configuration options or environment variables.}"
      },
      {
        "title": "Example 1: {Use Case}",
        "body": "{Step-by-step example with code.}"
      },
      {
        "title": "Troubleshooting",
        "body": "{Common issues and solutions.}\n\n### Initialize New Skill\n\n```bash\n# Create skill using the skills CLI\nnpx skills init <skill-name>\n\n# Or manually create the structure:\n# skill-name/\n# ├── SKILL.md (required)\n# ├── scripts/ (optional)\n# ├── references/ (optional)\n# └── assets/ (optional)"
      },
      {
        "title": "Phase 6: Generate Execution Plan",
        "body": "Compile all information into a structured execution plan:\n\nExecution Plan:\n  title: \"{Task Description}\"\n  \n  prerequisites:\n    - \"{Prerequisite 1}\"\n    - \"{Prerequisite 2}\"\n  \n  skills_to_install:\n    - skill: \"owner/repo@skill-name\"\n      command: \"npx skills add owner/repo@skill-name -g -y\"\n      url: \"https://skills.sh/owner/repo/skill-name\"\n  \n  skills_to_create:\n    - name: \"{new-skill-name}\"\n      capability: \"{capability_type}\"\n      description: \"{What it does}\"\n  \n  execution_steps:\n    - step: 1\n      task: \"{Task name}\"\n      skill: \"{skill-name | built-in}\"\n      action: \"{Specific action to take}\"\n      \n    - step: 2\n      task: \"{Task name}\"\n      skill: \"{skill-name | built-in}\"\n      action: \"{Specific action to take}\"\n  \n  verification:\n    - \"{How to verify step 1 succeeded}\"\n    - \"{How to verify step 2 succeeded}\""
      },
      {
        "title": "Principle 1: Atomicity",
        "body": "Each subtask should be the minimal executable unit with clear input and output."
      },
      {
        "title": "Principle 2: Independence",
        "body": "Minimize dependencies between tasks to allow parallel execution where possible."
      },
      {
        "title": "Principle 3: Verifiability",
        "body": "Each task should have a clear way to verify successful completion."
      },
      {
        "title": "Principle 4: Reusability",
        "body": "Identify reusable patterns and prefer creating general-purpose skills."
      },
      {
        "title": "Principle 5: Single Responsibility",
        "body": "Each task should do one thing well."
      },
      {
        "title": "Output Format",
        "body": "Present the decomposition results in a structured format:\n\n════════════════════════════════════════════════════════════════\n📋 TASK DECOMPOSITION REPORT\n════════════════════════════════════════════════════════════════\n\n🎯 Original Request:\n{User's original request}\n\n────────────────────────────────────────────────────────────────\n📊 SUBTASKS\n────────────────────────────────────────────────────────────────\n┌─────┬────────────────────────┬───────────────────┬───────────┐\n│ ID  │ Task                   │ Capability        │ Status    │\n├─────┼────────────────────────┼───────────────────┼───────────┤\n│ 1   │ {task name}            │ {capability}      │ Found     │\n│ 2   │ {task name}            │ {capability}      │ Built-in  │\n│ 3   │ {task name}            │ {capability}      │ Create    │\n└─────┴────────────────────────┴───────────────────┴───────────┘\n\n────────────────────────────────────────────────────────────────\n🔍 SKILL SEARCH RESULTS\n────────────────────────────────────────────────────────────────\nTask 1: {task name}\n  Search: npx skills find {keywords}\n  Found: owner/repo@skill-name\n  URL: https://skills.sh/owner/repo/skill-name\n  \nTask 3: {task name}\n  Search: npx skills find {keywords}\n  Found: No matching skills\n  Action: Create new skill\n\n────────────────────────────────────────────────────────────────\n🛠️ SKILLS TO CREATE\n────────────────────────────────────────────────────────────────\n1. {skill-name}\n   Capability: {capability_type}\n   Description: {what it does}\n\n────────────────────────────────────────────────────────────────\n📝 EXECUTION PLAN\n────────────────────────────────────────────────────────────────\nPrerequisites:\n  • {prerequisite 1}\n  • {prerequisite 2}\n\nSteps:\n  1. {action} using {skill}\n  2. {action} using {skill}\n  3. {action} using {skill}\n\n════════════════════════════════════════════════════════════════"
      },
      {
        "title": "Example 1: Workflow Automation",
        "body": "User Request:\n\nCreate a workflow that monitors GitHub issues, summarizes new issues, and posts notifications to Discord\n\nDecomposition:\n\nSubtasks:\n  1. Monitor GitHub repository for new issues\n     Capability: api_integration\n     Search: \"npx skills find github issues\"\n     \n  2. Extract issue content and metadata\n     Capability: data_extraction\n     Status: Built-in (code)\n     \n  3. Generate issue summary\n     Capability: content_generation\n     Status: Built-in (LLM)\n     \n  4. Send notification to Discord\n     Capability: message_delivery\n     Search: \"npx skills find discord notification\"\n     \n  5. Configure webhook or polling trigger\n     Capability: scheduling\n     Status: Built-in (system)"
      },
      {
        "title": "Example 2: Data Pipeline",
        "body": "User Request:\n\nSearch for AI research papers, download PDFs, extract key findings, and save to Notion\n\nDecomposition:\n\nSubtasks:\n  1. Search for AI research papers\n     Capability: web_search\n     Search: \"npx skills find academic search\"\n     \n  2. Download PDF files\n     Capability: browser_automation\n     Search: \"npx skills find browser download\"\n     \n  3. Extract text from PDFs\n     Capability: data_extraction\n     Search: \"npx skills find pdf extract\"\n     \n  4. Generate summaries of key findings\n     Capability: content_generation\n     Status: Built-in (LLM)\n     \n  5. Save to Notion database\n     Capability: api_integration\n     Search: \"npx skills find notion\""
      },
      {
        "title": "Best Practices",
        "body": "Start with skill search: Always check https://skills.sh/ before creating new skills\nUse specific search terms: Combine capability keywords with domain terms\nLeverage built-in capabilities: Don't create skills for things the agent can do natively\nCreate reusable skills: Design new skills to be general-purpose when possible\nDocument thoroughly: New skills should have clear usage instructions\nVerify before proceeding: Confirm skill installation before executing tasks\nHandle errors gracefully: Include fallback strategies in execution plans"
      },
      {
        "title": "Integration with find-skills",
        "body": "This skill works in conjunction with the find-skills skill for discovering existing solutions:\n\n# Search the skills ecosystem\nnpx skills find <query>\n\n# Install a discovered skill\nnpx skills add <owner/repo@skill> -g -y\n\n# Browse all available skills\n# Visit: https://skills.sh/"
      },
      {
        "title": "Notes",
        "body": "Always search for existing skills before creating new ones\nBuilt-in capabilities (LLM, basic code) don't require skills\nSkill creation requires user confirmation before proceeding\nComplex workflows may need multiple skills working together"
      }
    ],
    "body": "Task Decomposer & Skill Generator\n\nThis skill helps decompose complex user requests into executable subtasks, identify required capabilities for each task, search for existing skills from the open skills ecosystem, and automatically create new skills when no existing solution is available.\n\nCore Workflow\nUser Request → Task Decomposition → Capability Identification → Skill Search → Gap Analysis → Skill Creation → Execution Plan\n\nPhase 1: Task Analysis & Decomposition\n\nWhen receiving a user request, follow these steps:\n\nStep 1: Understand User Intent\n\nAnalyze the request to identify:\n\nCore objective: What is the end goal?\nDomains involved: What areas of expertise are needed?\nTrigger mechanism: One-time, scheduled, or event-driven?\n\nExample analysis:\n\nUser Input: \"Help me get email summaries every morning and send them to Slack\"\n\nAnalysis:\n- Core objective: Automated email digest delivery to Slack\n- Domains: Email access, content summarization, messaging\n- Trigger: Scheduled (daily morning)\n\nStep 2: Decompose into Atomic Tasks\n\nBreak down the complex task into minimal executable units:\n\nTask Decomposition:\n  - task_id: 1\n    name: \"Access and retrieve email list\"\n    type: \"data_retrieval\"\n    input: \"Email credentials/session\"\n    output: \"List of emails with metadata\"\n    dependencies: []\n    \n  - task_id: 2\n    name: \"Extract key information from emails\"\n    type: \"data_extraction\"\n    input: \"Email list\"\n    output: \"Structured email data\"\n    dependencies: [1]\n    \n  - task_id: 3\n    name: \"Generate email summary\"\n    type: \"content_generation\"\n    input: \"Structured email data\"\n    output: \"Formatted summary text\"\n    dependencies: [2]\n    \n  - task_id: 4\n    name: \"Send message to Slack\"\n    type: \"message_delivery\"\n    input: \"Summary text, Slack webhook/token\"\n    output: \"Delivery confirmation\"\n    dependencies: [3]\n    \n  - task_id: 5\n    name: \"Configure scheduled execution\"\n    type: \"scheduling\"\n    input: \"Workflow script, schedule config\"\n    output: \"Active scheduled job\"\n    dependencies: [4]\n\nPhase 2: Capability Identification\n\nMap each subtask to a capability type from the universal capability taxonomy.\n\nUniversal Capability Types\nCapability\tDescription\tSearch Keywords\nbrowser_automation\tWeb navigation, interaction, scraping\tbrowser, selenium, puppeteer, playwright, scrape\nweb_search\tInternet search and information retrieval\tsearch, google, bing, duckduckgo\napi_integration\tThird-party API communication\tapi, rest, graphql, webhook, {service-name}\ndata_extraction\tParse and extract structured data\tparse, extract, scrape, ocr, pdf\ndata_transformation\tConvert, clean, transform data\ttransform, convert, format, clean, etl\ncontent_generation\tCreate text, images, or other content\tgenerate, write, create, summarize, translate\nfile_operations\tRead, write, manipulate files\tfile, read, write, csv, excel, json, pdf\nmessage_delivery\tSend notifications or messages\tnotify, send, email, slack, discord, telegram\nscheduling\tTime-based task execution\tschedule, cron, timer, daily, weekly\nauthentication\tIdentity and access management\tauth, oauth, login, token, credentials\ndatabase_operations\tDatabase CRUD operations\tdatabase, sql, mongodb, query, store\ncode_execution\tRun scripts or programs\texecute, run, script, shell, python\nversion_control\tGit and code repository operations\tgit, github, gitlab, commit, pr, review\ntesting\tAutomated testing and QA\ttest, jest, pytest, e2e, unit\ndeployment\tApplication deployment and CI/CD\tdeploy, docker, kubernetes, ci-cd, release\nmonitoring\tSystem and application monitoring\tmonitor, alert, log, metrics, health\nCapability Identification Process\n\nFor each subtask:\n\nAnalyze the task description and requirements\nMatch to one or more capability types\nGenerate search keywords for skill discovery\n\nExample:\n\nTask: \"Send message to Slack\"\nCapability: message_delivery\nSearch Keywords: [\"slack\", \"notification\", \"message\", \"webhook\"]\n\nPhase 3: Skill Search\n\nUse the Skills CLI to search for existing skills at https://skills.sh/\n\nSearch Process\n\nFor each capability need, search using relevant keywords:\n\n# Search for skills matching the capability\nnpx skills find <keyword>\n\n# Examples:\nnpx skills find slack notification\nnpx skills find browser automation\nnpx skills find pdf extract\nnpx skills find github api\n\nEvaluate Search Results\n\nWhen results are returned:\n\nInstall with npx skills add <owner/repo@skill>\n\nowner/repo@skill-name\n└ https://skills.sh/owner/repo/skill-name\n\n\nEvaluate each result for:\n\nRelevance: Does it match the required capability?\nCompleteness: Does it cover all needed functionality?\nQuality: Is it well-documented and maintained?\nGenerate Capability Mapping\nCapability Mapping:\n  - task_id: 1\n    capability: browser_automation\n    search_query: \"browser email automation\"\n    found_skills:\n      - name: \"anthropic/claude-skills@browser-use\"\n        url: \"https://skills.sh/anthropic/claude-skills/browser-use\"\n        match_score: high\n    recommendation: \"Install browser-use skill\"\n    \n  - task_id: 4\n    capability: message_delivery\n    search_query: \"slack notification\"\n    found_skills: []\n    recommendation: \"Create new skill: slack-notification\"\n\nPhase 4: Gap Analysis\n\nIdentify tasks without matching skills:\n\nBuilt-in Capabilities (No Skill Needed)\n\nThese capabilities are typically handled by the agent's native abilities:\n\ncontent_generation - LLM's native text generation\ndata_transformation - Basic data manipulation via code\ncode_execution - Direct script execution\nscheduling - System-level cron/scheduler configuration\nSkills Required\n\nFor capabilities without built-in support, determine:\n\nSkill exists: Install from skills.sh\nSkill not found: Create new skill\nPhase 5: Skill Creation\n\nWhen no existing skill matches a required capability, create a new skill.\n\nSkill Creation Process\nDefine scope: Determine what the skill should do\nDesign interface: Define inputs, outputs, and usage patterns\nCreate SKILL.md: Write the skill definition file\nAdd resources: Include scripts, references, or assets as needed\nSkill Template\n---\nname: {skill-name}\ndescription: {Clear description of what the skill does and when to use it. Written in third person.}\n---\n\n# {Skill Title}\n\n{Brief introduction explaining the skill's purpose.}\n\n## When to Use\n\n{Describe scenarios when this skill should be triggered.}\n\n## Prerequisites\n\n{List any required installations, configurations, or credentials.}\n\n## Usage\n\n{Detailed usage instructions with examples.}\n\n### Basic Usage\n\n```bash\n{Basic command or code example}\n\nAdvanced Usage\n\n{More complex examples and options.}\n\nConfiguration\n\n{Any configuration options or environment variables.}\n\nExamples\nExample 1: {Use Case}\n\n{Step-by-step example with code.}\n\nTroubleshooting\n\n{Common issues and solutions.}\n\n\n### Initialize New Skill\n\n```bash\n# Create skill using the skills CLI\nnpx skills init <skill-name>\n\n# Or manually create the structure:\n# skill-name/\n# ├── SKILL.md (required)\n# ├── scripts/ (optional)\n# ├── references/ (optional)\n# └── assets/ (optional)\n\nPhase 6: Generate Execution Plan\n\nCompile all information into a structured execution plan:\n\nExecution Plan:\n  title: \"{Task Description}\"\n  \n  prerequisites:\n    - \"{Prerequisite 1}\"\n    - \"{Prerequisite 2}\"\n  \n  skills_to_install:\n    - skill: \"owner/repo@skill-name\"\n      command: \"npx skills add owner/repo@skill-name -g -y\"\n      url: \"https://skills.sh/owner/repo/skill-name\"\n  \n  skills_to_create:\n    - name: \"{new-skill-name}\"\n      capability: \"{capability_type}\"\n      description: \"{What it does}\"\n  \n  execution_steps:\n    - step: 1\n      task: \"{Task name}\"\n      skill: \"{skill-name | built-in}\"\n      action: \"{Specific action to take}\"\n      \n    - step: 2\n      task: \"{Task name}\"\n      skill: \"{skill-name | built-in}\"\n      action: \"{Specific action to take}\"\n  \n  verification:\n    - \"{How to verify step 1 succeeded}\"\n    - \"{How to verify step 2 succeeded}\"\n\nTask Decomposition Principles\nPrinciple 1: Atomicity\n\nEach subtask should be the minimal executable unit with clear input and output.\n\nPrinciple 2: Independence\n\nMinimize dependencies between tasks to allow parallel execution where possible.\n\nPrinciple 3: Verifiability\n\nEach task should have a clear way to verify successful completion.\n\nPrinciple 4: Reusability\n\nIdentify reusable patterns and prefer creating general-purpose skills.\n\nPrinciple 5: Single Responsibility\n\nEach task should do one thing well.\n\nOutput Format\n\nPresent the decomposition results in a structured format:\n\n════════════════════════════════════════════════════════════════\n📋 TASK DECOMPOSITION REPORT\n════════════════════════════════════════════════════════════════\n\n🎯 Original Request:\n{User's original request}\n\n────────────────────────────────────────────────────────────────\n📊 SUBTASKS\n────────────────────────────────────────────────────────────────\n┌─────┬────────────────────────┬───────────────────┬───────────┐\n│ ID  │ Task                   │ Capability        │ Status    │\n├─────┼────────────────────────┼───────────────────┼───────────┤\n│ 1   │ {task name}            │ {capability}      │ Found     │\n│ 2   │ {task name}            │ {capability}      │ Built-in  │\n│ 3   │ {task name}            │ {capability}      │ Create    │\n└─────┴────────────────────────┴───────────────────┴───────────┘\n\n────────────────────────────────────────────────────────────────\n🔍 SKILL SEARCH RESULTS\n────────────────────────────────────────────────────────────────\nTask 1: {task name}\n  Search: npx skills find {keywords}\n  Found: owner/repo@skill-name\n  URL: https://skills.sh/owner/repo/skill-name\n  \nTask 3: {task name}\n  Search: npx skills find {keywords}\n  Found: No matching skills\n  Action: Create new skill\n\n────────────────────────────────────────────────────────────────\n🛠️ SKILLS TO CREATE\n────────────────────────────────────────────────────────────────\n1. {skill-name}\n   Capability: {capability_type}\n   Description: {what it does}\n\n────────────────────────────────────────────────────────────────\n📝 EXECUTION PLAN\n────────────────────────────────────────────────────────────────\nPrerequisites:\n  • {prerequisite 1}\n  • {prerequisite 2}\n\nSteps:\n  1. {action} using {skill}\n  2. {action} using {skill}\n  3. {action} using {skill}\n\n════════════════════════════════════════════════════════════════\n\nExamples\nExample 1: Workflow Automation\n\nUser Request:\n\nCreate a workflow that monitors GitHub issues, summarizes new issues, and posts notifications to Discord\n\n\nDecomposition:\n\nSubtasks:\n  1. Monitor GitHub repository for new issues\n     Capability: api_integration\n     Search: \"npx skills find github issues\"\n     \n  2. Extract issue content and metadata\n     Capability: data_extraction\n     Status: Built-in (code)\n     \n  3. Generate issue summary\n     Capability: content_generation\n     Status: Built-in (LLM)\n     \n  4. Send notification to Discord\n     Capability: message_delivery\n     Search: \"npx skills find discord notification\"\n     \n  5. Configure webhook or polling trigger\n     Capability: scheduling\n     Status: Built-in (system)\n\nExample 2: Data Pipeline\n\nUser Request:\n\nSearch for AI research papers, download PDFs, extract key findings, and save to Notion\n\n\nDecomposition:\n\nSubtasks:\n  1. Search for AI research papers\n     Capability: web_search\n     Search: \"npx skills find academic search\"\n     \n  2. Download PDF files\n     Capability: browser_automation\n     Search: \"npx skills find browser download\"\n     \n  3. Extract text from PDFs\n     Capability: data_extraction\n     Search: \"npx skills find pdf extract\"\n     \n  4. Generate summaries of key findings\n     Capability: content_generation\n     Status: Built-in (LLM)\n     \n  5. Save to Notion database\n     Capability: api_integration\n     Search: \"npx skills find notion\"\n\nBest Practices\nStart with skill search: Always check https://skills.sh/ before creating new skills\nUse specific search terms: Combine capability keywords with domain terms\nLeverage built-in capabilities: Don't create skills for things the agent can do natively\nCreate reusable skills: Design new skills to be general-purpose when possible\nDocument thoroughly: New skills should have clear usage instructions\nVerify before proceeding: Confirm skill installation before executing tasks\nHandle errors gracefully: Include fallback strategies in execution plans\nIntegration with find-skills\n\nThis skill works in conjunction with the find-skills skill for discovering existing solutions:\n\n# Search the skills ecosystem\nnpx skills find <query>\n\n# Install a discovered skill\nnpx skills add <owner/repo@skill> -g -y\n\n# Browse all available skills\n# Visit: https://skills.sh/\n\nNotes\nAlways search for existing skills before creating new ones\nBuilt-in capabilities (LLM, basic code) don't require skills\nSkill creation requires user confirmation before proceeding\nComplex workflows may need multiple skills working together"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/10e9928a/super-skills",
    "publisherUrl": "https://clawhub.ai/10e9928a/super-skills",
    "owner": "10e9928a",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/super-skills",
    "downloadUrl": "https://openagent3.xyz/downloads/super-skills",
    "agentUrl": "https://openagent3.xyz/skills/super-skills/agent",
    "manifestUrl": "https://openagent3.xyz/skills/super-skills/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/super-skills/agent.md"
  }
}