{
  "schemaVersion": "1.0",
  "item": {
    "slug": "coding",
    "name": "Coding",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/ivangdavila/coding",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/coding",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/coding",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=coding",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "criteria.md",
      "dimensions.md",
      "memory-template.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/coding"
    },
    "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/coding",
    "agentPageUrl": "https://openagent3.xyz/skills/coding/agent",
    "manifestUrl": "https://openagent3.xyz/skills/coding/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/coding/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": "When to Use",
        "body": "User has coding style preferences, stack decisions, or patterns they want remembered. Agent learns ONLY from explicit corrections and confirmations, never from observation."
      },
      {
        "title": "Architecture",
        "body": "Memory lives in ~/coding/ with tiered structure. See memory-template.md for setup.\n\n~/coding/\n├── memory.md      # Active preferences (≤100 lines)\n└── history.md     # Archived old preferences"
      },
      {
        "title": "Quick Reference",
        "body": "TopicFileCategories of preferencesdimensions.mdWhen to add preferencescriteria.mdMemory templatesmemory-template.md"
      },
      {
        "title": "Data Storage",
        "body": "All data stored in ~/coding/. Create on first use:\n\nmkdir -p ~/coding"
      },
      {
        "title": "Scope",
        "body": "This skill ONLY:\n\nLearns from explicit user corrections (\"I prefer X over Y\")\nStores preferences in local files (~/coding/)\nApplies stored preferences to code output\n\nThis skill NEVER:\n\nReads project files to infer preferences\nObserves coding patterns without consent\nMakes network requests\nReads files outside ~/coding/\nModifies its own SKILL.md"
      },
      {
        "title": "1. Learn from Explicit Feedback Only",
        "body": "User corrects output → ask: \"Should I remember this preference?\"\nUser confirms → add to ~/coding/memory.md\nNever infer from silence or observation"
      },
      {
        "title": "2. Confirmation Required",
        "body": "No preference is stored without explicit user confirmation:\n\n\"Actually, I prefer X\" → \"Should I remember: prefer X?\"\nUser says yes → store\nUser says no → don't store, don't ask again"
      },
      {
        "title": "3. Ultra-Compact Format",
        "body": "Keep each entry 5 words max:\n\npython: prefer 3.11+\nnaming: snake_case for files\ntests: colocated, not separate folder"
      },
      {
        "title": "4. Category Organization",
        "body": "Group by type (see dimensions.md):\n\nStack — frameworks, databases, tools\nStyle — naming, formatting, comments\nStructure — folders, tests, configs\nNever — explicitly rejected patterns"
      },
      {
        "title": "5. Memory Limits",
        "body": "memory.md ≤100 lines\nWhen full → archive old patterns to history.md\nMerge similar entries: \"no Prettier\" + \"no ESLint\" → \"minimal tooling\""
      },
      {
        "title": "6. On Session Start",
        "body": "Load ~/coding/memory.md if exists\nApply stored preferences to responses\nIf no file exists, start with no assumptions"
      },
      {
        "title": "7. Query Support",
        "body": "User can ask:\n\n\"Show my coding preferences\" → display memory.md\n\"Forget X\" → remove from memory\n\"What do you know about my Python style?\" → show relevant entries"
      },
      {
        "title": "Common Traps",
        "body": "Adding preferences without confirmation → user loses trust\nInferring from project structure → privacy violation\nExceeding 100 lines → context bloat\nVague entries (\"good code\") → useless, be specific"
      },
      {
        "title": "Security & Privacy",
        "body": "Data that stays local:\n\nAll preferences stored in ~/coding/\nNo telemetry or analytics\n\nThis skill does NOT:\n\nSend data externally\nAccess files outside ~/coding/\nObserve without explicit user input"
      },
      {
        "title": "Feedback",
        "body": "If useful: clawhub star coding\nStay updated: clawhub sync"
      }
    ],
    "body": "When to Use\n\nUser has coding style preferences, stack decisions, or patterns they want remembered. Agent learns ONLY from explicit corrections and confirmations, never from observation.\n\nArchitecture\n\nMemory lives in ~/coding/ with tiered structure. See memory-template.md for setup.\n\n~/coding/\n├── memory.md      # Active preferences (≤100 lines)\n└── history.md     # Archived old preferences\n\nQuick Reference\nTopic\tFile\nCategories of preferences\tdimensions.md\nWhen to add preferences\tcriteria.md\nMemory templates\tmemory-template.md\nData Storage\n\nAll data stored in ~/coding/. Create on first use:\n\nmkdir -p ~/coding\n\nScope\n\nThis skill ONLY:\n\nLearns from explicit user corrections (\"I prefer X over Y\")\nStores preferences in local files (~/coding/)\nApplies stored preferences to code output\n\nThis skill NEVER:\n\nReads project files to infer preferences\nObserves coding patterns without consent\nMakes network requests\nReads files outside ~/coding/\nModifies its own SKILL.md\nCore Rules\n1. Learn from Explicit Feedback Only\nUser corrects output → ask: \"Should I remember this preference?\"\nUser confirms → add to ~/coding/memory.md\nNever infer from silence or observation\n2. Confirmation Required\n\nNo preference is stored without explicit user confirmation:\n\n\"Actually, I prefer X\" → \"Should I remember: prefer X?\"\nUser says yes → store\nUser says no → don't store, don't ask again\n3. Ultra-Compact Format\n\nKeep each entry 5 words max:\n\npython: prefer 3.11+\nnaming: snake_case for files\ntests: colocated, not separate folder\n4. Category Organization\n\nGroup by type (see dimensions.md):\n\nStack — frameworks, databases, tools\nStyle — naming, formatting, comments\nStructure — folders, tests, configs\nNever — explicitly rejected patterns\n5. Memory Limits\nmemory.md ≤100 lines\nWhen full → archive old patterns to history.md\nMerge similar entries: \"no Prettier\" + \"no ESLint\" → \"minimal tooling\"\n6. On Session Start\nLoad ~/coding/memory.md if exists\nApply stored preferences to responses\nIf no file exists, start with no assumptions\n7. Query Support\n\nUser can ask:\n\n\"Show my coding preferences\" → display memory.md\n\"Forget X\" → remove from memory\n\"What do you know about my Python style?\" → show relevant entries\nCommon Traps\nAdding preferences without confirmation → user loses trust\nInferring from project structure → privacy violation\nExceeding 100 lines → context bloat\nVague entries (\"good code\") → useless, be specific\nSecurity & Privacy\n\nData that stays local:\n\nAll preferences stored in ~/coding/\nNo telemetry or analytics\n\nThis skill does NOT:\n\nSend data externally\nAccess files outside ~/coding/\nObserve without explicit user input\nFeedback\nIf useful: clawhub star coding\nStay updated: clawhub sync"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ivangdavila/coding",
    "publisherUrl": "https://clawhub.ai/ivangdavila/coding",
    "owner": "ivangdavila",
    "version": "1.0.3",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/coding",
    "downloadUrl": "https://openagent3.xyz/downloads/coding",
    "agentUrl": "https://openagent3.xyz/skills/coding/agent",
    "manifestUrl": "https://openagent3.xyz/skills/coding/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/coding/agent.md"
  }
}