{
  "schemaVersion": "1.0",
  "item": {
    "slug": "claude-optimised",
    "name": "OpenClaw Optimised",
    "source": "tencent",
    "type": "skill",
    "category": "内容创作",
    "sourceUrl": "https://clawhub.ai/hexnickk/claude-optimised",
    "canonicalUrl": "https://clawhub.ai/hexnickk/claude-optimised",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/claude-optimised",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=claude-optimised",
    "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": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/claude-optimised"
    },
    "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/claude-optimised",
    "agentPageUrl": "https://openagent3.xyz/skills/claude-optimised/agent",
    "manifestUrl": "https://openagent3.xyz/skills/claude-optimised/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/claude-optimised/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": "CLAUDE.md Optimization Guide",
        "body": "Write CLAUDE.md files that maximize Claude's adherence and performance."
      },
      {
        "title": "Core Principle: Less Is More",
        "body": "Long CLAUDE.md = Claude ignores half of it. Critical rules get lost in noise.\n\nFor each line ask: \"Would removing this cause Claude to make mistakes?\"\n\nIf no → delete it\nIf Claude already does it correctly → delete it or convert to hook"
      },
      {
        "title": "Essential (High Value)",
        "body": "SectionExampleProject context\"Next.js e-commerce app with Stripe\" (1 line)Build/test commandsnpm run test, pnpm buildCritical gotchas\"Never modify auth.ts directly\"Non-obvious conventions\"Use vi for state, not useState\"Domain terminology\"PO = Purchase Order, not Product Owner\""
      },
      {
        "title": "Include Only If Non-Standard",
        "body": "Branch naming (if not feature/, fix/)\nCommit format (if not conventional commits)\nFile boundaries (sensitive files to avoid)"
      },
      {
        "title": "Do NOT Include",
        "body": "Things Claude already knows (general coding practices)\nObvious patterns (detectable from existing code)\nLengthy explanations (be terse)\nAspirational rules (only real problems you've hit)"
      },
      {
        "title": "Structure",
        "body": "# Project Name\n\nOne-line description.\n\n## Commands\n- Test: `npm test`\n- Build: `npm run build`\n- Lint: `npm run lint`\n\n## Code Style\n- [Only non-obvious conventions]\n\n## Architecture\n- [Brief, only if complex]\n\n## IMPORTANT\n- [Critical warnings - use sparingly]"
      },
      {
        "title": "Formatting Rules",
        "body": "Bullet points over paragraphs\nMarkdown headings to separate modules (prevents instruction bleed)\nSpecific over vague: \"2-space indent\" not \"format properly\"\nIMPORTANT/YOU MUST for critical rules (use sparingly or loses effect)"
      },
      {
        "title": "File Placement",
        "body": "LocationScope~/.claude/CLAUDE.mdAll sessions (user prefs)./CLAUDE.mdProject root (share via git)./subdir/CLAUDE.mdLoaded when working in subdir.claude/rules/*.mdAuto-loaded as project memory"
      },
      {
        "title": "Optimization Checklist",
        "body": "Before finalizing:\n\nUnder 50 lines? (ideal target)\n Every line solves a real problem you've encountered?\n No redundancy with other CLAUDE.md locations?\n No instructions Claude follows by default?\n Tested by observing if Claude's behavior changes?"
      },
      {
        "title": "Maintenance",
        "body": "Run /init as starting point, then prune aggressively\nEvery few weeks: \"Review this CLAUDE.md and suggest removals\"\nWhen Claude misbehaves: add specific rule\nWhen Claude ignores rules: file too long, prune other content"
      },
      {
        "title": "Anti-Patterns",
        "body": "Don'tWhy200+ line CLAUDE.mdGets ignored\"Write clean code\"Claude knows thisDuplicate rules across filesWastes tokens, conflictsTheoretical concernsOnly add for real problemsLong prose explanationsUse bullet points"
      },
      {
        "title": "Example: Minimal Effective CLAUDE.md",
        "body": "# MyApp\n\nReact Native app with Expo. Backend is Supabase.\n\n## Commands\n- `pnpm test` - run tests\n- `pnpm ios` - run iOS simulator\n\n## Style\n- Prefer Zustand over Context\n- Use `clsx` for conditional classes\n\n## IMPORTANT\n- NEVER commit .env files\n- Auth logic lives in src/lib/auth.ts only\n\n~15 lines. Covers what Claude can't infer. Nothing more."
      }
    ],
    "body": "CLAUDE.md Optimization Guide\n\nWrite CLAUDE.md files that maximize Claude's adherence and performance.\n\nCore Principle: Less Is More\n\nLong CLAUDE.md = Claude ignores half of it. Critical rules get lost in noise.\n\nFor each line ask: \"Would removing this cause Claude to make mistakes?\"\n\nIf no → delete it\nIf Claude already does it correctly → delete it or convert to hook\nWhat to Include\nEssential (High Value)\nSection\tExample\nProject context\t\"Next.js e-commerce app with Stripe\" (1 line)\nBuild/test commands\tnpm run test, pnpm build\nCritical gotchas\t\"Never modify auth.ts directly\"\nNon-obvious conventions\t\"Use vi for state, not useState\"\nDomain terminology\t\"PO = Purchase Order, not Product Owner\"\nInclude Only If Non-Standard\nBranch naming (if not feature/, fix/)\nCommit format (if not conventional commits)\nFile boundaries (sensitive files to avoid)\nDo NOT Include\nThings Claude already knows (general coding practices)\nObvious patterns (detectable from existing code)\nLengthy explanations (be terse)\nAspirational rules (only real problems you've hit)\nStructure\n# Project Name\n\nOne-line description.\n\n## Commands\n- Test: `npm test`\n- Build: `npm run build`\n- Lint: `npm run lint`\n\n## Code Style\n- [Only non-obvious conventions]\n\n## Architecture\n- [Brief, only if complex]\n\n## IMPORTANT\n- [Critical warnings - use sparingly]\n\nFormatting Rules\nBullet points over paragraphs\nMarkdown headings to separate modules (prevents instruction bleed)\nSpecific over vague: \"2-space indent\" not \"format properly\"\nIMPORTANT/YOU MUST for critical rules (use sparingly or loses effect)\nFile Placement\nLocation\tScope\n~/.claude/CLAUDE.md\tAll sessions (user prefs)\n./CLAUDE.md\tProject root (share via git)\n./subdir/CLAUDE.md\tLoaded when working in subdir\n.claude/rules/*.md\tAuto-loaded as project memory\nOptimization Checklist\n\nBefore finalizing:\n\n Under 50 lines? (ideal target)\n Every line solves a real problem you've encountered?\n No redundancy with other CLAUDE.md locations?\n No instructions Claude follows by default?\n Tested by observing if Claude's behavior changes?\nMaintenance\nRun /init as starting point, then prune aggressively\nEvery few weeks: \"Review this CLAUDE.md and suggest removals\"\nWhen Claude misbehaves: add specific rule\nWhen Claude ignores rules: file too long, prune other content\nAnti-Patterns\nDon't\tWhy\n200+ line CLAUDE.md\tGets ignored\n\"Write clean code\"\tClaude knows this\nDuplicate rules across files\tWastes tokens, conflicts\nTheoretical concerns\tOnly add for real problems\nLong prose explanations\tUse bullet points\nExample: Minimal Effective CLAUDE.md\n# MyApp\n\nReact Native app with Expo. Backend is Supabase.\n\n## Commands\n- `pnpm test` - run tests\n- `pnpm ios` - run iOS simulator\n\n## Style\n- Prefer Zustand over Context\n- Use `clsx` for conditional classes\n\n## IMPORTANT\n- NEVER commit .env files\n- Auth logic lives in src/lib/auth.ts only\n\n\n~15 lines. Covers what Claude can't infer. Nothing more."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/hexnickk/claude-optimised",
    "publisherUrl": "https://clawhub.ai/hexnickk/claude-optimised",
    "owner": "hexnickk",
    "version": "1.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/claude-optimised",
    "downloadUrl": "https://openagent3.xyz/downloads/claude-optimised",
    "agentUrl": "https://openagent3.xyz/skills/claude-optimised/agent",
    "manifestUrl": "https://openagent3.xyz/skills/claude-optimised/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/claude-optimised/agent.md"
  }
}