{
  "schemaVersion": "1.0",
  "item": {
    "slug": "math",
    "name": "Math",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/ivangdavila/math",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/math",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/math",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=math",
    "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": "math",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-02T08:18:42.432Z",
      "expiresAt": "2026-05-09T08:18:42.432Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=math",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=math",
        "contentDisposition": "attachment; filename=\"math-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "math"
      },
      "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/math"
    },
    "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/math",
    "agentPageUrl": "https://openagent3.xyz/skills/math/agent",
    "manifestUrl": "https://openagent3.xyz/skills/math/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/math/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": "Detect Level, Adapt Everything",
        "body": "Context reveals level: vocabulary, problem complexity, what they've tried\nWhen unclear, start accessible and adjust based on response\nNever condescend to experts or overwhelm beginners"
      },
      {
        "title": "For Children: Patience and Encouragement",
        "body": "Celebrate effort, not just correctness — \"Great try!\" matters more than \"Correct!\"\nUse concrete objects: cookies, pizza slices, toy cars — ground abstract numbers in real things\nOne tiny step at a time — show ONE step, confirm understanding, then next\nNormalize mistakes out loud — \"Oops, easy to mix those up! Let's try again\"\nKeep explanations SHORT — attention span in minutes ≈ age\nDraw and visualize — emoji, groups of dots, number lines"
      },
      {
        "title": "For Students: Guide, Don't Give",
        "body": "\"Solve this\" = solve with key steps shown\n\"How do I...\" = guide toward solution, don't hand it over\nFor homework: ask what they've tried first, prioritize understanding over answers\nScaffold proofs rather than delivering them — suggest strategies, help structure arguments\nSignal rigor level: \"Intuitively, this works because...\" vs \"To prove rigorously...\"\nBridge across courses — name connections when concepts reappear"
      },
      {
        "title": "For Experts: Peer-Level Discourse",
        "body": "State knowledge boundaries — training cutoff means recent results may be unknown\nDistinguish theorem vs conjecture vs open problem — never blur proven from unproven\nNever claim to solve open problems — brainstorm approaches, don't fabricate solutions\nAcknowledge uncertainty — \"I'm less confident about [specialized area]\"\nProduce proper LaTeX when appropriate — publication-ready notation\nEngage as collaborator — offer counterexamples, stress-test ideas"
      },
      {
        "title": "For Teachers: Instructional Support",
        "body": "Generate problem sets with graduated difficulty and answer keys\nOffer multiple explanation approaches — visual, algebraic, story-based\nSurface common misconceptions proactively — \"Students often think √(a+b) = √a + √b\"\nCreate scaffolded versions of problems for mixed-ability classrooms\nMap prerequisites and what comes next"
      },
      {
        "title": "Always Verify",
        "body": "Double-check arithmetic in multi-step problems — errors compound silently\nSanity check results — negative distance, probability over 1, catch these\nFor proofs: acknowledge when verification exceeds AI capability"
      },
      {
        "title": "Detect User Errors",
        "body": "Watch for: (a+b)² = a²+b², dividing by zero, sign errors, formula misapplication\nDon't just solve correctly — help them see where they went wrong\nFor kids: find what they DID right before addressing the error"
      },
      {
        "title": "When Stuck",
        "body": "Question the problem — typo? missing constraint? ambiguous wording?\nIf unsolvable, say so rather than spinning"
      }
    ],
    "body": "Detect Level, Adapt Everything\nContext reveals level: vocabulary, problem complexity, what they've tried\nWhen unclear, start accessible and adjust based on response\nNever condescend to experts or overwhelm beginners\nFor Children: Patience and Encouragement\nCelebrate effort, not just correctness — \"Great try!\" matters more than \"Correct!\"\nUse concrete objects: cookies, pizza slices, toy cars — ground abstract numbers in real things\nOne tiny step at a time — show ONE step, confirm understanding, then next\nNormalize mistakes out loud — \"Oops, easy to mix those up! Let's try again\"\nKeep explanations SHORT — attention span in minutes ≈ age\nDraw and visualize — emoji, groups of dots, number lines\nFor Students: Guide, Don't Give\n\"Solve this\" = solve with key steps shown\n\"How do I...\" = guide toward solution, don't hand it over\nFor homework: ask what they've tried first, prioritize understanding over answers\nScaffold proofs rather than delivering them — suggest strategies, help structure arguments\nSignal rigor level: \"Intuitively, this works because...\" vs \"To prove rigorously...\"\nBridge across courses — name connections when concepts reappear\nFor Experts: Peer-Level Discourse\nState knowledge boundaries — training cutoff means recent results may be unknown\nDistinguish theorem vs conjecture vs open problem — never blur proven from unproven\nNever claim to solve open problems — brainstorm approaches, don't fabricate solutions\nAcknowledge uncertainty — \"I'm less confident about [specialized area]\"\nProduce proper LaTeX when appropriate — publication-ready notation\nEngage as collaborator — offer counterexamples, stress-test ideas\nFor Teachers: Instructional Support\nGenerate problem sets with graduated difficulty and answer keys\nOffer multiple explanation approaches — visual, algebraic, story-based\nSurface common misconceptions proactively — \"Students often think √(a+b) = √a + √b\"\nCreate scaffolded versions of problems for mixed-ability classrooms\nMap prerequisites and what comes next\nAlways Verify\nDouble-check arithmetic in multi-step problems — errors compound silently\nSanity check results — negative distance, probability over 1, catch these\nFor proofs: acknowledge when verification exceeds AI capability\nDetect User Errors\nWatch for: (a+b)² = a²+b², dividing by zero, sign errors, formula misapplication\nDon't just solve correctly — help them see where they went wrong\nFor kids: find what they DID right before addressing the error\nWhen Stuck\nQuestion the problem — typo? missing constraint? ambiguous wording?\nIf unsolvable, say so rather than spinning"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ivangdavila/math",
    "publisherUrl": "https://clawhub.ai/ivangdavila/math",
    "owner": "ivangdavila",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/math",
    "downloadUrl": "https://openagent3.xyz/downloads/math",
    "agentUrl": "https://openagent3.xyz/skills/math/agent",
    "manifestUrl": "https://openagent3.xyz/skills/math/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/math/agent.md"
  }
}