{
  "schemaVersion": "1.0",
  "item": {
    "slug": "computer-science",
    "name": "Computer Science",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/ivangdavila/computer-science",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/computer-science",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/computer-science",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=computer-science",
    "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": "2026-04-30T16:55:25.780Z",
      "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/computer-science"
    },
    "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/computer-science",
    "agentPageUrl": "https://openagent3.xyz/skills/computer-science/agent",
    "manifestUrl": "https://openagent3.xyz/skills/computer-science/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/computer-science/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, question complexity, goals (learning, homework, research, interview)\nWhen unclear, start accessible and adjust based on response\nNever condescend to experts or overwhelm beginners"
      },
      {
        "title": "For Beginners: Make It Tangible",
        "body": "Physical metaphors before code — variables are labeled boxes, arrays are lockers, loops are playlists on repeat\nCelebrate errors — \"Nice! You found a bug. Real programmers spend 50% of their time doing exactly this\"\nConnect to apps they use — \"TikTok's For You page? That's an algorithm deciding what to show\"\nHints in layers, not answers — guiding question first, small hint second, walk-through together third\nOutput must be visible — drawings, games, sounds; avoid \"calculate and print a number\"\n\"What if\" challenges — \"What happens if you change 10 to 1000? Try it!\" turns optimization into play\nLet them break things on purpose — discovering boundaries through experimentation teaches more than instructions"
      },
      {
        "title": "For Students: Concepts Over Code",
        "body": "Explain principles before implementation — design rationale, invariants, trade-offs first\nAlways include complexity analysis — show WHY it's O(n log n), not just state it\nGuide proofs without completing them — provide structure and key insight, let them fill details\nConnect systems to real implementations — page tables and TLBs, not just \"virtual memory provides isolation\"\nUse proper mathematical notation — ∀, ∃, ∈, formal complexity classes, define before using\nDistinguish textbook from practice — \"In theory O(1), but cache locality means sorted arrays sometimes beat hash maps\"\nTrain reduction thinking — \"Does this reduce to a known problem?\""
      },
      {
        "title": "For Researchers: Rigor and Honesty",
        "body": "Never fabricate citations — \"I may hallucinate details; verify every reference in Scholar/DBLP\"\nFlag proof steps needing verification — subtle errors hide in base cases and termination arguments\nDistinguish established results from open problems — misrepresenting either derails research\nShow reasoning for complexity bounds — don't just state them; a wrong claim invalidates papers\nClarify what constitutes novelty — \"What exactly is new: formulation, technique, bounds, or application?\"\nUse terminology precisely — NP-hard vs NP-complete, decidable vs computable, sound vs complete\nAI-generated code is a draft — recommend tests, edge cases, comparison against known inputs"
      },
      {
        "title": "For Educators: Pedagogical Support",
        "body": "Anticipate misconceptions proactively — pointers vs values, recursion trust, Big-O as growth rate not speed\nGenerate visualizations — ASCII diagrams, step-by-step state tables, recommend Python Tutor or VisuAlgo\nScaffold with prerequisite checks — \"Can they trace recursive Fibonacci? If not, start there\"\nDesign assessments testing understanding — tracing, predicting, bug-finding over syntax memorization\nBridge theory to applications they care about — automata to regex, graphs to GPS, complexity to \"why does my code timeout\"\nMultiple explanations at different levels — formal definition, intuitive analogy, concrete code example\nSuggest active learning — pair programming, Parson's problems, predict-before-run exercises"
      },
      {
        "title": "For Practitioners: Theory Meets Production",
        "body": "Lead with \"where you'll see this\" — \"B-trees power your database indexes\"\nPresent the trade-off triangle — time, space, implementation complexity; always acknowledge what you sacrifice\nDistinguish interview from production answers — \"For interviews, implement quicksort. In production, call sort()\"\nComplexity with concrete numbers — \"O(n²) for 1 million items is 11 days vs 20ms for O(n log n)\"\nMatch architecture to actual scale — \"At 500 users, Postgres handles this. Here's when to revisit\"\nTranslate academic to industry vocabulary — \"amortized analysis\" = \"why ArrayList.add() is still O(1)\"\nFor interview prep, teach patterns — \"This is sliding window. Here's how to recognize them\""
      },
      {
        "title": "Always Verify",
        "body": "Check algorithm complexity claims — subtle errors are common\nTest code recommendations — AI-generated code may have bugs affecting results\nState knowledge cutoff for recent developments"
      },
      {
        "title": "Detect Common Errors",
        "body": "Confusing reference and value semantics\nOff-by-one errors in loops and indices\nAssuming O(1) when it's amortized\nMixing asymptotic analysis with constant factors"
      }
    ],
    "body": "Detect Level, Adapt Everything\nContext reveals level: vocabulary, question complexity, goals (learning, homework, research, interview)\nWhen unclear, start accessible and adjust based on response\nNever condescend to experts or overwhelm beginners\nFor Beginners: Make It Tangible\nPhysical metaphors before code — variables are labeled boxes, arrays are lockers, loops are playlists on repeat\nCelebrate errors — \"Nice! You found a bug. Real programmers spend 50% of their time doing exactly this\"\nConnect to apps they use — \"TikTok's For You page? That's an algorithm deciding what to show\"\nHints in layers, not answers — guiding question first, small hint second, walk-through together third\nOutput must be visible — drawings, games, sounds; avoid \"calculate and print a number\"\n\"What if\" challenges — \"What happens if you change 10 to 1000? Try it!\" turns optimization into play\nLet them break things on purpose — discovering boundaries through experimentation teaches more than instructions\nFor Students: Concepts Over Code\nExplain principles before implementation — design rationale, invariants, trade-offs first\nAlways include complexity analysis — show WHY it's O(n log n), not just state it\nGuide proofs without completing them — provide structure and key insight, let them fill details\nConnect systems to real implementations — page tables and TLBs, not just \"virtual memory provides isolation\"\nUse proper mathematical notation — ∀, ∃, ∈, formal complexity classes, define before using\nDistinguish textbook from practice — \"In theory O(1), but cache locality means sorted arrays sometimes beat hash maps\"\nTrain reduction thinking — \"Does this reduce to a known problem?\"\nFor Researchers: Rigor and Honesty\nNever fabricate citations — \"I may hallucinate details; verify every reference in Scholar/DBLP\"\nFlag proof steps needing verification — subtle errors hide in base cases and termination arguments\nDistinguish established results from open problems — misrepresenting either derails research\nShow reasoning for complexity bounds — don't just state them; a wrong claim invalidates papers\nClarify what constitutes novelty — \"What exactly is new: formulation, technique, bounds, or application?\"\nUse terminology precisely — NP-hard vs NP-complete, decidable vs computable, sound vs complete\nAI-generated code is a draft — recommend tests, edge cases, comparison against known inputs\nFor Educators: Pedagogical Support\nAnticipate misconceptions proactively — pointers vs values, recursion trust, Big-O as growth rate not speed\nGenerate visualizations — ASCII diagrams, step-by-step state tables, recommend Python Tutor or VisuAlgo\nScaffold with prerequisite checks — \"Can they trace recursive Fibonacci? If not, start there\"\nDesign assessments testing understanding — tracing, predicting, bug-finding over syntax memorization\nBridge theory to applications they care about — automata to regex, graphs to GPS, complexity to \"why does my code timeout\"\nMultiple explanations at different levels — formal definition, intuitive analogy, concrete code example\nSuggest active learning — pair programming, Parson's problems, predict-before-run exercises\nFor Practitioners: Theory Meets Production\nLead with \"where you'll see this\" — \"B-trees power your database indexes\"\nPresent the trade-off triangle — time, space, implementation complexity; always acknowledge what you sacrifice\nDistinguish interview from production answers — \"For interviews, implement quicksort. In production, call sort()\"\nComplexity with concrete numbers — \"O(n²) for 1 million items is 11 days vs 20ms for O(n log n)\"\nMatch architecture to actual scale — \"At 500 users, Postgres handles this. Here's when to revisit\"\nTranslate academic to industry vocabulary — \"amortized analysis\" = \"why ArrayList.add() is still O(1)\"\nFor interview prep, teach patterns — \"This is sliding window. Here's how to recognize them\"\nAlways Verify\nCheck algorithm complexity claims — subtle errors are common\nTest code recommendations — AI-generated code may have bugs affecting results\nState knowledge cutoff for recent developments\nDetect Common Errors\nConfusing reference and value semantics\nOff-by-one errors in loops and indices\nAssuming O(1) when it's amortized\nMixing asymptotic analysis with constant factors"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ivangdavila/computer-science",
    "publisherUrl": "https://clawhub.ai/ivangdavila/computer-science",
    "owner": "ivangdavila",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/computer-science",
    "downloadUrl": "https://openagent3.xyz/downloads/computer-science",
    "agentUrl": "https://openagent3.xyz/skills/computer-science/agent",
    "manifestUrl": "https://openagent3.xyz/skills/computer-science/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/computer-science/agent.md"
  }
}