{
  "schemaVersion": "1.0",
  "item": {
    "slug": "openclaw-knowledge-coach",
    "name": "openclaw-knowledge-coach",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/Sibo-Zhao/openclaw-knowledge-coach",
    "canonicalUrl": "https://clawhub.ai/Sibo-Zhao/openclaw-knowledge-coach",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/openclaw-knowledge-coach",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-knowledge-coach",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/exercise-patterns.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/openclaw-knowledge-coach"
    },
    "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/openclaw-knowledge-coach",
    "agentPageUrl": "https://openagent3.xyz/skills/openclaw-knowledge-coach/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-knowledge-coach/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-knowledge-coach/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": "OpenClaw Knowledge Coach",
        "body": "Create a local knowledge workflow in OpenClaw where importing knowledge also produces practice material for retention. OpenPraxis is on PyPI: use pip install openpraxis to get the praxis CLI."
      },
      {
        "title": "CLI First",
        "body": "Use OpenPraxis CLI as the default execution path.\n\nInstall from PyPI (recommended):\n\npip install openpraxis\npraxis --help\n\nOr install from source for development:\n\ngit clone https://github.com/Sibo-Zhao/OpenPraxis.git\ncd OpenPraxis\npip install -e \".[dev]\"\npraxis --help\n\nConfigure provider/model/API key before ingestion/practice:\n\npraxis llm setup\npraxis llm show\n\nUse environment variables when needed (higher priority than config file):\n\nexport OPENAI_API_KEY=\"your_key_here\"\n# or ARK_API_KEY / MOONSHOT_API_KEY / DEEPSEEK_API_KEY based on provider"
      },
      {
        "title": "Core Workflow",
        "body": "Confirm scope and source\n\nConfirm knowledge domains, source folders, and accepted file types.\nConfirm whether to preserve existing metadata (tags, dates, project names).\n\nDefine import contract\n\nNormalize each source into a record with doc_id, title, source_path, tags, created_at, and content.\nSplit long content into chunks with stable IDs such as doc_id#chunk-001.\n\nImport into OpenClaw\n\nIngest normalized records into the local OpenClaw knowledge base.\nKeep a deterministic mapping between source file and imported IDs for later updates.\n\nGenerate exercises at import time\n\nFor each chunk, create at least one retrieval exercise.\nPrefer three exercise types:\n\nfree-recall: ask the user to explain from memory.\nqa: ask direct question-answer pairs.\napplication: ask scenario-based transfer questions.\n\n\nSave answer keys and concise grading rubrics.\n\nBuild review queue\n\nGroup exercises by topic and difficulty.\nSchedule spaced review windows (for example: day 1, day 3, day 7, day 14).\n\nValidate quality\n\nReject exercises that can be answered without the imported knowledge.\nReject ambiguous or duplicate questions.\nEnsure every exercise points back to doc_id and chunk_id."
      },
      {
        "title": "CLI Command Playbook",
        "body": "Run this sequence when the user asks to import local knowledge and create practice:\n\nAdd a local file\n\npraxis add \"/absolute/path/to/note.md\" --type report\n\nList recent inputs and capture target input_id\n\npraxis list --limit 20\n\nForce-generate a new practice scene for an existing input\n\npraxis practice <input_id>\n\nSubmit answer by file (preferred for deterministic runs)\n\npraxis answer <scene_id> --file \"/absolute/path/to/answer.md\"\n\nInspect pipeline results and insight cards\n\npraxis show <input_id>\npraxis insight <input_id>\n\nExport insights to Markdown/JSON\n\npraxis export --format md --output \"/absolute/path/to/insights.md\"\npraxis export --format json --output \"/absolute/path/to/insights.json\""
      },
      {
        "title": "Agent Execution Rules",
        "body": "Prefer praxis add for import and initial exercise generation.\nParse IDs from CLI output, then chain praxis practice and praxis answer.\nUse praxis answer --file instead of interactive stdin in automation flows.\nIf duplicate content is skipped, rerun with praxis add ... --force when user wants reprocessing.\nUse one-shot runtime model override only when requested:\n\npraxis --provider openai --model gpt-4.1-mini add \"/absolute/path/to/note.md\"\n\nFor image notes, pass image file path directly to praxis add; OCR extraction is built in.\nAlways finish with praxis show plus praxis insight or praxis export so user gets concrete output artifacts."
      },
      {
        "title": "Output Contract",
        "body": "When executing tasks with this skill, always provide these outputs:\n\nImport summary: files processed, chunks created, failures.\nExercise summary: counts by type/topic/difficulty.\nReview plan: next due batches and estimated workload.\nTraceability map: source -> doc_id -> chunk_id -> exercise_id."
      },
      {
        "title": "Exercise Format",
        "body": "Use this compact JSON-like structure per exercise:\n\n{\n  \"exercise_id\": \"ex-...\",\n  \"doc_id\": \"...\",\n  \"chunk_id\": \"...\",\n  \"type\": \"free-recall | qa | application\",\n  \"question\": \"...\",\n  \"answer_key\": \"...\",\n  \"rubric\": [\"point 1\", \"point 2\"],\n  \"difficulty\": \"easy | medium | hard\",\n  \"next_review\": \"YYYY-MM-DD\"\n}\n\nFor more generation patterns, read references/exercise-patterns.md."
      }
    ],
    "body": "OpenClaw Knowledge Coach\n\nCreate a local knowledge workflow in OpenClaw where importing knowledge also produces practice material for retention. OpenPraxis is on PyPI: use pip install openpraxis to get the praxis CLI.\n\nCLI First\n\nUse OpenPraxis CLI as the default execution path.\n\nInstall from PyPI (recommended):\n\npip install openpraxis\npraxis --help\n\n\nOr install from source for development:\n\ngit clone https://github.com/Sibo-Zhao/OpenPraxis.git\ncd OpenPraxis\npip install -e \".[dev]\"\npraxis --help\n\n\nConfigure provider/model/API key before ingestion/practice:\n\npraxis llm setup\npraxis llm show\n\n\nUse environment variables when needed (higher priority than config file):\n\nexport OPENAI_API_KEY=\"your_key_here\"\n# or ARK_API_KEY / MOONSHOT_API_KEY / DEEPSEEK_API_KEY based on provider\n\nCore Workflow\nConfirm scope and source\nConfirm knowledge domains, source folders, and accepted file types.\nConfirm whether to preserve existing metadata (tags, dates, project names).\nDefine import contract\nNormalize each source into a record with doc_id, title, source_path, tags, created_at, and content.\nSplit long content into chunks with stable IDs such as doc_id#chunk-001.\nImport into OpenClaw\nIngest normalized records into the local OpenClaw knowledge base.\nKeep a deterministic mapping between source file and imported IDs for later updates.\nGenerate exercises at import time\nFor each chunk, create at least one retrieval exercise.\nPrefer three exercise types:\nfree-recall: ask the user to explain from memory.\nqa: ask direct question-answer pairs.\napplication: ask scenario-based transfer questions.\nSave answer keys and concise grading rubrics.\nBuild review queue\nGroup exercises by topic and difficulty.\nSchedule spaced review windows (for example: day 1, day 3, day 7, day 14).\nValidate quality\nReject exercises that can be answered without the imported knowledge.\nReject ambiguous or duplicate questions.\nEnsure every exercise points back to doc_id and chunk_id.\nCLI Command Playbook\n\nRun this sequence when the user asks to import local knowledge and create practice:\n\nAdd a local file\npraxis add \"/absolute/path/to/note.md\" --type report\n\nList recent inputs and capture target input_id\npraxis list --limit 20\n\nForce-generate a new practice scene for an existing input\npraxis practice <input_id>\n\nSubmit answer by file (preferred for deterministic runs)\npraxis answer <scene_id> --file \"/absolute/path/to/answer.md\"\n\nInspect pipeline results and insight cards\npraxis show <input_id>\npraxis insight <input_id>\n\nExport insights to Markdown/JSON\npraxis export --format md --output \"/absolute/path/to/insights.md\"\npraxis export --format json --output \"/absolute/path/to/insights.json\"\n\nAgent Execution Rules\nPrefer praxis add for import and initial exercise generation.\nParse IDs from CLI output, then chain praxis practice and praxis answer.\nUse praxis answer --file instead of interactive stdin in automation flows.\nIf duplicate content is skipped, rerun with praxis add ... --force when user wants reprocessing.\nUse one-shot runtime model override only when requested:\npraxis --provider openai --model gpt-4.1-mini add \"/absolute/path/to/note.md\"\n\nFor image notes, pass image file path directly to praxis add; OCR extraction is built in.\nAlways finish with praxis show plus praxis insight or praxis export so user gets concrete output artifacts.\nOutput Contract\n\nWhen executing tasks with this skill, always provide these outputs:\n\nImport summary: files processed, chunks created, failures.\nExercise summary: counts by type/topic/difficulty.\nReview plan: next due batches and estimated workload.\nTraceability map: source -> doc_id -> chunk_id -> exercise_id.\nExercise Format\n\nUse this compact JSON-like structure per exercise:\n\n{\n  \"exercise_id\": \"ex-...\",\n  \"doc_id\": \"...\",\n  \"chunk_id\": \"...\",\n  \"type\": \"free-recall | qa | application\",\n  \"question\": \"...\",\n  \"answer_key\": \"...\",\n  \"rubric\": [\"point 1\", \"point 2\"],\n  \"difficulty\": \"easy | medium | hard\",\n  \"next_review\": \"YYYY-MM-DD\"\n}\n\n\nFor more generation patterns, read references/exercise-patterns.md."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Sibo-Zhao/openclaw-knowledge-coach",
    "publisherUrl": "https://clawhub.ai/Sibo-Zhao/openclaw-knowledge-coach",
    "owner": "Sibo-Zhao",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/openclaw-knowledge-coach",
    "downloadUrl": "https://openagent3.xyz/downloads/openclaw-knowledge-coach",
    "agentUrl": "https://openagent3.xyz/skills/openclaw-knowledge-coach/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-knowledge-coach/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-knowledge-coach/agent.md"
  }
}