{
  "schemaVersion": "1.0",
  "item": {
    "slug": "principles",
    "name": "Principles",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/andyhcwang/principles",
    "canonicalUrl": "https://clawhub.ai/andyhcwang/principles",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/principles",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=principles",
    "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": "principles",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-03T05:13:37.301Z",
      "expiresAt": "2026-05-10T05:13:37.301Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=principles",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=principles",
        "contentDisposition": "attachment; filename=\"principles-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "principles"
      },
      "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/principles"
    },
    "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/principles",
    "agentPageUrl": "https://openagent3.xyz/skills/principles/agent",
    "manifestUrl": "https://openagent3.xyz/skills/principles/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/principles/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": "Principles — Personal Knowledge System",
        "body": "A structured system for turning raw observations into tested wisdom and personal principles. Inspired by Ray Dalio's \"Principles\" methodology."
      },
      {
        "title": "Overview",
        "body": "You manage a pipeline that transforms raw input into lasting knowledge:\n\nInbox (raw capture) → Wisdom (claims with sources) → Principles (tested beliefs)\n\nEverything lives in personal/ under the user's workspace. Create the directory structure on first use if it doesn't exist."
      },
      {
        "title": "Directory Structure",
        "body": "personal/\n├── _system.md          # These instructions (copy from SKILL.md on init)\n├── inbox.md            # Raw thought capture\n├── journal.md          # Daily reflections\n├── wisdom/\n│   └── collected.md    # Claims organized by domain\n├── principles/\n│   ├── _index.md       # Master list of all principles\n│   ├── life.md         # Personal philosophy\n│   ├── business.md     # Business principles\n│   └── leadership.md   # Leadership principles\n└── open-questions.md   # Genuine dilemmas"
      },
      {
        "title": "/reflect or /reflect process",
        "body": "Process the inbox. Parse each thought, check for conflicts, route to the right file."
      },
      {
        "title": "/reflect inbox or /inbox",
        "body": "Add a raw thought to inbox.md. User just dumps text — you clean it up later during processing."
      },
      {
        "title": "/reflect wisdom",
        "body": "Show collected wisdom, optionally filtered by domain."
      },
      {
        "title": "/reflect principles",
        "body": "Show current principles across all domains."
      },
      {
        "title": "/reflect questions",
        "body": "Show open questions and their status."
      },
      {
        "title": "/reflect sources",
        "body": "Show a summary of all sources and their credibility ratings across domains."
      },
      {
        "title": "/reflect journal",
        "body": "Add a journal entry for today with timestamp."
      },
      {
        "title": "Processing Inbox (/reflect)",
        "body": "This is the core workflow. When triggered:\n\nRead inbox.md\n\n\nParse each thought — identify type:\n\nExternal wisdom (from someone else) → wisdom/collected.md\nPersonal belief or stance → check against principles/*.md\nFactual learning → wisdom/collected.md\nQuestion or uncertainty → evaluate if genuine dilemma\nJust context/event → extract insight if any, discard the rest\n\n\n\nCheck for conflicts against existing wisdom claims:\n\nSame claim, new source → add as corroborating evidence\nConflicting claim in same domain → STOP. Present conflict. Ask user to resolve.\n\n\n\nCheck consistency against existing principles:\n\nIf new input conflicts with a principle → STOP. Present conflict. Ask user to resolve.\n\n\n\nIf ANY conflict found → STOP and ask user:\n\nShow the conflict clearly\nOffer options: update existing, keep existing, split claims, convert to open question\nDo NOT silently file conflicting information\n\n\n\nRoute content based on user decisions\n\n\nClean up inbox.md after processing\n\n\nUpdate principles/_index.md if new principles were added"
      },
      {
        "title": "Wisdom Claims (wisdom/collected.md)",
        "body": "Claims are organized by domain, not by source. Multiple sources can corroborate the same claim.\n\n## [Domain/Aspect]\n\n### [Claim stated plainly]\n**Domain**: [category/aspect]\n**Confidence**: [Low / Medium / High]\n\n**Sources**:\n1. [Person/Book] - [proven/plausible/untested] in this domain - [brief context]\n\n**Your experience**: [Untested / Confirmed / Contradicted]\n\n**Added**: YYYY-MM-DD | **Last updated**: YYYY-MM-DD\n\nSource credibility is assessed PER DOMAIN:\n\nA source can be [proven] in one domain and [plausible] in another\nExample: Alex Hormozi on business = [proven]. Alex Hormozi on health = [plausible].\nCredibility levels: [proven] (demonstrated expertise), [plausible] (reasonable but not their domain), [untested] (no track record)\n\nDomain format: category/aspect (e.g., health/sleep, business/pricing, productivity/focus)"
      },
      {
        "title": "Principles (principles/*.md)",
        "body": "## [Principle stated as a clear belief]\n\n**Confidence**: [certain / hypothesis / exploring]\n**Added**: YYYY-MM-DD\n**Context**: Why you believe this\n**Reasoning**: Evidence and experience supporting it\n**Related**: Links to related principles or wisdom claims"
      },
      {
        "title": "Open Questions (open-questions.md)",
        "body": "Only genuine dilemmas — not todo items or simple unknowns.\n\n## [Question]\n**Status**: [exploring / gathering-evidence / leaning-toward-X]\n\n**Goal**: What are you actually trying to achieve?\n**Problem**: What's blocking it?\n**Options**:\n1. [Option A] - pros/cons\n2. [Option B] - pros/cons\n\n**What would resolve this**: Specific criteria or evidence needed"
      },
      {
        "title": "Journal (journal.md)",
        "body": "Append-only daily entries:\n\n## YYYY-MM-DD\n\n[Observations, reflections, what happened today]"
      },
      {
        "title": "Graduation: Wisdom → Principles",
        "body": "When a wisdom claim reaches High confidence (multiple credible sources + personal experience confirms it), prompt the user:\n\n\"This claim has strong evidence and you've confirmed it personally. Want to graduate it to a principle in [domain]?\"\n\nIf yes, create the principle entry and cross-reference it."
      },
      {
        "title": "Assumption Surfacing",
        "body": "When user input has unstated assumptions:\n\nMake them explicit\nAsk: \"This assumes X — is that accurate?\"\nDon't proceed until confirmed"
      },
      {
        "title": "Language & Tone",
        "body": "Clean up sloppy writing but preserve original meaning exactly\nUser may write in any language — process accordingly\nBe direct, not preachy. This is a tool, not a lecture."
      },
      {
        "title": "First-Time Setup",
        "body": "If personal/ doesn't exist, create the full directory structure with empty template files. Tell the user:\n\n\"Set up your principles system. Start by dumping thoughts into /inbox — I'll help you process and organize them with /reflect.\""
      }
    ],
    "body": "Principles — Personal Knowledge System\n\nA structured system for turning raw observations into tested wisdom and personal principles. Inspired by Ray Dalio's \"Principles\" methodology.\n\nOverview\n\nYou manage a pipeline that transforms raw input into lasting knowledge:\n\nInbox (raw capture) → Wisdom (claims with sources) → Principles (tested beliefs)\n\n\nEverything lives in personal/ under the user's workspace. Create the directory structure on first use if it doesn't exist.\n\nDirectory Structure\npersonal/\n├── _system.md          # These instructions (copy from SKILL.md on init)\n├── inbox.md            # Raw thought capture\n├── journal.md          # Daily reflections\n├── wisdom/\n│   └── collected.md    # Claims organized by domain\n├── principles/\n│   ├── _index.md       # Master list of all principles\n│   ├── life.md         # Personal philosophy\n│   ├── business.md     # Business principles\n│   └── leadership.md   # Leadership principles\n└── open-questions.md   # Genuine dilemmas\n\nCommands\n/reflect or /reflect process\n\nProcess the inbox. Parse each thought, check for conflicts, route to the right file.\n\n/reflect inbox or /inbox\n\nAdd a raw thought to inbox.md. User just dumps text — you clean it up later during processing.\n\n/reflect wisdom\n\nShow collected wisdom, optionally filtered by domain.\n\n/reflect principles\n\nShow current principles across all domains.\n\n/reflect questions\n\nShow open questions and their status.\n\n/reflect sources\n\nShow a summary of all sources and their credibility ratings across domains.\n\n/reflect journal\n\nAdd a journal entry for today with timestamp.\n\nProcessing Inbox (/reflect)\n\nThis is the core workflow. When triggered:\n\nRead inbox.md\n\nParse each thought — identify type:\n\nExternal wisdom (from someone else) → wisdom/collected.md\nPersonal belief or stance → check against principles/*.md\nFactual learning → wisdom/collected.md\nQuestion or uncertainty → evaluate if genuine dilemma\nJust context/event → extract insight if any, discard the rest\n\nCheck for conflicts against existing wisdom claims:\n\nSame claim, new source → add as corroborating evidence\nConflicting claim in same domain → STOP. Present conflict. Ask user to resolve.\n\nCheck consistency against existing principles:\n\nIf new input conflicts with a principle → STOP. Present conflict. Ask user to resolve.\n\nIf ANY conflict found → STOP and ask user:\n\nShow the conflict clearly\nOffer options: update existing, keep existing, split claims, convert to open question\nDo NOT silently file conflicting information\n\nRoute content based on user decisions\n\nClean up inbox.md after processing\n\nUpdate principles/_index.md if new principles were added\n\nContent Formats\nWisdom Claims (wisdom/collected.md)\n\nClaims are organized by domain, not by source. Multiple sources can corroborate the same claim.\n\n## [Domain/Aspect]\n\n### [Claim stated plainly]\n**Domain**: [category/aspect]\n**Confidence**: [Low / Medium / High]\n\n**Sources**:\n1. [Person/Book] - [proven/plausible/untested] in this domain - [brief context]\n\n**Your experience**: [Untested / Confirmed / Contradicted]\n\n**Added**: YYYY-MM-DD | **Last updated**: YYYY-MM-DD\n\n\nSource credibility is assessed PER DOMAIN:\n\nA source can be [proven] in one domain and [plausible] in another\nExample: Alex Hormozi on business = [proven]. Alex Hormozi on health = [plausible].\nCredibility levels: [proven] (demonstrated expertise), [plausible] (reasonable but not their domain), [untested] (no track record)\n\nDomain format: category/aspect (e.g., health/sleep, business/pricing, productivity/focus)\n\nPrinciples (principles/*.md)\n## [Principle stated as a clear belief]\n\n**Confidence**: [certain / hypothesis / exploring]\n**Added**: YYYY-MM-DD\n**Context**: Why you believe this\n**Reasoning**: Evidence and experience supporting it\n**Related**: Links to related principles or wisdom claims\n\nOpen Questions (open-questions.md)\n\nOnly genuine dilemmas — not todo items or simple unknowns.\n\n## [Question]\n**Status**: [exploring / gathering-evidence / leaning-toward-X]\n\n**Goal**: What are you actually trying to achieve?\n**Problem**: What's blocking it?\n**Options**:\n1. [Option A] - pros/cons\n2. [Option B] - pros/cons\n\n**What would resolve this**: Specific criteria or evidence needed\n\nJournal (journal.md)\n\nAppend-only daily entries:\n\n## YYYY-MM-DD\n\n[Observations, reflections, what happened today]\n\nGraduation: Wisdom → Principles\n\nWhen a wisdom claim reaches High confidence (multiple credible sources + personal experience confirms it), prompt the user:\n\n\"This claim has strong evidence and you've confirmed it personally. Want to graduate it to a principle in [domain]?\"\n\nIf yes, create the principle entry and cross-reference it.\n\nAssumption Surfacing\n\nWhen user input has unstated assumptions:\n\nMake them explicit\nAsk: \"This assumes X — is that accurate?\"\nDon't proceed until confirmed\nLanguage & Tone\nClean up sloppy writing but preserve original meaning exactly\nUser may write in any language — process accordingly\nBe direct, not preachy. This is a tool, not a lecture.\nFirst-Time Setup\n\nIf personal/ doesn't exist, create the full directory structure with empty template files. Tell the user:\n\n\"Set up your principles system. Start by dumping thoughts into /inbox — I'll help you process and organize them with /reflect.\""
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/andyhcwang/principles",
    "publisherUrl": "https://clawhub.ai/andyhcwang/principles",
    "owner": "andyhcwang",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/principles",
    "downloadUrl": "https://openagent3.xyz/downloads/principles",
    "agentUrl": "https://openagent3.xyz/skills/principles/agent",
    "manifestUrl": "https://openagent3.xyz/skills/principles/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/principles/agent.md"
  }
}