{
  "schemaVersion": "1.0",
  "item": {
    "slug": "rule-creation",
    "name": "Rule Creation",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/levineam/rule-creation",
    "canonicalUrl": "https://clawhub.ai/levineam/rule-creation",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/rule-creation",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=rule-creation",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "package.json",
      "scripts/check-lobster-available.js",
      "scripts/create-lobster-workflow.js",
      "scripts/evaluate-enforcement-need.js"
    ],
    "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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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/rule-creation"
    },
    "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/rule-creation",
    "agentPageUrl": "https://openagent3.xyz/skills/rule-creation/agent",
    "manifestUrl": "https://openagent3.xyz/skills/rule-creation/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/rule-creation/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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Description",
        "body": "Auto-triggers Context Engineering compliance and Lobster enforcement evaluation when proposing, creating, or formalizing new rules, policies, processes, workflows, or behavioral constraints.\n\nContext Engineering is the practice of wiring rules into your AI's context so they're reliably followed — not just hoped for via prompting. Credit: Muratcan Koylan (@koylanai)\n\nUse this skill any time you are:\n\nDeclaring a new rule (e.g. \"From now on, always X\")\nFormalizing a policy (e.g. \"The policy for Y is Z\")\nCreating a behavioral constraint (e.g. \"Never do X without doing Y first\")\nProposing a process or workflow\nUpdating governance documents (TOOLS.md, CRITICAL-RULES.md, CONSTITUTION.md, etc.)"
      },
      {
        "title": "When This Skill Matches",
        "body": "Trigger phrases:\n\n\"Add this rule…\"\n\"Create a policy…\"\n\"From now on…\"\n\"The rule is…\"\n\"New constraint…\"\n\"Formalize that…\"\n\"Wire this rule…\"\n\"Make it a HARD rule…\"\nAny governance/policy update request"
      },
      {
        "title": "Mandatory Workflow",
        "body": "When this skill triggers, always execute the following steps in order. Do NOT ask permission — CE-PROCESS compliance means wire first, report after."
      },
      {
        "title": "Step 1: Identify the Rule",
        "body": "Extract:\n\nRule name — short slug (e.g. no-bare-spawns, external-message-gate)\nRule description — plain language statement of what the rule requires\nRule type — HARD (non-negotiable, always enforced) or soft (guideline, use judgment)"
      },
      {
        "title": "Step 2: Evaluate Enforcement Need (CR-012 Criteria)",
        "body": "Run scripts/evaluate-enforcement-need.js or apply manually:\n\nA rule needs Lobster enforcement if ANY of the following are true:\n\nCriterionExamplesHigh-stakesSends external messages, spends money, deletes data, publishes public content, deploys to productionPattern of violationsA similar rule was already stated but broken or ignoredMulti-step sequenceRequires multiple ordered steps (do A, then B, then C)External / public actionAffects things outside the user's local files\n\nScoring:\n\n0 criteria matched → needsEnforcement: false (wire to TOOLS.md only)\n1+ criteria matched → needsEnforcement: true (create Lobster workflow + wire)"
      },
      {
        "title": "Step 3: Lobster Availability Preflight",
        "body": "Before creating any workflow, verify Lobster is actually enabled:\n\nRun scripts/check-lobster-available.js or check manually:\n\nopenclaw plugins list | grep -i lobster\n\nOutputMeaningActionlobster … loaded✅ AvailableProceed to Step 3alobster … disabled❌ UnavailableUse fallback (below)No lobster row❌ Not installedUse fallback (below)\n\nFallback when Lobster is unavailable:\n\nSkip workflow creation entirely\nProceed directly to Step 4 (wire to docs) — no Lobster reference in the entry\nReport: ⚠️ Enforcement: unavailable (Lobster not enabled)\nInclude hint: Run: openclaw plugins enable lobster to activate\n\nNever claim enforcement is wired when Lobster is disabled."
      },
      {
        "title": "Step 3a: Create Lobster Workflow (enforcement needed AND Lobster available)",
        "body": "If needsEnforcement: true and Lobster preflight passed:\n\nCopy templates/lobster-workflow.template.lobster\nFill in: name, description, steps specific to rule enforcement\nSave to workflows/<rule-name>.lobster\nNote the workflow path for wiring"
      },
      {
        "title": "Step 4: Wire to Docs",
        "body": "Run scripts/wire-rule-to-docs.js or manually append to the appropriate file:\n\nRouting:\n\nOperational rules → TOOLS.md\nIdentity/persona constraints → SOUL.md or agents/identity.md\nHard system rules → CRITICAL-RULES.md (if exists) or AGENTS.md\nProject-specific rules → relevant project board or agents/projects.md\n\nEntry format (from templates/tools-md-entry.template.md):\n\n## <Rule Name> (<HARD|soft>)\n\n<Rule description>\n\n[If Lobster enforcement]: **Enforced by:** `workflows/<rule-name>.lobster`"
      },
      {
        "title": "Step 5: Report What Was Done",
        "body": "Your response must include:\n\n✅ Rule wired: <Rule Name>\n📄 Location: <file where it was added>\n🔒 Enforcement: <Lobster workflow path OR \"TOOLS.md entry only\">\n📋 Type: <HARD|soft>\n\nNever say:\n\n❌ \"Want me to add this to TOOLS.md?\"\n❌ \"Should I wire this through CE?\"\n❌ \"Is this CE compliant?\"\n\nAlways say:\n\n✅ \"Added <rule> to <file>. Enforcement: <status>.\""
      },
      {
        "title": "Script Reference",
        "body": "ScriptPurposescripts/check-lobster-available.jsPreflight: verify Lobster plugin is enabled in this OpenClaw instancescripts/evaluate-enforcement-need.jsEvaluate CR-012 criteria against rule descriptionscripts/wire-rule-to-docs.jsAppend rule entry to TOOLS.md or specified target filescripts/report-rule-creation.jsGenerate user-facing summary of what was created"
      },
      {
        "title": "Workflow Reference",
        "body": "WorkflowPurposeworkflows/create-rule.lobsterFull end-to-end rule creation pipeline"
      },
      {
        "title": "Context Engineering Auto-Trigger (HARD)",
        "body": "This skill embodies the Context Engineering Auto-Trigger principle:\n\n\"When proposing any new rule, behavioral constraint, or policy change: Wire it first. Add the rule to the appropriate file BEFORE responding. Never ask permission to formalize a rule.\"\n\nThe act of recognizing a rule IS the trigger. Wire immediately. Report after."
      }
    ],
    "body": "rule-creation Skill\nDescription\n\nAuto-triggers Context Engineering compliance and Lobster enforcement evaluation when proposing, creating, or formalizing new rules, policies, processes, workflows, or behavioral constraints.\n\nContext Engineering is the practice of wiring rules into your AI's context so they're reliably followed — not just hoped for via prompting. Credit: Muratcan Koylan (@koylanai)\n\nUse this skill any time you are:\n\nDeclaring a new rule (e.g. \"From now on, always X\")\nFormalizing a policy (e.g. \"The policy for Y is Z\")\nCreating a behavioral constraint (e.g. \"Never do X without doing Y first\")\nProposing a process or workflow\nUpdating governance documents (TOOLS.md, CRITICAL-RULES.md, CONSTITUTION.md, etc.)\nWhen This Skill Matches\n\nTrigger phrases:\n\n\"Add this rule…\"\n\"Create a policy…\"\n\"From now on…\"\n\"The rule is…\"\n\"New constraint…\"\n\"Formalize that…\"\n\"Wire this rule…\"\n\"Make it a HARD rule…\"\nAny governance/policy update request\nMandatory Workflow\n\nWhen this skill triggers, always execute the following steps in order. Do NOT ask permission — CE-PROCESS compliance means wire first, report after.\n\nStep 1: Identify the Rule\n\nExtract:\n\nRule name — short slug (e.g. no-bare-spawns, external-message-gate)\nRule description — plain language statement of what the rule requires\nRule type — HARD (non-negotiable, always enforced) or soft (guideline, use judgment)\nStep 2: Evaluate Enforcement Need (CR-012 Criteria)\n\nRun scripts/evaluate-enforcement-need.js or apply manually:\n\nA rule needs Lobster enforcement if ANY of the following are true:\n\nCriterion\tExamples\nHigh-stakes\tSends external messages, spends money, deletes data, publishes public content, deploys to production\nPattern of violations\tA similar rule was already stated but broken or ignored\nMulti-step sequence\tRequires multiple ordered steps (do A, then B, then C)\nExternal / public action\tAffects things outside the user's local files\n\nScoring:\n\n0 criteria matched → needsEnforcement: false (wire to TOOLS.md only)\n1+ criteria matched → needsEnforcement: true (create Lobster workflow + wire)\nStep 3: Lobster Availability Preflight\n\nBefore creating any workflow, verify Lobster is actually enabled:\n\nRun scripts/check-lobster-available.js or check manually:\n\nopenclaw plugins list | grep -i lobster\n\nOutput\tMeaning\tAction\nlobster … loaded\t✅ Available\tProceed to Step 3a\nlobster … disabled\t❌ Unavailable\tUse fallback (below)\nNo lobster row\t❌ Not installed\tUse fallback (below)\n\nFallback when Lobster is unavailable:\n\nSkip workflow creation entirely\nProceed directly to Step 4 (wire to docs) — no Lobster reference in the entry\nReport: ⚠️ Enforcement: unavailable (Lobster not enabled)\nInclude hint: Run: openclaw plugins enable lobster to activate\n\nNever claim enforcement is wired when Lobster is disabled.\n\nStep 3a: Create Lobster Workflow (enforcement needed AND Lobster available)\n\nIf needsEnforcement: true and Lobster preflight passed:\n\nCopy templates/lobster-workflow.template.lobster\nFill in: name, description, steps specific to rule enforcement\nSave to workflows/<rule-name>.lobster\nNote the workflow path for wiring\nStep 4: Wire to Docs\n\nRun scripts/wire-rule-to-docs.js or manually append to the appropriate file:\n\nRouting:\n\nOperational rules → TOOLS.md\nIdentity/persona constraints → SOUL.md or agents/identity.md\nHard system rules → CRITICAL-RULES.md (if exists) or AGENTS.md\nProject-specific rules → relevant project board or agents/projects.md\n\nEntry format (from templates/tools-md-entry.template.md):\n\n## <Rule Name> (<HARD|soft>)\n\n<Rule description>\n\n[If Lobster enforcement]: **Enforced by:** `workflows/<rule-name>.lobster`\n\nStep 5: Report What Was Done\n\nYour response must include:\n\n✅ Rule wired: <Rule Name>\n📄 Location: <file where it was added>\n🔒 Enforcement: <Lobster workflow path OR \"TOOLS.md entry only\">\n📋 Type: <HARD|soft>\n\n\nNever say:\n\n❌ \"Want me to add this to TOOLS.md?\"\n❌ \"Should I wire this through CE?\"\n❌ \"Is this CE compliant?\"\n\nAlways say:\n\n✅ \"Added <rule> to <file>. Enforcement: <status>.\"\nScript Reference\nScript\tPurpose\nscripts/check-lobster-available.js\tPreflight: verify Lobster plugin is enabled in this OpenClaw instance\nscripts/evaluate-enforcement-need.js\tEvaluate CR-012 criteria against rule description\nscripts/wire-rule-to-docs.js\tAppend rule entry to TOOLS.md or specified target file\nscripts/report-rule-creation.js\tGenerate user-facing summary of what was created\nWorkflow Reference\nWorkflow\tPurpose\nworkflows/create-rule.lobster\tFull end-to-end rule creation pipeline\nContext Engineering Auto-Trigger (HARD)\n\nThis skill embodies the Context Engineering Auto-Trigger principle:\n\n\"When proposing any new rule, behavioral constraint, or policy change: Wire it first. Add the rule to the appropriate file BEFORE responding. Never ask permission to formalize a rule.\"\n\nThe act of recognizing a rule IS the trigger. Wire immediately. Report after."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/levineam/rule-creation",
    "publisherUrl": "https://clawhub.ai/levineam/rule-creation",
    "owner": "levineam",
    "version": "1.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/rule-creation",
    "downloadUrl": "https://openagent3.xyz/downloads/rule-creation",
    "agentUrl": "https://openagent3.xyz/skills/rule-creation/agent",
    "manifestUrl": "https://openagent3.xyz/skills/rule-creation/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/rule-creation/agent.md"
  }
}