{
  "schemaVersion": "1.0",
  "item": {
    "slug": "adversarial-prompting",
    "name": "Adversarial Prompting",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/abe238/adversarial-prompting",
    "canonicalUrl": "https://clawhub.ai/abe238/adversarial-prompting",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/adversarial-prompting",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=adversarial-prompting",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/export_analysis.py"
    ],
    "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": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/adversarial-prompting"
    },
    "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/adversarial-prompting",
    "agentPageUrl": "https://openagent3.xyz/skills/adversarial-prompting/agent",
    "manifestUrl": "https://openagent3.xyz/skills/adversarial-prompting/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/adversarial-prompting/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": "Adversarial Prompting",
        "body": "This skill applies a structured adversarial methodology to problem-solving by generating multiple solutions, rigorously critiquing each for weaknesses, developing fixes, validating those fixes, and consolidating into ranked recommendations. The approach forces deep analysis of failure modes, edge cases, and unintended consequences before committing to a solution."
      },
      {
        "title": "When to Use This Skill",
        "body": "Use this skill when:\n\nFacing complex technical problems requiring thorough analysis (architecture decisions, debugging, performance optimization)\nSolving strategic or business problems with multiple viable approaches\nNeeding to identify weaknesses in proposed solutions before implementation\nRequiring validated fixes that address root causes, not symptoms\nWorking on high-stakes decisions where failure modes must be understood\nSeeking comprehensive analysis with detailed reasoning visible throughout\n\nDo not use this skill for:\n\nSimple, straightforward problems with obvious solutions\nTime-sensitive decisions requiring immediate action without analysis\nProblems where exploration and iteration are more valuable than upfront analysis"
      },
      {
        "title": "Primary Workflow",
        "body": "When invoked, apply the following 7-phase process to the user's problem:\n\nPhase 1: Solution Generation\n\nGenerate 3-7 distinct solution approaches. For each solution:\n\nExplain the reasoning behind the approach\nDescribe the core strategy\nOutline the key steps or components\n\nPhase 2: Adversarial Critique\n\nFor each solution, rigorously identify critical weaknesses. Show thinking while examining:\n\nEdge cases and failure modes\nSecurity vulnerabilities or risks\nPerformance bottlenecks\nScalability limitations\nHidden assumptions that could break\nResource constraints (time, money, people)\nUnintended consequences\nCatastrophic failure scenarios\n\nBe creative and thorough in identifying what could go wrong.\n\nPhase 3: Fix Development\n\nFor each identified weakness:\n\nPropose a specific fix or mitigation strategy\nExplain why this fix addresses the root cause\nDescribe how the fix integrates with the original solution\n\nPhase 4: Validation Check\n\nReview each fix to verify it actually solves the weakness:\n\nConfirm the fix addresses the root cause\nCheck for new problems introduced by the fix\nFlag any remaining concerns or trade-offs\n\nPhase 5: Consolidation\n\nSynthesize all solutions and validated fixes into comprehensive approaches:\n\nIntegrate complementary elements from different solutions\nEliminate redundancies\nShow how solutions can be combined for stronger approaches\nPresent the final set of viable options\n\nPhase 6: Summary of Options\n\nPresent all viable options in priority order, ranked by:\n\nFeasibility: Can this actually be implemented with available resources?\nImpact: How well does this solve the problem?\nRisk Level: What could still go wrong?\nResource Requirements: Cost in time, money, and effort\n\nFor each option, provide a one-paragraph summary highlighting key trade-offs.\n\nPhase 7: Final Recommendation\n\nState the top recommendation (single option or combination):\n\nClear rationale for why this is the best path\nConcrete next steps for implementation\nKey success metrics to track\nEarly warning signs to monitor for problems"
      },
      {
        "title": "Output Format",
        "body": "Present the complete analysis in three sections:\n\nDetailed Walkthrough: Show all phases (1-5) with full reasoning visible\nSummary of Options: Ranked list of viable approaches (Phase 6)\nFinal Recommendation: Top choice with implementation guidance (Phase 7)\n\nAfter presenting the analysis, automatically export the complete output to a markdown file using scripts/export_analysis.py."
      },
      {
        "title": "Implementation Notes",
        "body": "Show reasoning throughout the process for transparency\nBe thorough in adversarial critique—surface uncomfortable truths\nValidate fixes rigorously to avoid creating new problems\nConsolidation should create stronger solutions, not just list options\nFinal recommendation should be actionable with clear next steps\nExport results to markdown for future reference and sharing"
      }
    ],
    "body": "Adversarial Prompting\n\nThis skill applies a structured adversarial methodology to problem-solving by generating multiple solutions, rigorously critiquing each for weaknesses, developing fixes, validating those fixes, and consolidating into ranked recommendations. The approach forces deep analysis of failure modes, edge cases, and unintended consequences before committing to a solution.\n\nWhen to Use This Skill\n\nUse this skill when:\n\nFacing complex technical problems requiring thorough analysis (architecture decisions, debugging, performance optimization)\nSolving strategic or business problems with multiple viable approaches\nNeeding to identify weaknesses in proposed solutions before implementation\nRequiring validated fixes that address root causes, not symptoms\nWorking on high-stakes decisions where failure modes must be understood\nSeeking comprehensive analysis with detailed reasoning visible throughout\n\nDo not use this skill for:\n\nSimple, straightforward problems with obvious solutions\nTime-sensitive decisions requiring immediate action without analysis\nProblems where exploration and iteration are more valuable than upfront analysis\nHow to Use This Skill\nPrimary Workflow\n\nWhen invoked, apply the following 7-phase process to the user's problem:\n\nPhase 1: Solution Generation\n\nGenerate 3-7 distinct solution approaches. For each solution:\n\nExplain the reasoning behind the approach\nDescribe the core strategy\nOutline the key steps or components\nPhase 2: Adversarial Critique\n\nFor each solution, rigorously identify critical weaknesses. Show thinking while examining:\n\nEdge cases and failure modes\nSecurity vulnerabilities or risks\nPerformance bottlenecks\nScalability limitations\nHidden assumptions that could break\nResource constraints (time, money, people)\nUnintended consequences\nCatastrophic failure scenarios\n\nBe creative and thorough in identifying what could go wrong.\n\nPhase 3: Fix Development\n\nFor each identified weakness:\n\nPropose a specific fix or mitigation strategy\nExplain why this fix addresses the root cause\nDescribe how the fix integrates with the original solution\nPhase 4: Validation Check\n\nReview each fix to verify it actually solves the weakness:\n\nConfirm the fix addresses the root cause\nCheck for new problems introduced by the fix\nFlag any remaining concerns or trade-offs\nPhase 5: Consolidation\n\nSynthesize all solutions and validated fixes into comprehensive approaches:\n\nIntegrate complementary elements from different solutions\nEliminate redundancies\nShow how solutions can be combined for stronger approaches\nPresent the final set of viable options\nPhase 6: Summary of Options\n\nPresent all viable options in priority order, ranked by:\n\nFeasibility: Can this actually be implemented with available resources?\nImpact: How well does this solve the problem?\nRisk Level: What could still go wrong?\nResource Requirements: Cost in time, money, and effort\n\nFor each option, provide a one-paragraph summary highlighting key trade-offs.\n\nPhase 7: Final Recommendation\n\nState the top recommendation (single option or combination):\n\nClear rationale for why this is the best path\nConcrete next steps for implementation\nKey success metrics to track\nEarly warning signs to monitor for problems\nOutput Format\n\nPresent the complete analysis in three sections:\n\nDetailed Walkthrough: Show all phases (1-5) with full reasoning visible\nSummary of Options: Ranked list of viable approaches (Phase 6)\nFinal Recommendation: Top choice with implementation guidance (Phase 7)\n\nAfter presenting the analysis, automatically export the complete output to a markdown file using scripts/export_analysis.py.\n\nImplementation Notes\nShow reasoning throughout the process for transparency\nBe thorough in adversarial critique—surface uncomfortable truths\nValidate fixes rigorously to avoid creating new problems\nConsolidation should create stronger solutions, not just list options\nFinal recommendation should be actionable with clear next steps\nExport results to markdown for future reference and sharing"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/abe238/adversarial-prompting",
    "publisherUrl": "https://clawhub.ai/abe238/adversarial-prompting",
    "owner": "abe238",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/adversarial-prompting",
    "downloadUrl": "https://openagent3.xyz/downloads/adversarial-prompting",
    "agentUrl": "https://openagent3.xyz/skills/adversarial-prompting/agent",
    "manifestUrl": "https://openagent3.xyz/skills/adversarial-prompting/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/adversarial-prompting/agent.md"
  }
}