{
  "schemaVersion": "1.0",
  "item": {
    "slug": "charisma-research-loop",
    "name": "Charisma Research Loop",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/dman3629/charisma-research-loop",
    "canonicalUrl": "https://clawhub.ai/dman3629/charisma-research-loop",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/charisma-research-loop",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=charisma-research-loop",
    "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/charisma-research-loop"
    },
    "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/charisma-research-loop",
    "agentPageUrl": "https://openagent3.xyz/skills/charisma-research-loop/agent",
    "manifestUrl": "https://openagent3.xyz/skills/charisma-research-loop/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/charisma-research-loop/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": "Charisma Research Loop",
        "body": "Use this workflow to avoid shallow repeated advice and continuously improve insight quality."
      },
      {
        "title": "Output contract",
        "body": "Produce exactly 5 insights per run.\nMake each insight specific, testable, and action-oriented.\nInclude these fields for each insight:\n\nTheme\nInsight\nWhy it works\n24h experiment\nFailure mode / misuse risk"
      },
      {
        "title": "Theme rotation",
        "body": "Rotate themes so consecutive runs are not repetitive.\nUse this pool:\n\nBody language and non-verbal signaling\nOration and vocal delivery\nSocial psychology and status dynamics\nEthical persuasion and influence\nManipulation detection and defense\nConversation architecture and storytelling\nPresence under pressure (meetings, conflict, negotiation)"
      },
      {
        "title": "Source depth rules",
        "body": "Prefer synthesis over quotes.\nPull from mixed source types each run (discussion + educational + behavioral science).\nDo not rely on only surface-level generic tips.\nConvert raw source material into deeper mechanisms and practical tests."
      },
      {
        "title": "Self-improving loop (mandatory)",
        "body": "Before generating a new run:\n\nRead /root/.openclaw/workspace/memory/charisma-insight-ledger.md.\nIdentify what was already sent recently and mark those clusters as DONE in today’s section when superseded.\nChoose at least 3 new angles not used in the most recent 3 runs.\nGenerate the new 5-insight set.\nAppend a compact run log to the ledger:\n\ntimestamp\nthemes used\nnovelty score (1-10)\nrepeated ideas avoided\none improvement for next run"
      },
      {
        "title": "Delivery",
        "body": "Send concise email brief with the 5 insights.\nCreate/update calendar task/event containing same 5 insights.\nKeep wording practical, direct, non-fluffy."
      }
    ],
    "body": "Charisma Research Loop\n\nUse this workflow to avoid shallow repeated advice and continuously improve insight quality.\n\nOutput contract\nProduce exactly 5 insights per run.\nMake each insight specific, testable, and action-oriented.\nInclude these fields for each insight:\nTheme\nInsight\nWhy it works\n24h experiment\nFailure mode / misuse risk\nTheme rotation\n\nRotate themes so consecutive runs are not repetitive. Use this pool:\n\nBody language and non-verbal signaling\nOration and vocal delivery\nSocial psychology and status dynamics\nEthical persuasion and influence\nManipulation detection and defense\nConversation architecture and storytelling\nPresence under pressure (meetings, conflict, negotiation)\nSource depth rules\nPrefer synthesis over quotes.\nPull from mixed source types each run (discussion + educational + behavioral science).\nDo not rely on only surface-level generic tips.\nConvert raw source material into deeper mechanisms and practical tests.\nSelf-improving loop (mandatory)\n\nBefore generating a new run:\n\nRead /root/.openclaw/workspace/memory/charisma-insight-ledger.md.\nIdentify what was already sent recently and mark those clusters as DONE in today’s section when superseded.\nChoose at least 3 new angles not used in the most recent 3 runs.\nGenerate the new 5-insight set.\nAppend a compact run log to the ledger:\ntimestamp\nthemes used\nnovelty score (1-10)\nrepeated ideas avoided\none improvement for next run\nDelivery\nSend concise email brief with the 5 insights.\nCreate/update calendar task/event containing same 5 insights.\nKeep wording practical, direct, non-fluffy."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/dman3629/charisma-research-loop",
    "publisherUrl": "https://clawhub.ai/dman3629/charisma-research-loop",
    "owner": "dman3629",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/charisma-research-loop",
    "downloadUrl": "https://openagent3.xyz/downloads/charisma-research-loop",
    "agentUrl": "https://openagent3.xyz/skills/charisma-research-loop/agent",
    "manifestUrl": "https://openagent3.xyz/skills/charisma-research-loop/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/charisma-research-loop/agent.md"
  }
}