{
  "schemaVersion": "1.0",
  "item": {
    "slug": "content-creator-skill",
    "name": "Content Creator",
    "source": "tencent",
    "type": "skill",
    "category": "内容创作",
    "sourceUrl": "https://clawhub.ai/h4gen/content-creator-skill",
    "canonicalUrl": "https://clawhub.ai/h4gen/content-creator-skill",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/content-creator-skill",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=content-creator-skill",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/inspected-skills.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": "2026-04-23T16:43:11.935Z",
      "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/content-creator-skill"
    },
    "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/content-creator-skill",
    "agentPageUrl": "https://openagent3.xyz/skills/content-creator-skill/agent",
    "manifestUrl": "https://openagent3.xyz/skills/content-creator-skill/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/content-creator-skill/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": "Purpose",
        "body": "Create content that is:\n\npersuasive and high-signal,\nnatural in voice,\nplatform-appropriate,\nnon-generic and non-template-like.\n\nThis skill coordinates upstream writing/editing skills; it does not claim guaranteed virality."
      },
      {
        "title": "Required Installed Skills",
        "body": "humanizer (inspected latest: 1.0.0)\nde-ai-ify (inspected latest: 1.0.0)\ncopywriting (inspected latest: 0.1.0)\ntweet-writer (inspected latest: 1.0.0)\n\nInstall/update:\n\nnpx -y clawhub@latest install humanizer\nnpx -y clawhub@latest install de-ai-ify\nnpx -y clawhub@latest install copywriting\nnpx -y clawhub@latest install tweet-writer\nnpx -y clawhub@latest update --all\n\nVerify:\n\nnpx -y clawhub@latest list"
      },
      {
        "title": "Requested Scenario Profile",
        "body": "Example scenario:\n\nUser needs a LinkedIn post about remote work.\nThe post should feel authentic and engagement-oriented.\nThe final output should also include an X thread adaptation (5 tweets)."
      },
      {
        "title": "Inputs the LM Must Collect First",
        "body": "topic (example: remote work)\nplatform_primary (linkedin)\ntarget_audience (example: managers, founders, ICs)\ngoal (reach, comments, shares, leads)\nvoice_preferences (direct, reflective, contrarian, practical)\nauthor_context (first-hand experience, examples, proof points)\nhard_constraints (length, tone, banned claims/words)\nthread_required (yes/no, default yes for this scenario)\n\nDo not draft copy before these are explicit."
      },
      {
        "title": "humanizer",
        "body": "Use as first-pass anti-pattern editor:\n\nremove common AI writing signals,\nreplace inflated/formulaic language with specific concrete phrasing,\npreserve meaning while increasing naturalness.\n\nImportant behavior:\n\nstrongly pattern-based rewrite guidance,\noutput is rewritten text + change summary,\nno guaranteed numeric score in the base humanizer skill."
      },
      {
        "title": "de-ai-ify",
        "body": "Use as voice pass:\n\nreduce robotic transitions and hedging,\nsimplify buzzword-heavy language,\nincrease conversational rhythm,\nenforce direct, human cadence.\n\nImportant behavior:\n\nstyle/voice correction layer after humanizer,\nuseful for adding opinionated nuance and natural texture."
      },
      {
        "title": "copywriting",
        "body": "Use as persuasion structure pass:\n\napply AIDA/PAS/FAB where appropriate,\nstrengthen opening hook,\nsharpen value proposition,\nadd one clear engagement CTA.\n\nImportant behavior:\n\npersuasive framework selection by goal,\navoid over-salesy tone for social posts."
      },
      {
        "title": "tweet-writer",
        "body": "Use as X/Twitter adaptation layer:\n\nconvert long-form message into scroll-stopping tweet/thread format,\noptimize hooks, pacing, and mobile readability,\nenforce concise tweet structure.\n\nImportant boundary:\n\nthis is X-oriented optimization, not LinkedIn-native optimization."
      },
      {
        "title": "Canonical Pipeline",
        "body": "Use this order unless user requests otherwise."
      },
      {
        "title": "Stage 1: Base draft (message-first)",
        "body": "Create a clean first draft for LinkedIn:\n\none strong claim/opinion\none concrete example\none practical takeaway\none question for comments\n\nAvoid list-heavy, sterile, template-first drafting."
      },
      {
        "title": "Stage 2: Humanizer pass (pattern cleanup)",
        "body": "Run the draft through humanizer logic:\n\nremove inflated symbolism and generic conclusions\nreduce over-structured AI cadence\nreplace vague claims with specifics\n\nOutput target:\n\nsame core meaning,\nlower obvious AI-pattern density,\nstill readable and coherent."
      },
      {
        "title": "Stage 3: De-AI-ify pass (voice)",
        "body": "Apply de-ai-ify voice shaping:\n\nremove excessive transitions and hedging\ntighten to direct, natural language\nintroduce human rhythm (short + long sentence variation)\n\nOutput target:\n\nsounds like a person with a point of view,\nnot like policy copy."
      },
      {
        "title": "Stage 4: Copywriting pass (engagement architecture)",
        "body": "Apply copywriting frameworks to final LinkedIn post:\n\nopening: strong hook (bold thesis, tension, or contrarian angle)\nbody: concise value block (problem -> insight -> implication)\nclose: one engagement question (comments-oriented CTA)\n\nRule:\n\none CTA only."
      },
      {
        "title": "Stage 5: X adaptation (5-tweet thread)",
        "body": "Use tweet-writer principles to convert the same core argument into exactly 5 tweets:\n\nTweet 1: hook\nTweet 2: context/problem\nTweet 3: key insight\nTweet 4: practical framework/example\nTweet 5: question CTA\n\nHard constraints:\n\nno external links in the main tweets unless user explicitly requests\nshort, mobile-readable lines\nkeep continuity and avoid repeating the same sentence across tweets"
      },
      {
        "title": "Causal Chain (Scenario Mapping)",
        "body": "For the scenario \"LinkedIn post about remote work\":\n\nAgent drafts initial post on remote-work thesis.\nhumanizer flags typical AI-like signals and rewrites for specificity.\nde-ai-ify adds conversational nuance and less robotic cadence.\ncopywriting strengthens hook and adds one engagement question.\ntweet-writer transforms core message into a 5-tweet thread."
      },
      {
        "title": "Output Contract",
        "body": "Always return:\n\nLinkedInPost_Final\n\nfinal LinkedIn copy\n\n\n\nVoiceEdits_Summary\n\nkey changes from humanizer + de-ai-ify\n\n\n\nPersuasionStructure\n\nframework used (AIDA/PAS/FAB) and why\n\n\n\nXThread_5Tweets\n\nexactly five tweets, numbered 1/5 ... 5/5\n\n\n\nOptionalVariants\n\n2 alternative hooks\n2 alternative closing questions"
      },
      {
        "title": "Quality Gates",
        "body": "Before final output, verify:\n\nauthenticity: text does not read like a rigid template\nspecificity: at least one concrete detail/example included\nrhythm: sentence lengths vary naturally\npersuasion: one clear hook + one clear CTA\nplatform fit: LinkedIn readable + X thread concise\nintegrity: no fabricated data, experiences, or citations\n\nIf any gate fails, return Needs Revision with explicit reasons."
      },
      {
        "title": "Guardrails",
        "body": "Do not fabricate personal anecdotes or fake proof.\nDo not claim guaranteed virality or guaranteed reach outcomes.\nDo not hide factual uncertainty when claims are unverified.\nKeep persuasive language ethical and non-manipulative.\nPrioritize reader trust over stylistic gimmicks."
      },
      {
        "title": "Known Limits from Inspected Upstream Skills",
        "body": "Base humanizer is rewrite-focused and does not define a strict numeric AI score output.\nIf numeric AI-likeness scoring is required (for example \"85% AI\"), this may need the optional ai-humanizer variant or explicit custom scoring rubric.\ntweet-writer optimizes for X, not LinkedIn ranking mechanics.\nThese tools improve quality and naturalness but cannot guarantee SEO outcomes or detection immunity.\n\nTreat these limits as required disclosure when presenting results."
      }
    ],
    "body": "Purpose\n\nCreate content that is:\n\npersuasive and high-signal,\nnatural in voice,\nplatform-appropriate,\nnon-generic and non-template-like.\n\nThis skill coordinates upstream writing/editing skills; it does not claim guaranteed virality.\n\nRequired Installed Skills\nhumanizer (inspected latest: 1.0.0)\nde-ai-ify (inspected latest: 1.0.0)\ncopywriting (inspected latest: 0.1.0)\ntweet-writer (inspected latest: 1.0.0)\n\nInstall/update:\n\nnpx -y clawhub@latest install humanizer\nnpx -y clawhub@latest install de-ai-ify\nnpx -y clawhub@latest install copywriting\nnpx -y clawhub@latest install tweet-writer\nnpx -y clawhub@latest update --all\n\n\nVerify:\n\nnpx -y clawhub@latest list\n\nRequested Scenario Profile\n\nExample scenario:\n\nUser needs a LinkedIn post about remote work.\nThe post should feel authentic and engagement-oriented.\nThe final output should also include an X thread adaptation (5 tweets).\nInputs the LM Must Collect First\ntopic (example: remote work)\nplatform_primary (linkedin)\ntarget_audience (example: managers, founders, ICs)\ngoal (reach, comments, shares, leads)\nvoice_preferences (direct, reflective, contrarian, practical)\nauthor_context (first-hand experience, examples, proof points)\nhard_constraints (length, tone, banned claims/words)\nthread_required (yes/no, default yes for this scenario)\n\nDo not draft copy before these are explicit.\n\nTool Responsibilities\nhumanizer\n\nUse as first-pass anti-pattern editor:\n\nremove common AI writing signals,\nreplace inflated/formulaic language with specific concrete phrasing,\npreserve meaning while increasing naturalness.\n\nImportant behavior:\n\nstrongly pattern-based rewrite guidance,\noutput is rewritten text + change summary,\nno guaranteed numeric score in the base humanizer skill.\nde-ai-ify\n\nUse as voice pass:\n\nreduce robotic transitions and hedging,\nsimplify buzzword-heavy language,\nincrease conversational rhythm,\nenforce direct, human cadence.\n\nImportant behavior:\n\nstyle/voice correction layer after humanizer,\nuseful for adding opinionated nuance and natural texture.\ncopywriting\n\nUse as persuasion structure pass:\n\napply AIDA/PAS/FAB where appropriate,\nstrengthen opening hook,\nsharpen value proposition,\nadd one clear engagement CTA.\n\nImportant behavior:\n\npersuasive framework selection by goal,\navoid over-salesy tone for social posts.\ntweet-writer\n\nUse as X/Twitter adaptation layer:\n\nconvert long-form message into scroll-stopping tweet/thread format,\noptimize hooks, pacing, and mobile readability,\nenforce concise tweet structure.\n\nImportant boundary:\n\nthis is X-oriented optimization, not LinkedIn-native optimization.\nCanonical Pipeline\n\nUse this order unless user requests otherwise.\n\nStage 1: Base draft (message-first)\n\nCreate a clean first draft for LinkedIn:\n\none strong claim/opinion\none concrete example\none practical takeaway\none question for comments\n\nAvoid list-heavy, sterile, template-first drafting.\n\nStage 2: Humanizer pass (pattern cleanup)\n\nRun the draft through humanizer logic:\n\nremove inflated symbolism and generic conclusions\nreduce over-structured AI cadence\nreplace vague claims with specifics\n\nOutput target:\n\nsame core meaning,\nlower obvious AI-pattern density,\nstill readable and coherent.\nStage 3: De-AI-ify pass (voice)\n\nApply de-ai-ify voice shaping:\n\nremove excessive transitions and hedging\ntighten to direct, natural language\nintroduce human rhythm (short + long sentence variation)\n\nOutput target:\n\nsounds like a person with a point of view,\nnot like policy copy.\nStage 4: Copywriting pass (engagement architecture)\n\nApply copywriting frameworks to final LinkedIn post:\n\nopening: strong hook (bold thesis, tension, or contrarian angle)\nbody: concise value block (problem -> insight -> implication)\nclose: one engagement question (comments-oriented CTA)\n\nRule:\n\none CTA only.\nStage 5: X adaptation (5-tweet thread)\n\nUse tweet-writer principles to convert the same core argument into exactly 5 tweets:\n\nTweet 1: hook\nTweet 2: context/problem\nTweet 3: key insight\nTweet 4: practical framework/example\nTweet 5: question CTA\n\nHard constraints:\n\nno external links in the main tweets unless user explicitly requests\nshort, mobile-readable lines\nkeep continuity and avoid repeating the same sentence across tweets\nCausal Chain (Scenario Mapping)\n\nFor the scenario \"LinkedIn post about remote work\":\n\nAgent drafts initial post on remote-work thesis.\nhumanizer flags typical AI-like signals and rewrites for specificity.\nde-ai-ify adds conversational nuance and less robotic cadence.\ncopywriting strengthens hook and adds one engagement question.\ntweet-writer transforms core message into a 5-tweet thread.\nOutput Contract\n\nAlways return:\n\nLinkedInPost_Final\n\nfinal LinkedIn copy\n\nVoiceEdits_Summary\n\nkey changes from humanizer + de-ai-ify\n\nPersuasionStructure\n\nframework used (AIDA/PAS/FAB) and why\n\nXThread_5Tweets\n\nexactly five tweets, numbered 1/5 ... 5/5\n\nOptionalVariants\n\n2 alternative hooks\n2 alternative closing questions\nQuality Gates\n\nBefore final output, verify:\n\nauthenticity: text does not read like a rigid template\nspecificity: at least one concrete detail/example included\nrhythm: sentence lengths vary naturally\npersuasion: one clear hook + one clear CTA\nplatform fit: LinkedIn readable + X thread concise\nintegrity: no fabricated data, experiences, or citations\n\nIf any gate fails, return Needs Revision with explicit reasons.\n\nGuardrails\nDo not fabricate personal anecdotes or fake proof.\nDo not claim guaranteed virality or guaranteed reach outcomes.\nDo not hide factual uncertainty when claims are unverified.\nKeep persuasive language ethical and non-manipulative.\nPrioritize reader trust over stylistic gimmicks.\nKnown Limits from Inspected Upstream Skills\nBase humanizer is rewrite-focused and does not define a strict numeric AI score output.\nIf numeric AI-likeness scoring is required (for example \"85% AI\"), this may need the optional ai-humanizer variant or explicit custom scoring rubric.\ntweet-writer optimizes for X, not LinkedIn ranking mechanics.\nThese tools improve quality and naturalness but cannot guarantee SEO outcomes or detection immunity.\n\nTreat these limits as required disclosure when presenting results."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/h4gen/content-creator-skill",
    "publisherUrl": "https://clawhub.ai/h4gen/content-creator-skill",
    "owner": "h4gen",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/content-creator-skill",
    "downloadUrl": "https://openagent3.xyz/downloads/content-creator-skill",
    "agentUrl": "https://openagent3.xyz/skills/content-creator-skill/agent",
    "manifestUrl": "https://openagent3.xyz/skills/content-creator-skill/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/content-creator-skill/agent.md"
  }
}