{
  "schemaVersion": "1.0",
  "item": {
    "slug": "clear-writing",
    "name": "Clear Writing",
    "source": "tencent",
    "type": "skill",
    "category": "效率提升",
    "sourceUrl": "https://clawhub.ai/wpank/clear-writing",
    "canonicalUrl": "https://clawhub.ai/wpank/clear-writing",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/clear-writing",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=clear-writing",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "references/elements-of-style/01-introductory.md",
      "references/elements-of-style/02-elementary-rules-of-usage.md",
      "references/elements-of-style/03-elementary-principles-of-composition.md",
      "references/elements-of-style/04-a-few-matters-of-form.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. 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": "2026-04-23T16:43:11.935Z",
      "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/clear-writing"
    },
    "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/clear-writing",
    "agentPageUrl": "https://openagent3.xyz/skills/clear-writing/agent",
    "manifestUrl": "https://openagent3.xyz/skills/clear-writing/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/clear-writing/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": "Clear Writing",
        "body": "Write with clarity and force. This skill covers what to do (Strunk's rules), how to structure technical documentation (Divio patterns, templates), and what not to do (AI anti-patterns, doc anti-patterns)."
      },
      {
        "title": "When to Use",
        "body": "Use this skill whenever you write prose for humans:\n\nDocumentation, README files, technical explanations\nAPI documentation, endpoint references, integration guides\nTutorials, how-to guides, architecture docs\nCommit messages, pull request descriptions\nError messages, UI copy, help text, comments\nReports, summaries, or any explanation\nEditing existing prose to improve clarity\n\nIf you're writing sentences for a human to read, use this skill."
      },
      {
        "title": "Limited Context Strategy",
        "body": "When context is tight:\n\nWrite your draft using judgment\nDispatch a subagent with your draft and the relevant reference file\nHave the subagent copyedit and return the revision\n\nLoading a single reference (~1,000–4,500 tokens) instead of the full skill saves significant context."
      },
      {
        "title": "Elements of Style",
        "body": "William Strunk Jr.'s The Elements of Style (1918) teaches you to write clearly and cut ruthlessly."
      },
      {
        "title": "Rules",
        "body": "Elementary Rules of Usage (Grammar/Punctuation):\n\nForm possessive singular by adding 's\nUse comma after each term in series except last\nEnclose parenthetic expressions between commas\nComma before conjunction introducing co-ordinate clause\nDon't join independent clauses by comma\nDon't break sentences in two\nParticipial phrase at beginning refers to grammatical subject\n\nElementary Principles of Composition:\n\nOne paragraph per topic\nBegin paragraph with topic sentence\nUse active voice\nPut statements in positive form\nUse definite, specific, concrete language\nOmit needless words\nAvoid succession of loose sentences\nExpress co-ordinate ideas in similar form\nKeep related words together\nKeep to one tense in summaries\nPlace emphatic words at end of sentence"
      },
      {
        "title": "Reference Files",
        "body": "For complete explanations with examples:\n\nSectionFile~TokensGrammar, punctuation, comma rulesreferences/elements-of-style/02-elementary-rules-of-usage.md2,500Paragraph structure, active voice, concisionreferences/elements-of-style/03-elementary-principles-of-composition.md4,500Headings, quotations, formattingreferences/elements-of-style/04-a-few-matters-of-form.md1,000Word choice, common errorsreferences/elements-of-style/05-words-and-expressions-commonly-misused.md4,000\n\nMost tasks need only 03-elementary-principles-of-composition.md — it covers active voice, positive form, concrete language, and omitting needless words."
      },
      {
        "title": "AI Writing Patterns to Avoid",
        "body": "LLMs regress to statistical means, producing generic, puffy prose. Avoid:\n\nPuffery: pivotal, crucial, vital, testament, enduring legacy\nEmpty \"-ing\" phrases: ensuring reliability, showcasing features, highlighting capabilities\nPromotional adjectives: groundbreaking, seamless, robust, cutting-edge\nOverused AI vocabulary: delve, leverage, multifaceted, foster, realm, tapestry\nFormatting overuse: excessive bullets, emoji decorations, bold on every other word\n\nBe specific, not grandiose. Say what it actually does.\n\nFor comprehensive research on why these patterns occur, see references/signs-of-ai-writing.md. Wikipedia editors developed this guide to detect AI-generated submissions — their patterns are well-documented and field-tested."
      },
      {
        "title": "Document Types (Divio Framework)",
        "body": "TypePurposeStructureREADMEFirst impression, project overviewTitle, description, quick start, install, usageTutorialLearning-oriented, guided experienceNumbered steps with expected outcomesHow-to GuideTask-oriented, solve a specific problemProblem statement → steps → resultReferenceInformation-oriented, complete and accurateAlphabetical or grouped, consistent formatExplanationUnderstanding-oriented, context and rationaleNarrative prose, diagrams, historyArchitecture DocSystem design, component relationshipsContext → components → data flow → decisionsAPI DocumentationEndpoint contracts, integration guideEndpoint → params → request → response → errors"
      },
      {
        "title": "Inverted Pyramid",
        "body": "Lead with the most important information. Each subsequent section adds detail.\n\n1. What it does (one sentence)\n2. How to use it (quick start)\n3. Configuration options\n4. Advanced usage\n5. Internals / implementation details"
      },
      {
        "title": "Problem-Solution",
        "body": "1. Problem — what goes wrong, symptoms, error messages\n2. Cause — why it happens (brief)\n3. Solution — step-by-step fix\n4. Prevention — how to avoid it in the future"
      },
      {
        "title": "Sequential Steps",
        "body": "Every step is a single action with a verifiable outcome.\n\n1. Step — one action, one verb\n   Expected result: what the reader should see\n2. Step — next action\n   Expected result: confirmation of success"
      },
      {
        "title": "Writing Rules",
        "body": "RuleGuidelineExampleShort sentencesKeep under 25 words\"The server restarts automatically after config changes.\"Active voiceSubject does the action\"The function returns a promise\" not \"A promise is returned\"Present tenseDescribe current behavior\"This endpoint accepts JSON\" not \"will accept JSON\"One idea per paragraphEach paragraph has one pointSplit compound paragraphs at the topic shiftDefine jargon on first useNever assume vocabulary\"The ORM (Object-Relational Mapper) translates...\"Second personAddress the reader directly\"You can configure...\" not \"One can configure...\"Consistent terminologyPick one term and stick with itDon't alternate between \"repo\" and \"repository\"Concrete over abstractSpecifics beat generalities\"Returns a 404 status code\" not \"Returns an error\""
      },
      {
        "title": "Code Examples in Documentation",
        "body": "Every code example must follow these rules:\n\nComplete and runnable — copy-paste and execute without modification\nAnnotated — comments on the non-obvious parts, not the obvious ones\nProgressive complexity — simplest case first, then advanced usage\nLanguage-tagged — always specify the language in fenced code blocks\nCurrent — examples must work with the documented version\nMinimal — show only what is relevant; strip unrelated boilerplate\n\n# Good: complete, annotated, minimal\nimport httpx\n\n# Create a client with a base URL to avoid repeating it\nclient = httpx.Client(base_url=\"https://api.example.com\")\n\n# Fetch a user by ID — returns a User dict or raises for 4xx/5xx\nresponse = client.get(\"/users/42\")\nresponse.raise_for_status()\nuser = response.json()\nprint(user[\"name\"])  # \"Ada Lovelace\""
      },
      {
        "title": "README Template",
        "body": "# Project Name\n\nOne-line description of what this project does and who it is for.\n\n## Quick Start\n\nThe fastest path from zero to working. Three commands or fewer.\n\n## Installation\n\nPrerequisites, system requirements, and step-by-step install.\n\n## Usage\n\nCommon use cases with code examples. Cover the 80% case.\n\n## API\n\nPublic API surface — functions, classes, CLI flags, endpoints.\n\n## Configuration\n\nEnvironment variables, config files, and their defaults.\n\n## Contributing\n\nHow to set up the dev environment, run tests, and submit changes.\n\n## License\n\nLicense name and link to the full LICENSE file.\n\nREADME rules:\n\nKeep the quick start under 60 seconds of reader time\nInclude a badge row only if badges are kept current\nLink to deeper docs rather than bloating the README\nUpdate the README whenever the public interface changes"
      },
      {
        "title": "API Documentation Pattern",
        "body": "Document every endpoint with this structure:\n\n### GET /users/:id\n\nRetrieve a single user by their unique identifier.\n\n**Authentication:** Bearer token required\n\n**Path Parameters:**\n\n| Parameter | Type   | Required | Description          |\n|-----------|--------|----------|----------------------|\n| id        | string | Yes      | The user's unique ID |\n\n**Response: 200 OK**\n\n{json response example}\n\n**Error Responses:**\n\n| Status | Code         | Description              |\n|--------|--------------|--------------------------|\n| 401    | UNAUTHORIZED | Missing or invalid token |\n| 404    | NOT_FOUND    | User does not exist      |\n\nAlways document errors with: HTTP status, machine-readable error code, human-readable message, and resolution steps."
      },
      {
        "title": "Audience Adaptation",
        "body": "AudienceContext LevelFocusToneBeginnerHigh — define terms, explain prerequisitesWhat and how, step by stepEncouraging, patientIntermediateMedium — assume basic knowledgeHow and best practicesDirect, practicalExpertLow — skip fundamentalsWhy, edge cases, tradeoffsConcise, precise\n\nRules:\n\nState the assumed audience at the top of the document\nLink to prerequisite knowledge rather than re-explaining it\nUse expandable sections (<details>) for beginner context in expert docs\nNever mix audience levels in the same section"
      },
      {
        "title": "Review Checklist",
        "body": "Before publishing any documentation:\n\nAccurate — all code examples run, all commands work, all links resolve\n Complete — covers setup, happy path, error cases, and cleanup\n Consistent — terminology, formatting, and voice match the rest of the docs\n Readable — passes a cold read by someone unfamiliar with the project\n Scannable — headings, tables, and lists allow skimming for answers\n Examples work — every code block tested against the current version\n Links valid — no broken internal or external links\n Audience-appropriate — context level matches the stated audience\n Up to date — no references to deprecated features or old versions\n Spellchecked — no typos, no inconsistent capitalization"
      },
      {
        "title": "Documentation Anti-Patterns",
        "body": "Anti-PatternProblemFixWall of textReaders bounceBreak into sections with headings and listsOutdated docsErodes trustTie doc updates to PR checklists; date-stamp pagesNo examplesReaders can't apply abstract descriptionsAdd code examples for every public functionAssumed knowledgeExcludes beginnersDefine terms on first use, link to prerequisitesCopy-paste unfriendlyCode with $ prompts or line numbers breaks when pastedProvide clean, runnable code blocksScreenshot-only instructionsCan't be searched, go stale, inaccessiblePair screenshots with text and commands"
      },
      {
        "title": "NEVER Do",
        "body": "NEVER publish docs without testing every code example — broken examples destroy credibility faster than anything else\nNEVER write docs after the fact as an afterthought — write docs alongside the code; if you cannot explain it, the design needs work\nNEVER use \"simply\", \"just\", or \"obviously\" — these words shame readers who are struggling and add no information\nNEVER mix multiple audiences in one document — write separate beginner and advanced guides, or use clear section boundaries\nNEVER leave placeholder text in published docs — \"TODO\", \"TBD\", and \"lorem ipsum\" signal abandonment\nNEVER duplicate content across documents — link to a single source of truth; duplicates inevitably drift apart\nNEVER omit the date or version — readers must know if they are looking at current information\nNEVER use AI puffery words — pivotal, crucial, seamless, robust, groundbreaking, tapestry, and their ilk add nothing and signal lazy writing"
      }
    ],
    "body": "Clear Writing\n\nWrite with clarity and force. This skill covers what to do (Strunk's rules), how to structure technical documentation (Divio patterns, templates), and what not to do (AI anti-patterns, doc anti-patterns).\n\nWhen to Use\n\nUse this skill whenever you write prose for humans:\n\nDocumentation, README files, technical explanations\nAPI documentation, endpoint references, integration guides\nTutorials, how-to guides, architecture docs\nCommit messages, pull request descriptions\nError messages, UI copy, help text, comments\nReports, summaries, or any explanation\nEditing existing prose to improve clarity\n\nIf you're writing sentences for a human to read, use this skill.\n\nLimited Context Strategy\n\nWhen context is tight:\n\nWrite your draft using judgment\nDispatch a subagent with your draft and the relevant reference file\nHave the subagent copyedit and return the revision\n\nLoading a single reference (~1,000–4,500 tokens) instead of the full skill saves significant context.\n\nElements of Style\n\nWilliam Strunk Jr.'s The Elements of Style (1918) teaches you to write clearly and cut ruthlessly.\n\nRules\n\nElementary Rules of Usage (Grammar/Punctuation):\n\nForm possessive singular by adding 's\nUse comma after each term in series except last\nEnclose parenthetic expressions between commas\nComma before conjunction introducing co-ordinate clause\nDon't join independent clauses by comma\nDon't break sentences in two\nParticipial phrase at beginning refers to grammatical subject\n\nElementary Principles of Composition:\n\nOne paragraph per topic\nBegin paragraph with topic sentence\nUse active voice\nPut statements in positive form\nUse definite, specific, concrete language\nOmit needless words\nAvoid succession of loose sentences\nExpress co-ordinate ideas in similar form\nKeep related words together\nKeep to one tense in summaries\nPlace emphatic words at end of sentence\nReference Files\n\nFor complete explanations with examples:\n\nSection\tFile\t~Tokens\nGrammar, punctuation, comma rules\treferences/elements-of-style/02-elementary-rules-of-usage.md\t2,500\nParagraph structure, active voice, concision\treferences/elements-of-style/03-elementary-principles-of-composition.md\t4,500\nHeadings, quotations, formatting\treferences/elements-of-style/04-a-few-matters-of-form.md\t1,000\nWord choice, common errors\treferences/elements-of-style/05-words-and-expressions-commonly-misused.md\t4,000\n\nMost tasks need only 03-elementary-principles-of-composition.md — it covers active voice, positive form, concrete language, and omitting needless words.\n\nAI Writing Patterns to Avoid\n\nLLMs regress to statistical means, producing generic, puffy prose. Avoid:\n\nPuffery: pivotal, crucial, vital, testament, enduring legacy\nEmpty \"-ing\" phrases: ensuring reliability, showcasing features, highlighting capabilities\nPromotional adjectives: groundbreaking, seamless, robust, cutting-edge\nOverused AI vocabulary: delve, leverage, multifaceted, foster, realm, tapestry\nFormatting overuse: excessive bullets, emoji decorations, bold on every other word\n\nBe specific, not grandiose. Say what it actually does.\n\nFor comprehensive research on why these patterns occur, see references/signs-of-ai-writing.md. Wikipedia editors developed this guide to detect AI-generated submissions — their patterns are well-documented and field-tested.\n\nDocument Types (Divio Framework)\nType\tPurpose\tStructure\nREADME\tFirst impression, project overview\tTitle, description, quick start, install, usage\nTutorial\tLearning-oriented, guided experience\tNumbered steps with expected outcomes\nHow-to Guide\tTask-oriented, solve a specific problem\tProblem statement → steps → result\nReference\tInformation-oriented, complete and accurate\tAlphabetical or grouped, consistent format\nExplanation\tUnderstanding-oriented, context and rationale\tNarrative prose, diagrams, history\nArchitecture Doc\tSystem design, component relationships\tContext → components → data flow → decisions\nAPI Documentation\tEndpoint contracts, integration guide\tEndpoint → params → request → response → errors\nStructure Patterns\nInverted Pyramid\n\nLead with the most important information. Each subsequent section adds detail.\n\n1. What it does (one sentence)\n2. How to use it (quick start)\n3. Configuration options\n4. Advanced usage\n5. Internals / implementation details\n\nProblem-Solution\n1. Problem — what goes wrong, symptoms, error messages\n2. Cause — why it happens (brief)\n3. Solution — step-by-step fix\n4. Prevention — how to avoid it in the future\n\nSequential Steps\n\nEvery step is a single action with a verifiable outcome.\n\n1. Step — one action, one verb\n   Expected result: what the reader should see\n2. Step — next action\n   Expected result: confirmation of success\n\nWriting Rules\nRule\tGuideline\tExample\nShort sentences\tKeep under 25 words\t\"The server restarts automatically after config changes.\"\nActive voice\tSubject does the action\t\"The function returns a promise\" not \"A promise is returned\"\nPresent tense\tDescribe current behavior\t\"This endpoint accepts JSON\" not \"will accept JSON\"\nOne idea per paragraph\tEach paragraph has one point\tSplit compound paragraphs at the topic shift\nDefine jargon on first use\tNever assume vocabulary\t\"The ORM (Object-Relational Mapper) translates...\"\nSecond person\tAddress the reader directly\t\"You can configure...\" not \"One can configure...\"\nConsistent terminology\tPick one term and stick with it\tDon't alternate between \"repo\" and \"repository\"\nConcrete over abstract\tSpecifics beat generalities\t\"Returns a 404 status code\" not \"Returns an error\"\nCode Examples in Documentation\n\nEvery code example must follow these rules:\n\nComplete and runnable — copy-paste and execute without modification\nAnnotated — comments on the non-obvious parts, not the obvious ones\nProgressive complexity — simplest case first, then advanced usage\nLanguage-tagged — always specify the language in fenced code blocks\nCurrent — examples must work with the documented version\nMinimal — show only what is relevant; strip unrelated boilerplate\n# Good: complete, annotated, minimal\nimport httpx\n\n# Create a client with a base URL to avoid repeating it\nclient = httpx.Client(base_url=\"https://api.example.com\")\n\n# Fetch a user by ID — returns a User dict or raises for 4xx/5xx\nresponse = client.get(\"/users/42\")\nresponse.raise_for_status()\nuser = response.json()\nprint(user[\"name\"])  # \"Ada Lovelace\"\n\nREADME Template\n# Project Name\n\nOne-line description of what this project does and who it is for.\n\n## Quick Start\n\nThe fastest path from zero to working. Three commands or fewer.\n\n## Installation\n\nPrerequisites, system requirements, and step-by-step install.\n\n## Usage\n\nCommon use cases with code examples. Cover the 80% case.\n\n## API\n\nPublic API surface — functions, classes, CLI flags, endpoints.\n\n## Configuration\n\nEnvironment variables, config files, and their defaults.\n\n## Contributing\n\nHow to set up the dev environment, run tests, and submit changes.\n\n## License\n\nLicense name and link to the full LICENSE file.\n\n\nREADME rules:\n\nKeep the quick start under 60 seconds of reader time\nInclude a badge row only if badges are kept current\nLink to deeper docs rather than bloating the README\nUpdate the README whenever the public interface changes\nAPI Documentation Pattern\n\nDocument every endpoint with this structure:\n\n### GET /users/:id\n\nRetrieve a single user by their unique identifier.\n\n**Authentication:** Bearer token required\n\n**Path Parameters:**\n\n| Parameter | Type   | Required | Description          |\n|-----------|--------|----------|----------------------|\n| id        | string | Yes      | The user's unique ID |\n\n**Response: 200 OK**\n\n{json response example}\n\n**Error Responses:**\n\n| Status | Code         | Description              |\n|--------|--------------|--------------------------|\n| 401    | UNAUTHORIZED | Missing or invalid token |\n| 404    | NOT_FOUND    | User does not exist      |\n\n\nAlways document errors with: HTTP status, machine-readable error code, human-readable message, and resolution steps.\n\nAudience Adaptation\nAudience\tContext Level\tFocus\tTone\nBeginner\tHigh — define terms, explain prerequisites\tWhat and how, step by step\tEncouraging, patient\nIntermediate\tMedium — assume basic knowledge\tHow and best practices\tDirect, practical\nExpert\tLow — skip fundamentals\tWhy, edge cases, tradeoffs\tConcise, precise\n\nRules:\n\nState the assumed audience at the top of the document\nLink to prerequisite knowledge rather than re-explaining it\nUse expandable sections (<details>) for beginner context in expert docs\nNever mix audience levels in the same section\nReview Checklist\n\nBefore publishing any documentation:\n\n Accurate — all code examples run, all commands work, all links resolve\n Complete — covers setup, happy path, error cases, and cleanup\n Consistent — terminology, formatting, and voice match the rest of the docs\n Readable — passes a cold read by someone unfamiliar with the project\n Scannable — headings, tables, and lists allow skimming for answers\n Examples work — every code block tested against the current version\n Links valid — no broken internal or external links\n Audience-appropriate — context level matches the stated audience\n Up to date — no references to deprecated features or old versions\n Spellchecked — no typos, no inconsistent capitalization\nDocumentation Anti-Patterns\nAnti-Pattern\tProblem\tFix\nWall of text\tReaders bounce\tBreak into sections with headings and lists\nOutdated docs\tErodes trust\tTie doc updates to PR checklists; date-stamp pages\nNo examples\tReaders can't apply abstract descriptions\tAdd code examples for every public function\nAssumed knowledge\tExcludes beginners\tDefine terms on first use, link to prerequisites\nCopy-paste unfriendly\tCode with $ prompts or line numbers breaks when pasted\tProvide clean, runnable code blocks\nScreenshot-only instructions\tCan't be searched, go stale, inaccessible\tPair screenshots with text and commands\nNEVER Do\nNEVER publish docs without testing every code example — broken examples destroy credibility faster than anything else\nNEVER write docs after the fact as an afterthought — write docs alongside the code; if you cannot explain it, the design needs work\nNEVER use \"simply\", \"just\", or \"obviously\" — these words shame readers who are struggling and add no information\nNEVER mix multiple audiences in one document — write separate beginner and advanced guides, or use clear section boundaries\nNEVER leave placeholder text in published docs — \"TODO\", \"TBD\", and \"lorem ipsum\" signal abandonment\nNEVER duplicate content across documents — link to a single source of truth; duplicates inevitably drift apart\nNEVER omit the date or version — readers must know if they are looking at current information\nNEVER use AI puffery words — pivotal, crucial, seamless, robust, groundbreaking, tapestry, and their ilk add nothing and signal lazy writing"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/wpank/clear-writing",
    "publisherUrl": "https://clawhub.ai/wpank/clear-writing",
    "owner": "wpank",
    "version": "0.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/clear-writing",
    "downloadUrl": "https://openagent3.xyz/downloads/clear-writing",
    "agentUrl": "https://openagent3.xyz/skills/clear-writing/agent",
    "manifestUrl": "https://openagent3.xyz/skills/clear-writing/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/clear-writing/agent.md"
  }
}