[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M788772K4QYXCZX3Y2P2AX9V":3,"skill-same:01M788772K4QYXCZX3Y2P2AX9V":52},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M788772K4QYXCZX3Y2P2AX9V","technical-writing",null,"House style for technical writing — the voice, sentence craft, formatting, and user-facing-copy rules that make docs and product text clear, direct, and consistent. Use when writing or editing a README, docs, a spec, release notes, a changelog, help text, or any error\u002FCLI\u002FUI copy a person reads; when reviewing a diff that touches prose or messages; or when a project needs a writing standard. Reference-heavy mechanics live in REFERENCE.md.","officialunofficial\u002Fskills","officialunofficial","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F127067914?v=4","01M78827JABEMMN63AC8J1RCXV","Official Unofficial, Inc.","01M78827KC164SFKN4DXTCKK7N",7,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fofficialunofficial\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Ftechnical-writing\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: technical-writing\ndescription: >\n  House style for technical writing — the voice, sentence craft, formatting, and\n  user-facing-copy rules that make docs and product text clear, direct, and\n  consistent. Use when writing or editing a README, docs, a spec, release notes,\n  a changelog, help text, or any error\u002FCLI\u002FUI copy a person reads; when reviewing\n  a diff that touches prose or messages; or when a project needs a writing\n  standard. Reference-heavy mechanics live in REFERENCE.md.\n---\n\n# Technical writing\n\nDocumentation is the single source of truth for how a system behaves, and every\nstring a person reads shapes their trust in it. Write for clarity, accuracy, and\ncompleteness. When you can show instead of tell, show: an example lands faster\nthan an explanation.\n\nThis skill is the durable, behavior-changing core. The exhaustive mechanics\n(units, possessives, abbreviations, keyboard shortcuts, code-doc conventions)\nlive in [REFERENCE.md](REFERENCE.md) &mdash; consult it when a specific question\ncomes up. Project-specific vocabulary (a glossary, wire-format terms, product\nnames) belongs in that project's own style guide; link the canonical definition\non first use.\n\n## Voice and tone\n\nThree words are the touchstone: **clear, direct, specific.** Every rule below\nserves one of them.\n\n- **Second person.** Write \"you\", not \"we\". Reserve \"we\" for the rare moment the\n  maintainers address the reader directly (a security advisory, a deprecation).\n- **Present tense.** Say what the system does now, not what it \"will\" do.\n- **Active voice.** Name the actor. \"The command writes a lockfile\", not \"a\n  lockfile is written\". Passive constructions lean on \"was\" and \"by\" &mdash; hunt them.\n- **Plain American English**, readable by every English speaker, not only native\n  ones. Prefer the shorter forms (\"behavior\", \"canceled\").\n- **Gender-neutral.** Singular \"they\"; address groups as developers, operators,\n  maintainers, or callers.\n\n## Sentence craft\n\nWrite short sentences. One thought each is punchier than three crammed together.\n\n- Use action verbs and subject-verb-object order. Cut clunky phrases. Drop any\n  adjective or adverb that doesn't change the meaning.\n- After a long sentence, write a short one. The contrast snaps attention back.\n- Don't repeat a word inside one sentence, and don't open or close a sentence\n  with the word that opened or closed the one before it.\n- Prefer splitting a phrase into two sentences over gluing clauses with a comma.\n  When you must join them, use an em dash or a connecting word (\"then\",\n  \"however\", \"so\"), never a bare comma between two independent clauses.\n\n## Formatting\n\n- **Headings in sentence case.** Capitalize only the first word and real proper\n  nouns, kept at their canonical casing (GitHub, BLAKE3, in-toto). Never Title\n  Case a heading for emphasis. The page title is the H1; top-level sections are\n  H2; don't skip levels.\n- **Link the noun phrase, never \"here\".** The link text names its destination and\n  reads as the call to action: \"see the [packfile specification](#)\", not \"the\n  spec is available [here](#)\". Use relative links between files in the same repo.\n- **Inline code is for code.** Back-tick identifiers, paths, commands, and literal\n  output only. Do not use inline code, bold, or caps as a substitute for emphasis.\n- **Bold file and directory names** (**.kit\u002F**, **src\u002F**, **.cbor**) rather than\n  back-ticking them.\n- **No emojis** &mdash; not in prose, headings, callouts, or changelog entries.\n- **Spell out symbols in prose**: \"and\" not \"&\", \"plus\" not \"+\" (except in\n  keyboard shortcuts).\n- **Em dashes**: write `&mdash;` rather than a hyphen or the literal `—`. Markdown\n  renders the entity reliably, and the literal `—` is the most common tell of\n  AI-assisted writing &mdash; flag it in review.\n- Numbered lists start at 1. Use Oxford commas in prose; if a sentence sags under\n  its commas, split it rather than dropping the Oxford comma.\n\n## User-facing copy\n\nAny string a person reads is user-facing copy: stdout and stderr, error and\nprogress messages, `--help` text, prompts, buttons, the web UI, the docs site. A\ndynamic `format!`\u002Ftemplate string counts. Every string earns its place by doing\nat least one of three things: say what happened, say what happens next, or say\nwhat to do. Get to the point.\n\n- **State facts, not feelings.** No \"please\", \"sorry\", \"unfortunately\". Write\n  `non-fast-forward push rejected: fetch and retry`, not `Sorry, we couldn't push\n  your changes. Please try again.`\n- **Every error carries the next action.** The exit code carries the class; the\n  message carries the specifics and, when one exists, the recovery step.\n- **Plain terms first.** Keep spec jargon in the specs. In help text, errors, and\n  UI, prefer the plain term (\"attestation envelope\"); expand or link a precise\n  term on first use.\n- **Exact verbs on prompts and buttons.** A confirmation names its action &mdash;\n  \"Delete branch\", \"Overwrite key\" &mdash; never \"Yes\" or \"OK\". Prompt copy is a\n  full sentence saying what happens and why.\n- **Same state, same words.** Never word one state two ways across surfaces (CLI\n  vs UI vs a JSON `message`). Route a repeated string through one helper.\n- **Sentence case everywhere** &mdash; headings, labels, buttons, table headers.\n  Title case only for real proper nouns.\n- **Fidelity wins over style.** Where output is pinned byte-for-byte to another\n  tool's (a compatibility format), match that tool's wording even when it breaks\n  these rules. Note why.\n\n## Before you ship\n\nRun this pass on any diff that touches prose or copy:\n\n1. **Grep the diff** for `please`, `sorry`, `unfortunately`, `simply`, and\n   `easy`. Each is almost always cuttable. (\"Simply\" and \"easy\" tell the reader\n   their trouble is their own fault.)\n2. **Search for the literal `—`** you didn't type as `&mdash;` &mdash; it's the\n   AI-writing giveaway.\n3. **Check for a duplicated string** already worded by a helper; reuse it instead\n   of hand-writing the state again.\n4. **Read it once for passive voice and long sentences.** Split the longest\n   sentence on the page. Turn one \"was …\" into an active clause.\n5. **Confirm headings are sentence case** and links name their destination.\n\nFor anything this skill doesn't cover, fall back to the\n[Google developer documentation style guide](https:\u002F\u002Fdevelopers.google.com\u002Fstyle)\nand, for the words to strike, [Words to avoid in educational writing](https:\u002F\u002Fcss-tricks.com\u002Fwords-avoid-educational-writing\u002F).\n","# Technical writing\n\nDocumentation is the single source of truth for how a system behaves, and every\nstring a person reads shapes their trust in it. Write for clarity, accuracy, and\ncompleteness. When you can show instead of tell, show: an example lands faster\nthan an explanation.\n\nThis skill is the durable, behavior-changing core. The exhaustive mechanics\n(units, possessives, abbreviations, keyboard shortcuts, code-doc conventions)\nlive in [REFERENCE.md](REFERENCE.md) &mdash; consult it when a specific question\ncomes up. Project-specific vocabulary (a glossary, wire-format terms, product\nnames) belongs in that project's own style guide; link the canonical definition\non first use.\n\n## Voice and tone\n\nThree words are the touchstone: **clear, direct, specific.** Every rule below\nserves one of them.\n\n- **Second person.** Write \"you\", not \"we\". Reserve \"we\" for the rare moment the\n  maintainers address the reader directly (a security advisory, a deprecation).\n- **Present tense.** Say what the system does now, not what it \"will\" do.\n- **Active voice.** Name the actor. \"The command writes a lockfile\", not \"a\n  lockfile is written\". Passive constructions lean on \"was\" and \"by\" &mdash; hunt them.\n- **Plain American English**, readable by every English speaker, not only native\n  ones. Prefer the shorter forms (\"behavior\", \"canceled\").\n- **Gender-neutral.** Singular \"they\"; address groups as developers, operators,\n  maintainers, or callers.\n\n## Sentence craft\n\nWrite short sentences. One thought each is punchier than three crammed together.\n\n- Use action verbs and subject-verb-object order. Cut clunky phrases. Drop any\n  adjective or adverb that doesn't change the meaning.\n- After a long sentence, write a short one. The contrast snaps attention back.\n- Don't repeat a word inside one sentence, and don't open or close a sentence\n  with the word that opened or closed the one before it.\n- Prefer splitting a phrase into two sentences over gluing clauses with a comma.\n  When you must join them, use an em dash or a connecting word (\"then\",\n  \"however\", \"so\"), never a bare comma between two independent clauses.\n\n## Formatting\n\n- **Headings in sentence case.** Capitalize only the first word and real proper\n  nouns, kept at their canonical casing (GitHub, BLAKE3, in-toto). Never Title\n  Case a heading for emphasis. The page title is the H1; top-level sections are\n  H2; don't skip levels.\n- **Link the noun phrase, never \"here\".** The link text names its destination and\n  reads as the call to action: \"see the [packfile specification](#)\", not \"the\n  spec is available [here](#)\". Use relative links between files in the same repo.\n- **Inline code is for code.** Back-tick identifiers, paths, commands, and literal\n  output only. Do not use inline code, bold, or caps as a substitute for emphasis.\n- **Bold file and directory names** (**.kit\u002F**, **src\u002F**, **.cbor**) rather than\n  back-ticking them.\n- **No emojis** &mdash; not in prose, headings, callouts, or changelog entries.\n- **Spell out symbols in prose**: \"and\" not \"&\", \"plus\" not \"+\" (except in\n  keyboard shortcuts).\n- **Em dashes**: write `&mdash;` rather than a hyphen or the literal `—`. Markdown\n  renders the entity reliably, and the literal `—` is the most common tell of\n  AI-assisted writing &mdash; flag it in review.\n- Numbered lists start at 1. Use Oxford commas in prose; if a sentence sags under\n  its commas, split it rather than dropping the Oxford comma.\n\n## User-facing copy\n\nAny string a person reads is user-facing copy: stdout and stderr, error and\nprogress messages, `--help` text, prompts, buttons, the web UI, the docs site. A\ndynamic `format!`\u002Ftemplate string counts. Every string earns its place by doing\nat least one of three things: say what happened, say what happens next, or say\nwhat to do. Get to the point.\n\n- **State facts, not feelings.** No \"please\", \"sorry\", \"unfortunately\". Write\n  `non-fast-forward push rejected: fetch and retry`, not `Sorry, we couldn't push\n  your changes. Please try again.`\n- **Every error carries the next action.** The exit code carries the class; the\n  message carries the specifics and, when one exists, the recovery step.\n- **Plain terms first.** Keep spec jargon in the specs. In help text, errors, and\n  UI, prefer the plain term (\"attestation envelope\"); expand or link a precise\n  term on first use.\n- **Exact verbs on prompts and buttons.** A confirmation names its action &mdash;\n  \"Delete branch\", \"Overwrite key\" &mdash; never \"Yes\" or \"OK\". Prompt copy is a\n  full sentence saying what happens and why.\n- **Same state, same words.** Never word one state two ways across surfaces (CLI\n  vs UI vs a JSON `message`). Route a repeated string through one helper.\n- **Sentence case everywhere** &mdash; headings, labels, buttons, table headers.\n  Title case only for real proper nouns.\n- **Fidelity wins over style.** Where output is pinned byte-for-byte to another\n  tool's (a compatibility format), match that tool's wording even when it breaks\n  these rules. Note why.\n\n## Before you ship\n\nRun this pass on any diff that touches prose or copy:\n\n1. **Grep the diff** for `please`, `sorry`, `unfortunately`, `simply`, and\n   `easy`. Each is almost always cuttable. (\"Simply\" and \"easy\" tell the reader\n   their trouble is their own fault.)\n2. **Search for the literal `—`** you didn't type as `&mdash;` &mdash; it's the\n   AI-writing giveaway.\n3. **Check for a duplicated string** already worded by a helper; reuse it instead\n   of hand-writing the state again.\n4. **Read it once for passive voice and long sentences.** Split the longest\n   sentence on the page. Turn one \"was …\" into an active clause.\n5. **Confirm headings are sentence case** and links name their destination.\n\nFor anything this skill doesn't cover, fall back to the\n[Google developer documentation style guide](https:\u002F\u002Fdevelopers.google.com\u002Fstyle)\nand, for the words to strike, [Words to avoid in educational writing](https:\u002F\u002Fcss-tricks.com\u002Fwords-avoid-educational-writing\u002F).\n",{"name":5,"description":7},"main","e1e71e8aa302edca3e052370aefa9272f86d07ee","skills\u002Fproductivity\u002Ftechnical-writing",0,"https:\u002F\u002Fgithub.com\u002Fofficialunofficial\u002Fskills","https:\u002F\u002Fgithub.com\u002Fofficialunofficial","officialunofficial.com","2026-11-06 10:07:10",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add officialunofficial\u002Fskills --skill technical-writing",{"tool":38,"command":39},"bunx","bunx skills add officialunofficial\u002Fskills --skill technical-writing",{"tool":41,"command":42},"pnpm","pnpm dlx skills add officialunofficial\u002Fskills --skill technical-writing","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fofficialunofficial\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Ftechnical-writing\u002FSKILL.md",true,[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"REFERENCE.md","REFERENCE","参考文档",6281,"https:\u002F\u002Fgithub.com\u002Fofficialunofficial\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Ftechnical-writing\u002FREFERENCE.md",[53,60,67,74,81,88],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7887BDP2BC5HFHEKCNMBZ4Q","writing-great-skills","Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.","https:\u002F\u002Fgithub.com\u002Fofficialunofficial\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fwriting-great-skills\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M78875087F1XKP7C6VRC49CY","teach","Teach the user a new skill or concept, within this workspace.","https:\u002F\u002Fgithub.com\u002Fofficialunofficial\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fteach\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M78872Z38MACN22AQDY9410P","handoff","Compact the current conversation into a handoff document for another agent to pick up.","https:\u002F\u002Fgithub.com\u002Fofficialunofficial\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fhandoff\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M78870FVRDYRT1WVP9HJ6FQ3","grilling","Interrogate the user's plan or design one decision at a time until you both share the same understanding. Use when the user wants to pressure-test an idea before building it, or reaches for any 'grill' trigger phrase.","https:\u002F\u002Fgithub.com\u002Fofficialunofficial\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fgrilling\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7886XGPEWXZYDA6K310HNYP","grill-me","A relentless, one-decision-at-a-time interview that sharpens a plan or design.","https:\u002F\u002Fgithub.com\u002Fofficialunofficial\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fgrill-me\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7886RR14H806M0GMNYX2BCV","setup-pre-commit","Add a Husky pre-commit hook backed by lint-staged (Prettier), plus type checking and tests, to the current repo. Use when the user wants pre-commit hooks, wants to set up Husky or lint-staged, or wants Prettier, typecheck, and tests to run at commit time.","https:\u002F\u002Fgithub.com\u002Fofficialunofficial\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fmisc\u002Fsetup-pre-commit\u002FSKILL.md",[],[]]