[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78BH9D09HCA7ECZMPEEAE5Y":3,"skill-same:01M78BH9D09HCA7ECZMPEEAE5Y":48},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M78BH9D09HCA7ECZMPEEAE5Y","humanize-english",null,"Edit English drafts for clear, natural language while preserving facts, uncertainty,\ntechnical meaning, citations and genre. Use when: humanize this text, remove AI-style\nfiller, improve English prose, or edit an English article before publication.\nNot an authorship detector or a promise to bypass one. For Russian use\nhumanize-russian; for thesis\u002Fevidence and structure use article-structure-review.","hermes-jarvis-bot\u002Fhermes-agent-config-kit","hermes-jarvis-bot","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F288284026?v=4","01M78AV3BBD4M67J3YWSQRKP1Q","01M78AV3C2SKH53E0PZMXAKTTS",1,"MIT","https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fwriting\u002Fhumanize-english\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: humanize-english\ndescription: |\n  Edit English drafts for clear, natural language while preserving facts, uncertainty,\n  technical meaning, citations and genre. Use when: humanize this text, remove AI-style\n  filler, improve English prose, or edit an English article before publication.\n  Not an authorship detector or a promise to bypass one. For Russian use\n  humanize-russian; for thesis\u002Fevidence and structure use article-structure-review.\nmetadata:\n  version: \"2.0.0\"\n  reviewed: \"2026-09-06\"\n---\n\n# Clear, Natural English Editing\n\nImprove the reader's understanding, not a detector score. A good reference can\nhave repeated terminology, regular tables, definitions and no anecdote.\nKeep the user's intended voice and the destination's format.\n\n## Facts Are Not Style Material\n\n- Preserve supplied numbers, units, dates, versions, names, citations, negation,\n  uncertainty and claim scope. Do not silently update a historical date.\n- Never invent a count, quote, interview, personal experience, experiment,\n  failure, comparison or source to make prose more vivid.\n- Add specificity only when the supporting evidence supplies it. If no\n  measurement exists, retain uncertainty or remove an unsupported claim.\n  An unsupplied number is not an improvement over a vague quantity.\n- Label illustrative scenarios as hypothetical. Do not present them as a real\n  case study or treat their invented values as proof of a product claim.\n- Preserve identifiers, executable code and technical obligations. Words such\n  as may, must, can and will are not interchangeable style alternatives.\n- Reuse provided facts without asking the user to repeat them. Research a\n  material factual gap when research is in scope; otherwise identify the gap\n  without manufacturing an answer or blocking supported edits.\n\n## Match the Genre\n\n| Genre | Useful editing | Avoid forcing |\n|---|---|---|\n| technical reference | exact terms, clear conditions, scannable structure | slang, story openings, rhetorical questions, sales CTA |\n| explanation\u002Ftutorial | prerequisites and action\u002Fresult sequence | an untested command described as verified |\n| analysis | separate observation, inference and limits | stronger causal claims than the evidence supports |\n| personal narrative | the author's supplied experiences and voice | invented first-person testimony |\n| marketing | a supported benefit and relevant next action | fabricated testimonials, percentages or guarantees |\n\nContractions, fragments, humour, analogies and direct address are options, not\nquotas. Use them when they fit the audience and improve comprehension.\nParallel lists and consistent terminology can be desirable in documentation.\n\n## Editing Procedure\n\n1. Identify the reader's task, genre, source material and protected facts from\n   the existing request and draft. Do not add an unnecessary intake questionnaire.\n2. Remove empty intensifiers and duplicated ideas. Use direct verbs when meaning\n   is preserved; keep connectors that express real causality or contrast.\n3. Clarify who acts, on what, under which conditions and with what result.\n   Do not supply a result that the source does not establish.\n4. Fix awkward rhythm where it hinders reading. Do not maximize variation,\n   enforce a paragraph pattern or replace terms to appear less predictable.\n5. Compare input and output for semantic changes. Check quantities with their\n   units, denominator, time frame and uncertainty, not just the numeral.\n6. Return the edited text and any necessary factual caveat. Once the edit is\n   sufficient, continue the remaining requested publication workflow rather\n   than starting another stylistic pass automatically.\n\n## Examples: Same Facts, Clearer Prose\n\n| Supplied text | Faithful edit |\n|---|---|\n| In order to load the file, the user must select Open. | To load the file, select Open. |\n| The tool may reduce processing time; no benchmark is available. | The tool may save processing time, but no benchmark is available. |\n| Some testers reported failures. The sample size was not recorded. | Some testers reported failures; the sample size was not recorded. |\n| On 2026-09-01, 12 of 40 runs failed with version 2.1. | With version 2.1, 12 of 40 runs failed on 2026-09-01. |\n\nThese are editing fixtures, not results from a deployed product. Unknown sample\nsize stays unknown; a date, denominator and version do not disappear for fluency.\n\n## Verification\n\n- Every changed factual assertion still maps to the supplied material or a\n  source actually checked for this task.\n- Conditions, uncertainty, negatives, numbers, units, dates, versions and code\n  are preserved unless an evidence-backed factual correction was requested.\n- The result helps its intended reader without an unrequested genre change.\n- No invented testimony or detector-evasion claim was added.\n\nA no-change verdict is valid for an already clear passage. Do not add numbers,\nquestions, opinions, deliberate errors or fake admissions to satisfy a score.\n\n## Gotchas\n\n- **Detector score as evidence:** it establishes neither authorship nor factual\n  accuracy. Do not promise an undetectable edit.\n- **Replacing every vague quantity:** guessing a plausible percentage fabricates\n  evidence when the sample size is unknown.\n- **Forced informality:** slang can make a reference harder to understand,\n  particularly for readers using English as an additional language.\n- **Synonym churn:** repeating a technical term is safer than creating a false\n  distinction through alternate names.\n- **Example contamination:** a skill example is not an event that happened to\n  the user or author.\n\n## Troubleshooting\n\n| Symptom | Check | Correction |\n|---|---|---|\n| polished but unsupported claim | source scope and conditions | restore supported meaning or remove the claim |\n| bureaucratic phrasing | action and actor | use a direct sentence without changing obligations |\n| repetitive text | repeated meaning versus necessary terms | cut redundancy, keep precise terminology |\n| reference sounds like an advertisement | requested genre | remove promotion and invented narrative |\n| detector flags the passage | actual writing and detector limitations | repair evidenced defects, not a guessed authorship score |\n\n## Sources and Maintenance\n\nReviewed 2026-09-06. Owner: the existing writing-skill maintainers. Change through\ncanonical Git, focused before\u002Fafter fixtures, independent review and the supported\ninstaller; retain the prior revision and installation backup for rollback.\nRefresh sources when guidance changes or a factual\u002Fgenre regression is observed,\nnot by automatically rewriting working prose on a schedule.\n\n- [Developer documentation voice and tone](https:\u002F\u002Fdevelopers.google.com\u002Fstyle\u002Ftone),\n  updated 2026-05-27: clarity and audience matter more than forced informality.\n- [GPT detectors are biased against non-native English writers](https:\u002F\u002Farxiv.org\u002Fabs\u002F2304.02819),\n  revised 2023-07-10: limitations of the evaluated detectors, not a test of every\n  current detector or a guarantee about any individual passage.\n- [Excess vocabulary in biomedical publications](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.07016),\n  revised 2025-07-03: corpus-level biomedical analysis, not an individual-author\n  test or a prescriptive word blacklist.\n","# Clear, Natural English Editing\n\nImprove the reader's understanding, not a detector score. A good reference can\nhave repeated terminology, regular tables, definitions and no anecdote.\nKeep the user's intended voice and the destination's format.\n\n## Facts Are Not Style Material\n\n- Preserve supplied numbers, units, dates, versions, names, citations, negation,\n  uncertainty and claim scope. Do not silently update a historical date.\n- Never invent a count, quote, interview, personal experience, experiment,\n  failure, comparison or source to make prose more vivid.\n- Add specificity only when the supporting evidence supplies it. If no\n  measurement exists, retain uncertainty or remove an unsupported claim.\n  An unsupplied number is not an improvement over a vague quantity.\n- Label illustrative scenarios as hypothetical. Do not present them as a real\n  case study or treat their invented values as proof of a product claim.\n- Preserve identifiers, executable code and technical obligations. Words such\n  as may, must, can and will are not interchangeable style alternatives.\n- Reuse provided facts without asking the user to repeat them. Research a\n  material factual gap when research is in scope; otherwise identify the gap\n  without manufacturing an answer or blocking supported edits.\n\n## Match the Genre\n\n| Genre | Useful editing | Avoid forcing |\n|---|---|---|\n| technical reference | exact terms, clear conditions, scannable structure | slang, story openings, rhetorical questions, sales CTA |\n| explanation\u002Ftutorial | prerequisites and action\u002Fresult sequence | an untested command described as verified |\n| analysis | separate observation, inference and limits | stronger causal claims than the evidence supports |\n| personal narrative | the author's supplied experiences and voice | invented first-person testimony |\n| marketing | a supported benefit and relevant next action | fabricated testimonials, percentages or guarantees |\n\nContractions, fragments, humour, analogies and direct address are options, not\nquotas. Use them when they fit the audience and improve comprehension.\nParallel lists and consistent terminology can be desirable in documentation.\n\n## Editing Procedure\n\n1. Identify the reader's task, genre, source material and protected facts from\n   the existing request and draft. Do not add an unnecessary intake questionnaire.\n2. Remove empty intensifiers and duplicated ideas. Use direct verbs when meaning\n   is preserved; keep connectors that express real causality or contrast.\n3. Clarify who acts, on what, under which conditions and with what result.\n   Do not supply a result that the source does not establish.\n4. Fix awkward rhythm where it hinders reading. Do not maximize variation,\n   enforce a paragraph pattern or replace terms to appear less predictable.\n5. Compare input and output for semantic changes. Check quantities with their\n   units, denominator, time frame and uncertainty, not just the numeral.\n6. Return the edited text and any necessary factual caveat. Once the edit is\n   sufficient, continue the remaining requested publication workflow rather\n   than starting another stylistic pass automatically.\n\n## Examples: Same Facts, Clearer Prose\n\n| Supplied text | Faithful edit |\n|---|---|\n| In order to load the file, the user must select Open. | To load the file, select Open. |\n| The tool may reduce processing time; no benchmark is available. | The tool may save processing time, but no benchmark is available. |\n| Some testers reported failures. The sample size was not recorded. | Some testers reported failures; the sample size was not recorded. |\n| On 2026-09-01, 12 of 40 runs failed with version 2.1. | With version 2.1, 12 of 40 runs failed on 2026-09-01. |\n\nThese are editing fixtures, not results from a deployed product. Unknown sample\nsize stays unknown; a date, denominator and version do not disappear for fluency.\n\n## Verification\n\n- Every changed factual assertion still maps to the supplied material or a\n  source actually checked for this task.\n- Conditions, uncertainty, negatives, numbers, units, dates, versions and code\n  are preserved unless an evidence-backed factual correction was requested.\n- The result helps its intended reader without an unrequested genre change.\n- No invented testimony or detector-evasion claim was added.\n\nA no-change verdict is valid for an already clear passage. Do not add numbers,\nquestions, opinions, deliberate errors or fake admissions to satisfy a score.\n\n## Gotchas\n\n- **Detector score as evidence:** it establishes neither authorship nor factual\n  accuracy. Do not promise an undetectable edit.\n- **Replacing every vague quantity:** guessing a plausible percentage fabricates\n  evidence when the sample size is unknown.\n- **Forced informality:** slang can make a reference harder to understand,\n  particularly for readers using English as an additional language.\n- **Synonym churn:** repeating a technical term is safer than creating a false\n  distinction through alternate names.\n- **Example contamination:** a skill example is not an event that happened to\n  the user or author.\n\n## Troubleshooting\n\n| Symptom | Check | Correction |\n|---|---|---|\n| polished but unsupported claim | source scope and conditions | restore supported meaning or remove the claim |\n| bureaucratic phrasing | action and actor | use a direct sentence without changing obligations |\n| repetitive text | repeated meaning versus necessary terms | cut redundancy, keep precise terminology |\n| reference sounds like an advertisement | requested genre | remove promotion and invented narrative |\n| detector flags the passage | actual writing and detector limitations | repair evidenced defects, not a guessed authorship score |\n\n## Sources and Maintenance\n\nReviewed 2026-09-06. Owner: the existing writing-skill maintainers. Change through\ncanonical Git, focused before\u002Fafter fixtures, independent review and the supported\ninstaller; retain the prior revision and installation backup for rollback.\nRefresh sources when guidance changes or a factual\u002Fgenre regression is observed,\nnot by automatically rewriting working prose on a schedule.\n\n- [Developer documentation voice and tone](https:\u002F\u002Fdevelopers.google.com\u002Fstyle\u002Ftone),\n  updated 2026-05-27: clarity and audience matter more than forced informality.\n- [GPT detectors are biased against non-native English writers](https:\u002F\u002Farxiv.org\u002Fabs\u002F2304.02819),\n  revised 2023-07-10: limitations of the evaluated detectors, not a test of every\n  current detector or a guarantee about any individual passage.\n- [Excess vocabulary in biomedical publications](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.07016),\n  revised 2025-07-03: corpus-level biomedical analysis, not an individual-author\n  test or a prescriptive word blacklist.\n",{"name":5,"metadata":23,"description":26},{"version":24,"reviewed":25},"2.0.0","2026-09-06","Edit English drafts for clear, natural language while preserving facts, uncertainty,\ntechnical meaning, citations and genre. Use when: humanize this text, remove AI-style\nfiller, improve English prose, or edit an English article before publication.\nNot an authorship detector or a promise to bypass one. For Russian use\nhumanize-russian; for thesis\u002Fevidence and structure use article-structure-review.\n","main","07d02526f424fc814f8350d6b0b728e81576603d","upstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fwriting\u002Fhumanize-english",0,"https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit","https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot","2026-11-14 18:25:27",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add hermes-jarvis-bot\u002Fhermes-agent-config-kit --skill humanize-english",{"tool":40,"command":41},"bunx","bunx skills add hermes-jarvis-bot\u002Fhermes-agent-config-kit --skill humanize-english",{"tool":43,"command":44},"pnpm","pnpm dlx skills add hermes-jarvis-bot\u002Fhermes-agent-config-kit --skill humanize-english","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fwriting\u002Fhumanize-english\u002FSKILL.md",true,[],[49,55,62,69,76,83],{"skillNo":50,"name":51,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":18},"01M78BHH6VNT0MKZXGMP2F50X1","owner-voice","https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fwriting\u002Fowner-voice\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":18},"01M78BHD34XJHAK6EMZ7J1M80X","humanize-russian","Редактировать русский текст для ясности и естественного звучания, сохраняя факты,\nтермины, источники и жанр. Использовать когда: убрать канцелярит, сделать текст\nживее, отредактировать русский черновик или статью перед публикацией.\nНе определяет авторство и не обещает обход детекторов. Для английского —\nhumanize-english; для структуры и доказательств — article-structure-review.","https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fwriting\u002Fhumanize-russian\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":18},"01M78BH44Q25YMA16MC6FKZ2WY","caveman","Ultra-compressed reply mode. Cuts output tokens ~65-75% by answering in terse \"caveman\" style while keeping full technical accuracy, and shapes what survives: action first, state restated every turn, concrete time estimates, visible wins. Intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says \"caveman\", \"talk like caveman\", \"use caveman\", \"less tokens\", \"be brief\", or Russian \"пещерный режим\", \"говори как пещерный\", \"кратко\", \"меньше токенов\", \"экономь токены\" — or invokes \u002Fcaveman. Preserves the user's language (Russian in → Russian caveman out). Off only: \"stop caveman\" \u002F \"normal mode\" \u002F \"обычный режим\". Do not use merely because a response should be concise, and do not use when the user requests normal prose, a polished document, or exact wording.","https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fwriting\u002Fcaveman\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":18},"01M78BGY0JTMTW3J3YE5RQTHCK","article-structure-review","Проверить структуру технической статьи после черновика: задача читателя, жанр,\nопора значимых утверждений на доказательства и честные ограничения.\nUse after the first draft, before publication. Исправлять структуру, когда это\nвходит в запрос; не создавать обязательный конвейер из других навыков.\nДля локальной языковой редактуры — humanize-english или humanize-russian.","https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fwriting\u002Farticle-structure-review\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M78BGRJYZGK1TNTCHWGY32W3","video-post-production","Video post-production rules: audio mastering, color, captions, platform export. Use when: 'add music', 'add voiceover', 'export for tiktok', 'add captions', 'color grade', 'audio levels', 'master audio', 'export settings', 'platform requirements'. Covers FFmpeg patterns, audio chain, subtitle standards, and platform-specific export configs. Do NOT use to generate or animate the video frames\u002Fscenes in code (use remotion-production-guide), to write the script (use video-narrative-arc), or to evaluate script quality (use script-evaluator); this is the finishing stage applied to an already-rendered video.","https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fvideo-production\u002Fvideo-post-production\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M78BGK0XZ3NZF723WG4014B6","video-narrative-arc","Proven narrative arc templates for product videos and ads. Use when: 'write script', 'video structure', 'narrative arc', 'scene plan', 'storyboard', '15 second video', '30 second video', '60 second video', 'how to structure the video', 'video script template'. Provides beat-by-beat templates with timing, emotional arc mapping, hook formulas, and pacing rules. Covers 10s-90s formats for social, product demos, launches, and pitches. Do NOT use to judge or score an already-written script (use script-evaluator), to derive the product insight\u002Fbrief from scratch (use product-meaning-extractor), or to render the video in code (use remotion-production-guide); this stage only produces the structured script\u002Fbeats.","https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fvideo-production\u002Fvideo-narrative-arc\u002FSKILL.md",[],[]]