[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MGE31JC1H2NTR6MRPBAG3M":3,"skill-same:01M6MGE31JC1H2NTR6MRPBAG3M":94},{"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":33,"publishedAt":54,"linkOnly":55,"markdownContent":56,"markdownBody":57,"frontMatter":58,"refName":74,"commitSha":75,"skillDirectory":76,"forksCount":13,"repositoryHtmlUrl":77,"repositoryHomepageUrl":6,"ownerHtmlUrl":78,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":79,"install":80,"resources":93},"01M6MGE31JC1H2NTR6MRPBAG3M","md-document",null,"Converts long-form markdown (specs, RFCs, reports, plans, explainers) into a single-file, lightly-interactive HTML document with sticky TOC, scrollspy, search filter, code-copy buttons, and design-system-driven brand tokens. Triggers when the markdown-html-orchestrator classifies an input as DOCUMENT, or when invoked directly via \u002Fcs:md-document. Reads the design-system config via config_loader.py and inlines the user's 12 derived CSS custom properties; refuses to render if onboarding hasn't run. Single-file output — Google Fonts + Prism.js CDN are the only externals; no framework runtime, no build step. Use after orchestrator routing or after design-system onboarding is confirmed.","JiayiV\u002Fquestion_mixing","JiayiV","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54466889?v=4","01M6JFJYYMRZ3QRGP9339JNQ2K","01M6JFJZ35KB0QVT50NAHPJA7G",0,"MIT","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fpublic-02-claude-skills-main-gemini-skills-md-document-skill-0935c9dd\u002FSKILL.md",[17,22,25,28],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":26,"categoryName":27,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":29,"categoryName":30,"taxonomyType":31,"taxonomyTypeDesc":32},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53],"document","md document","orchestrator","sticky","fonts","render","prism","filter","reports","opencode","only","design","markdown","search","code","run","documentation","config","css","cli","2026-11-10 10:12:30",false,"---\nname: md-document\ndescription: Converts long-form markdown (specs, RFCs, reports, plans, explainers) into a single-file, lightly-interactive HTML document with sticky TOC, scrollspy, search filter, code-copy buttons, and design-system-driven brand tokens. Triggers when the markdown-html-orchestrator classifies an input as DOCUMENT, or when invoked directly via \u002Fcs:md-document. Reads the design-system config via config_loader.py and inlines the user's 12 derived CSS custom properties; refuses to render if onboarding hasn't run. Single-file output — Google Fonts + Prism.js CDN are the only externals; no framework runtime, no build step. Use after orchestrator routing or after design-system onboarding is confirmed.\nversion: 2.10.1\nauthor: Alireza Rezvani\nlicense: MIT\ntags: [markdown, html, documentation, single-file, toc, scrollspy, search, code-copy, design-system]\ncompatible_tools: [claude-code, codex-cli, cursor, antigravity, opencode, gemini-cli]\n---\n\n# md-document — Long-form Markdown to HTML\n\nThe general-purpose converter — handles the 90% case Shihipar describes (specs, plans, RFCs, reports, explainers). Three stdlib tools pipeline together:\n\n```\nmarkdown_parser.py  →  html_renderer.py  →  interactivity_injector.py\n   (md → JSON AST)    (AST + tokens → HTML)    (HTML + JS behavior)\n```\n\nOutput is one `.html` file with sticky TOC, search filter, scrollspy, code-copy buttons, and the user's 12 derived brand tokens. Externals limited to Google Fonts CSS + Prism.js CDN.\n\n## When to invoke\n\n| Symptom | Action |\n|---|---|\n| `markdown-html-orchestrator` routes input as DOCUMENT | Invoke this skill |\n| User runs `\u002Fcs:md-document \u003Cpath>.md` directly | Invoke this skill |\n| User says \"convert this spec\u002Freport\u002FRFC\u002Fplan to HTML\" | Invoke this skill |\n| Input is a code review (has ` ```diff ` blocks) | Route to `md-review` instead |\n| Input is a slide deck (clear `---` boundaries) | Route to `md-slides` instead |\n| Input is \u003C 100 lines | Refuse (Shihipar threshold — markdown still wins) |\n| Design-system not onboarded | Refuse, surface `\u002Fcs:design-system` |\n\n## Pipeline\n\n```bash\n# 1. Parse markdown → JSON AST\npython3 markdown-html\u002Fskills\u002Fmd-document\u002Fscripts\u002Fmarkdown_parser.py \\\n    --input \u003Cpath>.md --output sections.json\n\n# 2. Render AST + design-system config → single-file HTML\npython3 markdown-html\u002Fskills\u002Fmd-document\u002Fscripts\u002Fhtml_renderer.py \\\n    --sections sections.json --output document.html\n\n# 3. Inject lightweight JS (search, copycode, smoothscroll, scrollspy)\npython3 markdown-html\u002Fskills\u002Fmd-document\u002Fscripts\u002Finteractivity_injector.py \\\n    --file document.html \\\n    --features search,copycode,smoothscroll,scrollspy\n```\n\nOr all-in-one (sample render):\n\n```bash\npython3 markdown-html\u002Fskills\u002Fmd-document\u002Fscripts\u002Fhtml_renderer.py --sample \\\n  | python3 markdown-html\u002Fskills\u002Fmd-document\u002Fscripts\u002Finteractivity_injector.py \\\n      --file \u002Fdev\u002Fstdin --output document.html\n```\n\n## What gets rendered\n\nCommonMark subset sufficient for agent-generated artifacts:\n- Headings H1-H6 (every H2+ gets an anchor id and TOC entry)\n- Paragraphs with inline **bold** \u002F *italic* \u002F `code` \u002F [links](url) \u002F ![images](url)\n- Fenced code blocks (` ```python `) with Prism.js highlighting on demand\n- GFM tables with per-column alignment\n- GFM callouts (`> [!NOTE]`, `> [!TIP]`, `> [!IMPORTANT]`, `> [!WARNING]`, `> [!CAUTION]`)\n- Blockquotes, ordered + unordered lists (single-level), horizontal rules\n\nOut of scope: nested lists, HTML inlines, footnotes, definition lists, task list checkboxes (rendered as plain text), reference-style links.\n\n## Hard rules\n\n1. **Refuses input \u003C 100 lines.** Markdown wins below the threshold (Shihipar).\n2. **Refuses without onboarding.** `config_loader.setup_completed()` must return `True`. Otherwise surface `\u002Fcs:design-system`.\n3. **Single-file output.** All CSS + JS inline. Only externals are `fonts.googleapis.com` and `cdn.jsdelivr.net` (Prism). Anything else is a regression.\n4. **Customization must change behavior.** `design_style=editorial` produces 720px-wide layout with 1.75 line-height; `playful` rounds the callouts and adds shadow; `technical` is dense with 0.875rem code. Smoke-tested.\n5. **WCAG-compliant tokens.** Inherits the design-system's WCAG AA palette — body text ≥ 4.5:1 contrast, links iteratively walked to 4.5:1.\n6. **Idempotent injection.** Re-injecting interactivity is a no-op (marker check). Re-rendering with a different design_style works cleanly.\n\n## Forcing-question library (Matt Pocock grill discipline)\n\n1. **What's the document for — skim, decide, or deep-read?** Recommended: name it; density follows. Canon: Shihipar; Tufte *Envisioning Information*.\n2. **Sticky-sidebar TOC or collapsible-top?** Recommended: sticky-sidebar for > 800 words \u002F 4+ H2s; collapsible-top for shorter mobile-first docs. Canon: NN\u002Fg *TOC Best Practices* (2023).\n3. **All four interactive features, or a subset?** Recommended: all four — none of them cost more than ~1 KB. Canon: Wattenberger *Why React isn't great for actually building websites*.\n4. **Code theme — light, dark, or auto?** Recommended: auto (follows OS `prefers-color-scheme`). Canon: WCAG 2.2 §1.4.3.\n5. **Does the document have a clear H1 title?** Recommended: yes — H1 becomes the page `\u003Ctitle>` and is excluded from the TOC.\n\n## Distinct from\n\n- **`md-review`** — that converter renders diff blocks + severity-tagged margin annotations. This one renders prose + tables + code + callouts.\n- **`md-slides`** — that converter splits on `---` boundaries into slides. This one renders one continuous document.\n- **`marketing\u002Flanding\u002F`** — that generates landing pages from scratch (no markdown input). This converts existing markdown.\n\n## Output artifact\n\n`{default_output_dir}\u002Fdoc-{slug}.html` (path resolved by orchestrator's `output_path_resolver.py`; collision suffix `-2`, `-3`, … by default).\n\n## References\n\n- Shihipar — *Claude Code HTML output* (Medium, 2026)\n- Tufte — *Envisioning Information* (1990), ch. 2 \"Micro\u002FMacro Readings\"\n- NN\u002Fg — *Table of Contents Best Practices* (2023)\n- WCAG 2.2 — §1.4.3 contrast, §2.4.5 multiple ways\n- Wattenberger — *Why React isn't great for actually building websites*\n- See `references\u002F` for full citations\n","# md-document — Long-form Markdown to HTML\n\nThe general-purpose converter — handles the 90% case Shihipar describes (specs, plans, RFCs, reports, explainers). Three stdlib tools pipeline together:\n\n```\nmarkdown_parser.py  →  html_renderer.py  →  interactivity_injector.py\n   (md → JSON AST)    (AST + tokens → HTML)    (HTML + JS behavior)\n```\n\nOutput is one `.html` file with sticky TOC, search filter, scrollspy, code-copy buttons, and the user's 12 derived brand tokens. Externals limited to Google Fonts CSS + Prism.js CDN.\n\n## When to invoke\n\n| Symptom | Action |\n|---|---|\n| `markdown-html-orchestrator` routes input as DOCUMENT | Invoke this skill |\n| User runs `\u002Fcs:md-document \u003Cpath>.md` directly | Invoke this skill |\n| User says \"convert this spec\u002Freport\u002FRFC\u002Fplan to HTML\" | Invoke this skill |\n| Input is a code review (has ` ```diff ` blocks) | Route to `md-review` instead |\n| Input is a slide deck (clear `---` boundaries) | Route to `md-slides` instead |\n| Input is \u003C 100 lines | Refuse (Shihipar threshold — markdown still wins) |\n| Design-system not onboarded | Refuse, surface `\u002Fcs:design-system` |\n\n## Pipeline\n\n```bash\n# 1. Parse markdown → JSON AST\npython3 markdown-html\u002Fskills\u002Fmd-document\u002Fscripts\u002Fmarkdown_parser.py \\\n    --input \u003Cpath>.md --output sections.json\n\n# 2. Render AST + design-system config → single-file HTML\npython3 markdown-html\u002Fskills\u002Fmd-document\u002Fscripts\u002Fhtml_renderer.py \\\n    --sections sections.json --output document.html\n\n# 3. Inject lightweight JS (search, copycode, smoothscroll, scrollspy)\npython3 markdown-html\u002Fskills\u002Fmd-document\u002Fscripts\u002Finteractivity_injector.py \\\n    --file document.html \\\n    --features search,copycode,smoothscroll,scrollspy\n```\n\nOr all-in-one (sample render):\n\n```bash\npython3 markdown-html\u002Fskills\u002Fmd-document\u002Fscripts\u002Fhtml_renderer.py --sample \\\n  | python3 markdown-html\u002Fskills\u002Fmd-document\u002Fscripts\u002Finteractivity_injector.py \\\n      --file \u002Fdev\u002Fstdin --output document.html\n```\n\n## What gets rendered\n\nCommonMark subset sufficient for agent-generated artifacts:\n- Headings H1-H6 (every H2+ gets an anchor id and TOC entry)\n- Paragraphs with inline **bold** \u002F *italic* \u002F `code` \u002F [links](url) \u002F ![images](url)\n- Fenced code blocks (` ```python `) with Prism.js highlighting on demand\n- GFM tables with per-column alignment\n- GFM callouts (`> [!NOTE]`, `> [!TIP]`, `> [!IMPORTANT]`, `> [!WARNING]`, `> [!CAUTION]`)\n- Blockquotes, ordered + unordered lists (single-level), horizontal rules\n\nOut of scope: nested lists, HTML inlines, footnotes, definition lists, task list checkboxes (rendered as plain text), reference-style links.\n\n## Hard rules\n\n1. **Refuses input \u003C 100 lines.** Markdown wins below the threshold (Shihipar).\n2. **Refuses without onboarding.** `config_loader.setup_completed()` must return `True`. Otherwise surface `\u002Fcs:design-system`.\n3. **Single-file output.** All CSS + JS inline. Only externals are `fonts.googleapis.com` and `cdn.jsdelivr.net` (Prism). Anything else is a regression.\n4. **Customization must change behavior.** `design_style=editorial` produces 720px-wide layout with 1.75 line-height; `playful` rounds the callouts and adds shadow; `technical` is dense with 0.875rem code. Smoke-tested.\n5. **WCAG-compliant tokens.** Inherits the design-system's WCAG AA palette — body text ≥ 4.5:1 contrast, links iteratively walked to 4.5:1.\n6. **Idempotent injection.** Re-injecting interactivity is a no-op (marker check). Re-rendering with a different design_style works cleanly.\n\n## Forcing-question library (Matt Pocock grill discipline)\n\n1. **What's the document for — skim, decide, or deep-read?** Recommended: name it; density follows. Canon: Shihipar; Tufte *Envisioning Information*.\n2. **Sticky-sidebar TOC or collapsible-top?** Recommended: sticky-sidebar for > 800 words \u002F 4+ H2s; collapsible-top for shorter mobile-first docs. Canon: NN\u002Fg *TOC Best Practices* (2023).\n3. **All four interactive features, or a subset?** Recommended: all four — none of them cost more than ~1 KB. Canon: Wattenberger *Why React isn't great for actually building websites*.\n4. **Code theme — light, dark, or auto?** Recommended: auto (follows OS `prefers-color-scheme`). Canon: WCAG 2.2 §1.4.3.\n5. **Does the document have a clear H1 title?** Recommended: yes — H1 becomes the page `\u003Ctitle>` and is excluded from the TOC.\n\n## Distinct from\n\n- **`md-review`** — that converter renders diff blocks + severity-tagged margin annotations. This one renders prose + tables + code + callouts.\n- **`md-slides`** — that converter splits on `---` boundaries into slides. This one renders one continuous document.\n- **`marketing\u002Flanding\u002F`** — that generates landing pages from scratch (no markdown input). This converts existing markdown.\n\n## Output artifact\n\n`{default_output_dir}\u002Fdoc-{slug}.html` (path resolved by orchestrator's `output_path_resolver.py`; collision suffix `-2`, `-3`, … by default).\n\n## References\n\n- Shihipar — *Claude Code HTML output* (Medium, 2026)\n- Tufte — *Envisioning Information* (1990), ch. 2 \"Micro\u002FMacro Readings\"\n- NN\u002Fg — *Table of Contents Best Practices* (2023)\n- WCAG 2.2 — §1.4.3 contrast, §2.4.5 multiple ways\n- Wattenberger — *Why React isn't great for actually building websites*\n- See `references\u002F` for full citations\n",{"name":5,"tags":59,"author":66,"license":14,"version":67,"description":7,"compatible_tools":68},[46,60,50,61,62,63,47,64,65],"html","single-file","toc","scrollspy","code-copy","design-system","Alireza Rezvani","2.10.1",[69,70,71,72,43,73],"claude-code","codex-cli","cursor","antigravity","gemini-cli","main","068c2486ccc0f8d200a3db4d21ec137064eda3b4","skills\u002Fpublic-02-claude-skills-main-gemini-skills-md-document-skill-0935c9dd","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing","https:\u002F\u002Fgithub.com\u002FJiayiV","2026-08-25 16:30:52",{"source":8,"skillName":5,"commands":81,"prompt":91,"zipAvailable":92},[82,85,88],{"tool":83,"command":84},"npx","npx skills add JiayiV\u002Fquestion_mixing --skill md-document",{"tool":86,"command":87},"bunx","bunx skills add JiayiV\u002Fquestion_mixing --skill md-document",{"tool":89,"command":90},"pnpm","pnpm dlx skills add JiayiV\u002Fquestion_mixing --skill md-document","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fpublic-02-claude-skills-main-gemini-skills-md-document-skill-0935c9dd\u002FSKILL.md",true,[],[95,120,146,177,204,236],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":54},"01M6NN9PJS9NHWPDG4QP93BP8F","webmcpify","Make a web app agent-ready — propose a WebMCP tool manifest, integrate, verify in a real browser, heal; unrelated code stays untouched. Use for \"webmcpify\", \"add WebMCP\", or \"expose app actions to AI agents\".","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fwebmcpify\u002FSKILL.md",[],[97,102,103,104,105,48,106,107,108,109,110,111,112,113,114,115,116,117,118,119],"github","ai agents","web","notes","browser","https","actions","manifest","inventory","verify","tool","use","ready","unrelated","app","scope","for","webmcp",{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":124,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":54},"01M6NN6KZE5RBN6NGHN2WXV1RE","vardoger-analyze","Use when the user asks to personalize the GitHub Copilot CLI assistant, adapt Copilot to their style, use vardoger, or analyze their Copilot CLI conversation history. Reads the local session directory at `~\u002F.copilot\u002Fsession-state\u002F`, extracts recurring preferences and conventions, and writes a fenced personalization block into `~\u002F.copilot\u002Fcopilot-instructions.md`. Runs entirely on the user's machine via the local `vardoger` CLI (`pipx install vardoger`); no network calls and no uploads. Triggers: 'personalize my copilot', 'analyze my copilot history', 'tailor copilot to me', 'run vardoger', 'update my copilot instructions from history', 'make copilot learn my style'.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fvardoger-analyze\u002FSKILL.md",[],[128,129,130,53,131,132,49,133,134,135,136,137,138,139,140,141,142,143,144,145],"vardoger analyze","analyze","directory","github copilot","copilot","update","learn","network","my style","install","conversation","me","local","github copilot cli","pipx","my","at","copilot instructions",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":158,"publishedAt":54},"01M6NN3CZGQP3XAJ04BM1NNYGT","transloadit-media-processing","Process media files (video, audio, images, documents) using Transloadit. Use when asked to encode video to HLS\u002FMP4, generate thumbnails, resize or watermark images, extract audio, concatenate clips, add subtitles, OCR documents, or run any media processing pipeline. Covers 86+ processing robots for file transformation at scale.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Ftransloadit-media-processing\u002FSKILL.md",[152,155],{"categoryNo":153,"categoryName":154,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":156,"categoryName":157,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[159,160,161,162,163,164,165,166,167,168,169,170,171,113,172,173,174,175,118,176],"transloadit media processing","Media","media processing","processing","MCP","mcp server","documents","subtitles","pipeline","ocr","Video","Audio","mp4","images","files","transformation","free","hls",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":186,"publishedAt":54},"01M6NN28E92F9GH4WFYQ2H1Y15","terraform-azurerm-set-diff-analyzer","Analyze Terraform plan JSON output for AzureRM Provider to distinguish between false-positive diffs (order-only changes in Set-type attributes) and actual resource changes. Use when reviewing terraform plan output for Azure resources like Application Gateway, Load Balancer, Firewall, Front Door, NSG, and other resources with Set-type attributes that cause spurious diffs due to internal ordering changes.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fterraform-azurerm-set-diff-analyzer\u002FSKILL.md",[183],{"categoryNo":184,"categoryName":185,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[187,188,189,190,191,192,193,194,195,113,44,196,197,198,199,200,201,202,203,118],"terraform","SET","terraform azurerm set diff analyzer","diff","analyzer","diffs","azure","gateway","firewall","resource changes","provider","resources","load balancer","attributes","front","load","balancer",{"skillNo":205,"name":206,"nameZh":6,"description":207,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":208,"categories":209,"keywords":219,"publishedAt":54},"01M6NN1QMH2TDYWTH3XY3N5XPV","technical-job-search","Use this skill when a software engineer asks for help with job search tasks: parsing or analyzing a job description, tailoring a CV\u002Fresume, writing a cover letter, evaluating a job offer, or drafting a post-interview follow-up email. Do not activate for general career advice unrelated to an active job search action.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Ftechnical-job-search\u002FSKILL.md",[210,213,216],{"categoryNo":211,"categoryName":212,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":214,"categoryName":215,"taxonomyType":31,"taxonomyTypeDesc":32},"01JBSEEDCAT000000000000036","内容创作者",{"categoryNo":217,"categoryName":218,"taxonomyType":31,"taxonomyTypeDesc":32},"01JBSEEDCAT000000000000038","人力资源",[47,220,221,222,223,224,225,226,129,227,113,228,229,230,231,232,233,234,118,235],"Job Search","technical job search","technical","writing","tasks","email","parsing","interview","up","engineer","general","activate","do","task","cv","letter",{"skillNo":237,"name":238,"nameZh":6,"description":239,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":240,"categories":241,"keywords":242,"publishedAt":54},"01M6NMZFA67XYS1GS09WT42235","steno-mode","Shorthand-first response compression that cuts ~40% of response tokens while preserving technical precision and exact literals. Use when the user says \"steno mode\", \"shorthand mode\", \"compressed responses\", \"token reduction\", \"brief structured output\", or invokes \u002Fsteno. Supports four compression levels: lite, brief, court, machine. Do not trigger for requests needing polished prose such as onboarding\u002Ftutorial content, stakeholder or customer-facing copy, or teaching-focused explanations.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fsteno-mode\u002FSKILL.md",[],[243,244,245,246,247,222,248,113,232,249,250,251,252,253,254,255,256,257,118,258],"steno mode","mode","customer","brief","first","tutorial","teaching","tokens","as","trigger","structured output","machine","output","court","requests","response compression"]