[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MGCDJG5KXS62FXVT0NTBRF":3,"skill-same:01M6MGCDJG5KXS62FXVT0NTBRF":97},{"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":36,"publishedAt":57,"linkOnly":58,"markdownContent":59,"markdownBody":60,"frontMatter":61,"refName":77,"commitSha":78,"skillDirectory":79,"forksCount":13,"repositoryHtmlUrl":80,"repositoryHomepageUrl":6,"ownerHtmlUrl":81,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":82,"install":83,"resources":96},"01M6MGCDJG5KXS62FXVT0NTBRF","markdown-html-orchestrator",null,"Use when a user wants to convert any markdown file in their Claude project into a single-file, lightly-interactive HTML — long-form documents (specs, plans, RFCs, reports, explainers), code reviews with diffs and severity-tagged annotations, or slide decks. Triggers on \"convert this markdown to HTML\", \"make this an HTML file\", \"turn this into an interactive document\", \"render this report as HTML\", \"PR writeup as HTML\", \"slides from this markdown\". Forks context to route to one of three converter sub-skills (md-document, md-review, md-slides) based on a deterministic doctype classifier, after the user has run the design-system onboarding once. Refuses if input is under 100 lines (per Shihipar — markdown still wins below the threshold) or design-system isn't onboarded. Distinct from Anthropic's official Playground plugin (which is interactive prompt-tuning controls with sliders\u002Fknobs\u002Fprompt-copy-back) and from marketing\u002Flanding\u002F (which is a landing-page generator).","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-markdown-html-orchestrator-skill-5ae40de2\u002FSKILL.md",[17,22,25,28,33],{"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},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":29,"categoryName":30,"taxonomyType":31,"taxonomyTypeDesc":32},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",{"categoryNo":34,"categoryName":35,"taxonomyType":31,"taxonomyTypeDesc":32},"01JBSEEDCAT000000000000038","人力资源",[37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56],"markdown","markdown html orchestrator","orchestrator","html","which","design","reviews","form","slide decks","input","as","project","classifier","context","annotations","slides","severity","run","documents","diffs","2026-11-10 10:12:30",false,"---\nname: markdown-html-orchestrator\ndescription: Use when a user wants to convert any markdown file in their Claude project into a single-file, lightly-interactive HTML — long-form documents (specs, plans, RFCs, reports, explainers), code reviews with diffs and severity-tagged annotations, or slide decks. Triggers on \"convert this markdown to HTML\", \"make this an HTML file\", \"turn this into an interactive document\", \"render this report as HTML\", \"PR writeup as HTML\", \"slides from this markdown\". Forks context to route to one of three converter sub-skills (md-document, md-review, md-slides) based on a deterministic doctype classifier, after the user has run the design-system onboarding once. Refuses if input is under 100 lines (per Shihipar — markdown still wins below the threshold) or design-system isn't onboarded. Distinct from Anthropic's official Playground plugin (which is interactive prompt-tuning controls with sliders\u002Fknobs\u002Fprompt-copy-back) and from marketing\u002Flanding\u002F (which is a landing-page generator).\ncontext: fork\nversion: 2.10.3\nauthor: Alireza Rezvani\nlicense: MIT\ntags: [markdown, html, converter, orchestrator, documentation, code-review, slides, design-system]\ncompatible_tools: [claude-code, codex-cli, cursor, antigravity, opencode, gemini-cli]\n---\n\n# Markdown → HTML — Domain Orchestrator\n\nThariq Shihipar's argument (Claude Code HTML output essay, Medium 2026): **markdown collapses past 100 lines for agent-generated artifacts.** Long specs, code reviews, and architecture explainers lose density, hierarchy, and lightweight interaction the moment they exceed a screen of text. HTML restores all three — single-file, browser-native, shareable.\n\nThis orchestrator forks context, classifies the input markdown deterministically, routes to the right converter sub-skill, and returns a digest with the output path. Heavy intake (full markdown bodies, diffs, slide decks) stays in the forked context.\n\n**Domain status (complete):** all five skills are live — orchestrator + `design-system` (onboarding + shared brand tokens) + the three converter sub-skills (`md-document`, `md-review`, `md-slides`). Always route conversions to the shipped converter's scripts; never hand-render HTML inline.\n\n## When to invoke\n\n| Symptom | Sub-skill |\n|---|---|\n| \"Convert this RFC \u002F spec \u002F report \u002F explainer to HTML\" — long-form doc | `md-document` |\n| \"Turn this PR writeup \u002F code review into HTML\" — markdown with diff blocks | `md-review` |\n| \"Make a slide deck from this markdown\" — `---` boundaries or H1 cadence | `md-slides` |\n\n## Pre-flight gates (hard refusals)\n\n1. **Below the 100-line threshold.** Markdown wins below 100 lines (Shihipar). The classifier prints `below_min_lines: true` and `route_explainer.py` refuses. Tell the user to keep their input as markdown.\n2. **Design-system not onboarded.** If `~\u002F.config\u002Fmarkdown-html\u002Fdesign-system.json` doesn't exist (or its `setup_completed_at` is null), refuse. Point the user at `python3 markdown-html\u002Fskills\u002Fdesign-system\u002Fscripts\u002Fonboard.py` (or `--defaults` for a zero-touch run).\n3. **Unwritable save location.** `output_path_resolver.py` refuses if the configured `default_output_dir` (or `--out` override) isn't writable.\n\n## Routing logic (deterministic)\n\nTwo-signal threshold pattern lifted from `research-ops\u002Fskills\u002Fresearch-ops-skills\u002FSKILL.md`. Filename hint = 2 points; each content signal = 1 point. Silent-route allowed when winner ≥ 3 AND (runner-up = 0 OR winner ≥ 2× runner-up). Below threshold → one clarifying question with a recommended answer.\n\n### Signal table\n\n| Signal class | Filename hints | Content signals | Sub-skill |\n|---|---|---|---|\n| DOCUMENT | `report.md`, `*-doc.md`, `spec.md`, `rfc-*.md`, `*-analysis.md`, `*-explainer.md` | `## Table of Contents` (2), `^# `, `^## `, markdown table rows, `> [!NOTE]\u002F[!TIP]\u002F[!IMPORTANT]` callouts | `md-document` |\n| REVIEW | `review.md`, `*-pr-*.md`, `*.diff.md`, `code-review*.md` | ` ```diff ` (2), `^[-+]{3} ` (2), `^@@` (2), `> [!BLOCKER]\u002F[!MAJOR]\u002F[!MINOR]\u002F[!NIT]` (2), `LGTM`\u002F`nit:`\u002F`blocker:` | `md-review` |\n| SLIDES | `deck.md`, `slides.md`, `*-talk.md`, `presentation*.md` | `^---$` ≥ 3 (2 + per-boundary), `\u003C!-- notes:` (2), H1 count ≥ 5 with median gap ≤ 12 lines (2) | `md-slides` |\n\nThe pipeline:\n\n```bash\npython3 markdown-html\u002Fskills\u002Fmarkdown-html-orchestrator\u002Fscripts\u002Fdoctype_classifier.py \\\n    --input \u003Cpath>.md --output json \\\n  | python3 markdown-html\u002Fskills\u002Fmarkdown-html-orchestrator\u002Fscripts\u002Froute_explainer.py\n```\n\n`route_explainer.py` checks the design-system status, applies the \u003C 100-line refusal, and prints one of: `ROUTE_SILENTLY -> md-\u003Ctype>`, `ASK_USER one question: ...`, or `REFUSE — fix the issues above`.\n\n## Workflow\n\n### Step 1 — Confirm onboarding\n\nIf the user has never run onboarding, surface the one-time setup:\n\n```bash\npython3 markdown-html\u002Fskills\u002Fdesign-system\u002Fscripts\u002Fonboard.py\n```\n\nTen questions, 1-2 minutes. Captures brand primary + accent + heading\u002Fbody Google Fonts + design style (editorial\u002Ftechnical\u002Fminimal\u002Fplayful) + default output dir + syntax theme + TOC behavior + optional logo\u002Fcompany. Stored at `~\u002F.config\u002Fmarkdown-html\u002Fdesign-system.json`. Re-runnable with `--scope project` for per-repo overrides.\n\n### Step 2 — Classify the input\n\nRun `doctype_classifier.py` on the markdown. Inspect the verdict.\n\n### Step 3 — Route or ask\n\nPipe the classification into `route_explainer.py`. If it says `ROUTE_SILENTLY`, forward the original markdown + the design-system config into the named sub-skill's renderer in the forked context. If it says `ASK_USER`, ask ONE question with the recommended answer.\n\n### Step 4 — Resolve the output path\n\n```bash\npython3 markdown-html\u002Fskills\u002Fmarkdown-html-orchestrator\u002Fscripts\u002Foutput_path_resolver.py \\\n    --input \u003Cpath>.md --doctype \u003Cdocument|review|slides>\n```\n\nCollision handling defaults to `-2 \u002F -3 \u002F ...` suffix; `--on-collision timestamp` for stamped names.\n\n### Step 5 — Hand off to the sub-skill\n\nThe routed converter sub-skill's renderer (`md-document\u002Fscripts\u002F`, `md-review\u002Fscripts\u002F`, or `md-slides\u002Fscripts\u002F`) takes the input markdown, the design-system config, and the resolved output path, and writes a single self-contained HTML file. The orchestrator returns a ≤ 100-word digest: input lines, output path, design style applied, top 3 features used (TOC, search, code-copy, etc.), and one forcing question for the user. Never render HTML by hand — the converter scripts own the rendering.\n\n## Forcing-question library (Matt Pocock grill-with-docs pattern)\n\nWalk these one at a time, with a recommended answer per question, citing the canon. Lift this list into `\u002Fcs:grill-markdown-html` for plan-stage interrogation.\n\n1. **What decision does this HTML drive — is the reader skimming, deciding, or presenting?**\n   Recommended: name it first; density follows from purpose. Canon: Shihipar — \"match output format to consumption context\"; Tufte — *Visual Display of Quantitative Information*, ch. 1.\n2. **Is the input markdown ≥ 100 lines?**\n   Recommended: yes — below that, keep it as markdown. Canon: Shihipar — markdown still wins under 100 lines.\n3. **Is the design-system onboarded?**\n   Recommended: yes, globally (`~\u002F.config\u002Fmarkdown-html\u002Fdesign-system.json`). Canon: research-ops onboarding pattern (`research-ops\u002FCLAUDE.md` §8); WCAG 2.2 §1.4.3 (text contrast 4.5:1).\n4. **Where does the output save, and will it overwrite anything?**\n   Recommended: the configured `default_output_dir` with `--on-collision suffix`. Canon: Matt Pocock `handoff` skill — never silently overwrite a working artifact.\n5. **Document type confidence — silent-route or one question?**\n   Recommended: silent-route only when the classifier's verdict is one of `document\u002Freview\u002Fslides` AND `silent_route_allowed: true`. Otherwise ask. Canon: research-ops two-signal threshold (`research-ops\u002Fskills\u002Fresearch-ops-skills\u002FSKILL.md` §\"Routing logic\").\n\nNever run a sub-skill before the lane is locked.\n\n## Assumptions\n\n1. User has a markdown file ≥ 100 lines they want to convert.\n2. User has run onboarding once (`~\u002F.config\u002Fmarkdown-html\u002Fdesign-system.json` exists with `setup_completed_at` populated).\n3. Single-file HTML output is acceptable (no multi-file site, no embedded server, no build step).\n4. Externals limited to Google Fonts CSS + Prism.js CDN (jsdelivr \u002F cdnjs).\n\n## Non-goals\n\n- Not a landing-page generator (use `marketing\u002Flanding\u002F`).\n- Not an interactive prompt-tuning playground (use Anthropic's official `playground` plugin).\n- Not a static-site generator (no multi-file output, no site index).\n- Not a PDF generator (slides use `@media print`; user prints from browser).\n- Not a watch \u002F live-reload pipeline (conversion is one-shot).\n\n## Distinct from\n\n- **Anthropic Playground plugin** (`\u002Fplayground`) — builds interactive controls (sliders, knobs, drag-drop) for prompt tuning, with a copy-prompt-back loop. This plugin converts existing markdown documents to HTML. Different tools for different jobs.\n- **`marketing\u002Flanding\u002F`** — generates landing pages from scratch (Phase-0 intake → 3 sections → branded TSX\u002FHTML). This plugin converts an existing markdown file you already have.\n- **`engineering\u002Fhandoff\u002F` + `productivity\u002Fhandoff\u002F`** — preserve session continuity between Claude conversations. Different artifact type (handoff brief vs. document conversion).\n\n## Output artifacts\n\n| Sub-skill | Artifact | Status |\n|---|---|---|\n| `md-document` | `doc-\u003Cslug>.html` (single file, sticky TOC, collapsibles, search, code-copy, scrollspy) | ✓ live |\n| `md-review` | `review-\u003Cslug>.html` (2-col diff + severity margin notes + jump-nav) | ✓ live |\n| `md-slides` | `deck-\u003Cslug>.html` (arrow-key nav + presenter mode + print-to-PDF) | ✓ live |\n\n## Anti-patterns (do not)\n\n- ❌ Convert markdown \u003C 100 lines — markdown still wins. Refuse and tell the user.\n- ❌ Run the orchestrator before the design-system is onboarded. The output looks broken without tokens.\n- ❌ Silently chain two sub-skills (e.g., \"convert doc AND make slides from it\"). Pick one, finish, ask before chaining.\n- ❌ Use external JS frameworks (React\u002FVue\u002FSvelte). Vanilla JS + IntersectionObserver only. Prism.js CDN is the single exception.\n- ❌ Multi-file output (extracted CSS, asset directories). Single file or nothing — that's the whole point.\n- ❌ Overwrite an existing output file by default. The path resolver suffixes `-2`, `-3`, …; `--on-collision overwrite` is opt-in only.\n\n## References\n\n- Spec: Thariq Shihipar — \"Claude Code HTML output\" (Medium, 2026)\n- Forking pattern: `research-ops\u002Fskills\u002Fresearch-ops-skills\u002FSKILL.md` (`context: fork`, two-signal routing)\n- Customization pattern: `research-ops\u002Fskills\u002Fclinical-research\u002Fscripts\u002F` (`onboard.py`, `config_loader.py`)\n- Brand palette math: `marketing\u002Flanding\u002Fskills\u002Flanding\u002Fscripts\u002Fbrand_palette_validator.py` (WCAG + HSL derive)\n- Information-density canon: Tufte; Shihipar's `thariqs.github.io\u002Fhtml-effectiveness\u002F` gallery; Wattenberger interactive essays; Maggie Appleton digital gardens\n","# Markdown → HTML — Domain Orchestrator\n\nThariq Shihipar's argument (Claude Code HTML output essay, Medium 2026): **markdown collapses past 100 lines for agent-generated artifacts.** Long specs, code reviews, and architecture explainers lose density, hierarchy, and lightweight interaction the moment they exceed a screen of text. HTML restores all three — single-file, browser-native, shareable.\n\nThis orchestrator forks context, classifies the input markdown deterministically, routes to the right converter sub-skill, and returns a digest with the output path. Heavy intake (full markdown bodies, diffs, slide decks) stays in the forked context.\n\n**Domain status (complete):** all five skills are live — orchestrator + `design-system` (onboarding + shared brand tokens) + the three converter sub-skills (`md-document`, `md-review`, `md-slides`). Always route conversions to the shipped converter's scripts; never hand-render HTML inline.\n\n## When to invoke\n\n| Symptom | Sub-skill |\n|---|---|\n| \"Convert this RFC \u002F spec \u002F report \u002F explainer to HTML\" — long-form doc | `md-document` |\n| \"Turn this PR writeup \u002F code review into HTML\" — markdown with diff blocks | `md-review` |\n| \"Make a slide deck from this markdown\" — `---` boundaries or H1 cadence | `md-slides` |\n\n## Pre-flight gates (hard refusals)\n\n1. **Below the 100-line threshold.** Markdown wins below 100 lines (Shihipar). The classifier prints `below_min_lines: true` and `route_explainer.py` refuses. Tell the user to keep their input as markdown.\n2. **Design-system not onboarded.** If `~\u002F.config\u002Fmarkdown-html\u002Fdesign-system.json` doesn't exist (or its `setup_completed_at` is null), refuse. Point the user at `python3 markdown-html\u002Fskills\u002Fdesign-system\u002Fscripts\u002Fonboard.py` (or `--defaults` for a zero-touch run).\n3. **Unwritable save location.** `output_path_resolver.py` refuses if the configured `default_output_dir` (or `--out` override) isn't writable.\n\n## Routing logic (deterministic)\n\nTwo-signal threshold pattern lifted from `research-ops\u002Fskills\u002Fresearch-ops-skills\u002FSKILL.md`. Filename hint = 2 points; each content signal = 1 point. Silent-route allowed when winner ≥ 3 AND (runner-up = 0 OR winner ≥ 2× runner-up). Below threshold → one clarifying question with a recommended answer.\n\n### Signal table\n\n| Signal class | Filename hints | Content signals | Sub-skill |\n|---|---|---|---|\n| DOCUMENT | `report.md`, `*-doc.md`, `spec.md`, `rfc-*.md`, `*-analysis.md`, `*-explainer.md` | `## Table of Contents` (2), `^# `, `^## `, markdown table rows, `> [!NOTE]\u002F[!TIP]\u002F[!IMPORTANT]` callouts | `md-document` |\n| REVIEW | `review.md`, `*-pr-*.md`, `*.diff.md`, `code-review*.md` | ` ```diff ` (2), `^[-+]{3} ` (2), `^@@` (2), `> [!BLOCKER]\u002F[!MAJOR]\u002F[!MINOR]\u002F[!NIT]` (2), `LGTM`\u002F`nit:`\u002F`blocker:` | `md-review` |\n| SLIDES | `deck.md`, `slides.md`, `*-talk.md`, `presentation*.md` | `^---$` ≥ 3 (2 + per-boundary), `\u003C!-- notes:` (2), H1 count ≥ 5 with median gap ≤ 12 lines (2) | `md-slides` |\n\nThe pipeline:\n\n```bash\npython3 markdown-html\u002Fskills\u002Fmarkdown-html-orchestrator\u002Fscripts\u002Fdoctype_classifier.py \\\n    --input \u003Cpath>.md --output json \\\n  | python3 markdown-html\u002Fskills\u002Fmarkdown-html-orchestrator\u002Fscripts\u002Froute_explainer.py\n```\n\n`route_explainer.py` checks the design-system status, applies the \u003C 100-line refusal, and prints one of: `ROUTE_SILENTLY -> md-\u003Ctype>`, `ASK_USER one question: ...`, or `REFUSE — fix the issues above`.\n\n## Workflow\n\n### Step 1 — Confirm onboarding\n\nIf the user has never run onboarding, surface the one-time setup:\n\n```bash\npython3 markdown-html\u002Fskills\u002Fdesign-system\u002Fscripts\u002Fonboard.py\n```\n\nTen questions, 1-2 minutes. Captures brand primary + accent + heading\u002Fbody Google Fonts + design style (editorial\u002Ftechnical\u002Fminimal\u002Fplayful) + default output dir + syntax theme + TOC behavior + optional logo\u002Fcompany. Stored at `~\u002F.config\u002Fmarkdown-html\u002Fdesign-system.json`. Re-runnable with `--scope project` for per-repo overrides.\n\n### Step 2 — Classify the input\n\nRun `doctype_classifier.py` on the markdown. Inspect the verdict.\n\n### Step 3 — Route or ask\n\nPipe the classification into `route_explainer.py`. If it says `ROUTE_SILENTLY`, forward the original markdown + the design-system config into the named sub-skill's renderer in the forked context. If it says `ASK_USER`, ask ONE question with the recommended answer.\n\n### Step 4 — Resolve the output path\n\n```bash\npython3 markdown-html\u002Fskills\u002Fmarkdown-html-orchestrator\u002Fscripts\u002Foutput_path_resolver.py \\\n    --input \u003Cpath>.md --doctype \u003Cdocument|review|slides>\n```\n\nCollision handling defaults to `-2 \u002F -3 \u002F ...` suffix; `--on-collision timestamp` for stamped names.\n\n### Step 5 — Hand off to the sub-skill\n\nThe routed converter sub-skill's renderer (`md-document\u002Fscripts\u002F`, `md-review\u002Fscripts\u002F`, or `md-slides\u002Fscripts\u002F`) takes the input markdown, the design-system config, and the resolved output path, and writes a single self-contained HTML file. The orchestrator returns a ≤ 100-word digest: input lines, output path, design style applied, top 3 features used (TOC, search, code-copy, etc.), and one forcing question for the user. Never render HTML by hand — the converter scripts own the rendering.\n\n## Forcing-question library (Matt Pocock grill-with-docs pattern)\n\nWalk these one at a time, with a recommended answer per question, citing the canon. Lift this list into `\u002Fcs:grill-markdown-html` for plan-stage interrogation.\n\n1. **What decision does this HTML drive — is the reader skimming, deciding, or presenting?**\n   Recommended: name it first; density follows from purpose. Canon: Shihipar — \"match output format to consumption context\"; Tufte — *Visual Display of Quantitative Information*, ch. 1.\n2. **Is the input markdown ≥ 100 lines?**\n   Recommended: yes — below that, keep it as markdown. Canon: Shihipar — markdown still wins under 100 lines.\n3. **Is the design-system onboarded?**\n   Recommended: yes, globally (`~\u002F.config\u002Fmarkdown-html\u002Fdesign-system.json`). Canon: research-ops onboarding pattern (`research-ops\u002FCLAUDE.md` §8); WCAG 2.2 §1.4.3 (text contrast 4.5:1).\n4. **Where does the output save, and will it overwrite anything?**\n   Recommended: the configured `default_output_dir` with `--on-collision suffix`. Canon: Matt Pocock `handoff` skill — never silently overwrite a working artifact.\n5. **Document type confidence — silent-route or one question?**\n   Recommended: silent-route only when the classifier's verdict is one of `document\u002Freview\u002Fslides` AND `silent_route_allowed: true`. Otherwise ask. Canon: research-ops two-signal threshold (`research-ops\u002Fskills\u002Fresearch-ops-skills\u002FSKILL.md` §\"Routing logic\").\n\nNever run a sub-skill before the lane is locked.\n\n## Assumptions\n\n1. User has a markdown file ≥ 100 lines they want to convert.\n2. User has run onboarding once (`~\u002F.config\u002Fmarkdown-html\u002Fdesign-system.json` exists with `setup_completed_at` populated).\n3. Single-file HTML output is acceptable (no multi-file site, no embedded server, no build step).\n4. Externals limited to Google Fonts CSS + Prism.js CDN (jsdelivr \u002F cdnjs).\n\n## Non-goals\n\n- Not a landing-page generator (use `marketing\u002Flanding\u002F`).\n- Not an interactive prompt-tuning playground (use Anthropic's official `playground` plugin).\n- Not a static-site generator (no multi-file output, no site index).\n- Not a PDF generator (slides use `@media print`; user prints from browser).\n- Not a watch \u002F live-reload pipeline (conversion is one-shot).\n\n## Distinct from\n\n- **Anthropic Playground plugin** (`\u002Fplayground`) — builds interactive controls (sliders, knobs, drag-drop) for prompt tuning, with a copy-prompt-back loop. This plugin converts existing markdown documents to HTML. Different tools for different jobs.\n- **`marketing\u002Flanding\u002F`** — generates landing pages from scratch (Phase-0 intake → 3 sections → branded TSX\u002FHTML). This plugin converts an existing markdown file you already have.\n- **`engineering\u002Fhandoff\u002F` + `productivity\u002Fhandoff\u002F`** — preserve session continuity between Claude conversations. Different artifact type (handoff brief vs. document conversion).\n\n## Output artifacts\n\n| Sub-skill | Artifact | Status |\n|---|---|---|\n| `md-document` | `doc-\u003Cslug>.html` (single file, sticky TOC, collapsibles, search, code-copy, scrollspy) | ✓ live |\n| `md-review` | `review-\u003Cslug>.html` (2-col diff + severity margin notes + jump-nav) | ✓ live |\n| `md-slides` | `deck-\u003Cslug>.html` (arrow-key nav + presenter mode + print-to-PDF) | ✓ live |\n\n## Anti-patterns (do not)\n\n- ❌ Convert markdown \u003C 100 lines — markdown still wins. Refuse and tell the user.\n- ❌ Run the orchestrator before the design-system is onboarded. The output looks broken without tokens.\n- ❌ Silently chain two sub-skills (e.g., \"convert doc AND make slides from it\"). Pick one, finish, ask before chaining.\n- ❌ Use external JS frameworks (React\u002FVue\u002FSvelte). Vanilla JS + IntersectionObserver only. Prism.js CDN is the single exception.\n- ❌ Multi-file output (extracted CSS, asset directories). Single file or nothing — that's the whole point.\n- ❌ Overwrite an existing output file by default. The path resolver suffixes `-2`, `-3`, …; `--on-collision overwrite` is opt-in only.\n\n## References\n\n- Spec: Thariq Shihipar — \"Claude Code HTML output\" (Medium, 2026)\n- Forking pattern: `research-ops\u002Fskills\u002Fresearch-ops-skills\u002FSKILL.md` (`context: fork`, two-signal routing)\n- Customization pattern: `research-ops\u002Fskills\u002Fclinical-research\u002Fscripts\u002F` (`onboard.py`, `config_loader.py`)\n- Brand palette math: `marketing\u002Flanding\u002Fskills\u002Flanding\u002Fscripts\u002Fbrand_palette_validator.py` (WCAG + HSL derive)\n- Information-density canon: Tufte; Shihipar's `thariqs.github.io\u002Fhtml-effectiveness\u002F` gallery; Wattenberger interactive essays; Maggie Appleton digital gardens\n",{"name":5,"tags":62,"author":67,"context":68,"license":14,"version":69,"description":7,"compatible_tools":70},[37,40,63,39,64,65,52,66],"converter","documentation","code-review","design-system","Alireza Rezvani","fork","2.10.3",[71,72,73,74,75,76],"claude-code","codex-cli","cursor","antigravity","opencode","gemini-cli","main","068c2486ccc0f8d200a3db4d21ec137064eda3b4","skills\u002Fpublic-02-claude-skills-main-gemini-skills-markdown-html-orchestrator-skill-5ae40de2","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing","https:\u002F\u002Fgithub.com\u002FJiayiV","2026-08-25 16:30:52",{"source":8,"skillName":5,"commands":84,"prompt":94,"zipAvailable":95},[85,88,91],{"tool":86,"command":87},"npx","npx skills add JiayiV\u002Fquestion_mixing --skill markdown-html-orchestrator",{"tool":89,"command":90},"bunx","bunx skills add JiayiV\u002Fquestion_mixing --skill markdown-html-orchestrator",{"tool":92,"command":93},"pnpm","pnpm dlx skills add JiayiV\u002Fquestion_mixing --skill markdown-html-orchestrator","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-markdown-html-orchestrator-skill-5ae40de2\u002FSKILL.md",true,[],[98,124,151,179,206,237],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":57},"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",[],[100,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123],"github","ai agents","web","notes","code","browser","https","actions","manifest","inventory","verify","tool","use","ready","unrelated","app","scope","for","webmcp",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":128,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":57},"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",[],[132,133,134,135,136,137,54,138,139,140,141,142,143,144,145,146,147,148,149,150],"vardoger analyze","analyze","directory","cli","github copilot","copilot","update","learn","network","my style","install","conversation","me","local","github copilot cli","pipx","my","at","copilot instructions",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":161,"publishedAt":57},"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",[157,160],{"categoryNo":158,"categoryName":159,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":26,"categoryName":27,"taxonomyType":20,"taxonomyTypeDesc":21},[162,163,164,165,166,167,55,168,169,170,171,172,173,117,174,175,176,177,122,178],"transloadit media processing","Media","media processing","processing","MCP","mcp server","subtitles","pipeline","ocr","Video","Audio","mp4","images","files","transformation","free","hls",{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":188,"publishedAt":57},"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",[185],{"categoryNo":186,"categoryName":187,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[189,190,191,192,193,56,194,195,196,117,197,198,199,200,201,202,203,204,205,122],"terraform","SET","terraform azurerm set diff analyzer","diff","analyzer","azure","gateway","firewall","only","resource changes","provider","resources","load balancer","attributes","front","load","balancer",{"skillNo":207,"name":208,"nameZh":6,"description":209,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":210,"categories":211,"keywords":219,"publishedAt":57},"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",[212,215,218],{"categoryNo":213,"categoryName":214,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":216,"categoryName":217,"taxonomyType":31,"taxonomyTypeDesc":32},"01JBSEEDCAT000000000000036","内容创作者",{"categoryNo":34,"categoryName":35,"taxonomyType":31,"taxonomyTypeDesc":32},[220,221,222,223,224,225,226,227,133,228,117,229,230,231,232,233,234,235,122,236],"search","Job Search","technical job search","technical","writing","tasks","email","parsing","interview","up","engineer","general","activate","do","task","cv","letter",{"skillNo":238,"name":239,"nameZh":6,"description":240,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":241,"categories":242,"keywords":243,"publishedAt":57},"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",[],[244,245,246,247,248,223,249,117,233,250,251,47,252,253,254,255,256,257,122,258],"steno mode","mode","customer","brief","first","tutorial","teaching","tokens","trigger","structured output","machine","output","court","requests","response compression"]