git:20261005.ab04c6e to git:20261005.bf37098

+ argument-hint: "[config [key value] | clean | update]"

+ # Answer me with HTML: answer a complex question with one HTML page

+ You write only the **content draft** (extended Markdown). The `am` CLI does all layout, colours, dark mode and diagram coordinates. **Do not hand-write HTML / CSS / SVG.**

+ Reply to the user, and write the draft, in the user's language.

+ ## 0. When the user wants to change settings

+ Arguments for this call: `$ARGUMENTS`

+ When the arguments start with `config` (for example `/answer-me-with-html config open off`), this turn handles settings only and produces no page:

+ - `config`: run `am config` to show the current settings, then ask the user which one to change.

+ - `config <key> <value>`: run `am config set <key> <value>`.

+ - `config reset [key]`: run `am config reset [key]`.

+ When the user asks in natural language ("stop opening the browser", "turn off always-on mode", "use the card theme by default"), also convert it to `am config set`. Settings: `open` (auto-open the browser), `always` (always-on mode), `theme`, `mode`, `style`, `voice` (video narration), `update_check` (new-version notices). Run `am config` to see all descriptions.

+ When the arguments start with `clean`, or the user asks to clean up pages / the cache: first run `am clean --dry-run` and tell the user how many items and how much space will be deleted. Run `am clean` only after the user agrees (add `--all` to delete all pages and videos, `--days N` to change how many days to keep).

+ When the arguments start with `update`, or the user asks to update this skill: update according to how it was installed. Installed with `npx skills`: run `npx skills update answer-me-with-html -y`. Installed as a Claude Code plugin: run `claude plugin update answer-me-with-html@answer-me-with-html` (or ask the user to click Update now in `/plugin` → Installed), then ask the user to run `/reload-plugins`. Installed with git clone: run `git pull && npm install` in the repository directory.

+ ## 1. Decide: produce a page or not

+ Produce a page if any of these is true:

+ - There are ≥3 interrelated concepts, and the reader needs to see how they relate.

+ - There is a flow, protocol, call chain or state transition (especially with branches or several actors).

+ - There is a comparison across ≥3 dimensions, a trade-off between options, or a "can / cannot" list.

+ - There is a hierarchy or an evolution over time.

+ Otherwise answer in plain text. When unsure: the more the question "needs a picture to understand", the more it calls for a page.

+ ### Always-on mode

+ If the context contains the `[answer-me-with-html always-on]` reminder (the user installed the answer-me-with-html-always plugin, or turned on always-on mode in a rules file), the bar is lower:

+ - Whenever this turn gives a conclusion, summary, plan, comparison, review or explanation, attach a page.

+ - Do not skip it because "the answer is short". If there is a conclusion, produce a page.

+ - For everyday conclusions use a small page with 2–4 panels: one callout with the conclusion, plus one table or one diagram. Do not add panels just to fill space.

+ - Render with `--no-open`, so no browser window interrupts the user. The user opens the page by clicking the path at the end of the reply.

+ - In the terminal, give the text conclusion first as usual, and put the page path on the last line.

+ - Produce no page for small talk, one or two sentences with no conclusion, pure command output, or when the user asks for plain text.

+ ## 2. Workflow (one Bash call)

+ The CLI is bundled in this skill's directory: `scripts/am.mjs`, a single file with no dependencies to install; it needs only Node.js 20+. Below, `am` always means:

+

+ In Claude Code, the path above is replaced with this skill's directory automatically. If you see the variable unreplaced (other agents), replace it with the absolute path of the directory that contains this SKILL.md. If the user installed the `am` command globally, you can also use `am` directly.

+ 1. First list 3–8 panels in your head. Each panel answers one sub-question only.

+ The draft language follows the language of the user's question: an English question gets an English draft, a Chinese question a Chinese draft, a Japanese question a Japanese draft. The page button labels, `<html lang>` and the STE check rules switch automatically by the draft language (a draft containing kana counts as Japanese); STE applies the English or Chinese rules to each sentence by its language (Japanese sentences get only the sentence-length and paragraph-length checks, with the same character limits as Chinese). To force the interface language, write `lang: en`, `lang: zh` or `lang: ja` in the frontmatter.

+ 2. Choose components by the shape of the information (see section 4).

+ 3. Render in one go with a heredoc:

+ title: Title

+ ## A Panel title

+ A -> B: label

+ 4. Read the output:

+ - `✓ <path>`: success. Whether the browser opens automatically depends on the user's settings (`am config`); `--no-open` affects only this run.

+ - `✗ L<line> [component] …` + `Correct example:`: fix that line following the example, then render again.

+ - `STE n warnings`: rewrite the flagged lines as suggested, then render again. Retry at most 2 rounds; if warnings remain, keep the page and say so.

+ - `! Cleanup hint: …` or `! Update hint: …`: pass it on to the user in one sentence at the end of the reply, and ask whether to clean up / update. **Do not run am clean or the update command yourself**; wait until the user agrees. The CLI throttles these: the cleanup hint appears at most once every 7 days, the update hint at most once every 3 days.

+ 5. Reply in the terminal with only 2–3 lines: one core conclusion + the page path. Do not paste the draft or the HTML back into the terminal.

+ When a page already exists and only one panel needs to change, do not rewrite the whole page. Take the source draft from the HTML's `#am-source`, replace only the matching `##` section, and overwrite the page in place:

+ node "${CLAUDE_SKILL_DIR}/scripts/am.mjs" patch page.html --panel "Panel title" <<'AM_EOF'

+ ## A Panel title

+ New content

+ `--panel` matches the title, the letter ID, or `ID title`. If the panel is not found or the page has no `#am-source`, leave the file unchanged. patch keeps the original page's theme, light/dark mode and STE style; add `--theme` / `--mode` / `--style` to change them. Full usage: `am help patch`.

+ ## 3. Draft format quick reference

+ template: sheet # sheet board (default, one-screen overview) | doc linear explanation (read step by step)

+ theme: blueprint # blueprint drawing style (default) | shadcn card style

+ title: Title

+ subtitle: One-line summary # optional

+ cols: 3 # sheet columns, default 3; panels span columns / rows with span / rows

+ source: RFC 9293 # any other key is shown in the page header's meta line

+ Lead: one or two sentences with the core conclusion (optional).

+ ## A Panel title {span=2 meta="small text, top right"}

+ Plain Markdown: paragraphs, lists, tables, quotes.

+ Table status words: ok / no / warn (may carry text: "ok approved") → ✓ / ✗ / ! badges.

+ ## B {bare} ← bare: no title bar (suits a kv title block)

+ - The panel letter ID can be omitted; it is assigned automatically.

+ - ```html / ```svg fenced blocks are embedded as-is. **Use them only when no component can express the content.**

+ - Full reference: `am help format`; component syntax: `am help <component>`; component list: `am list`.

+ ## 4. Choose components by the shape of the information

+ | Shape of the information | Component | Minimal syntax |

+ | What connects to what, architecture, decision branches | `flow [LR]` | `A -> B: label`, `A --> C` dashed, `A -> B & C` fan-out, `{decision?}` `(start)` `[(database)]`, `*emphasis`, `group name: A, B` |

+ | Messages between actors over time | `sequence [num]` | `A -> B: request`, `B --> A: response`, `note A, B: note`, `== phase ==` |

+ | Hierarchy / directories / taxonomy | `tree [list]` | indentation for levels, `label \| description`, `` `id` label `` |

+ | History / phases | `timeline [v]` | `time \| title \| description`, `*` highlights |

+ | Values and limits | `limits` | `label \| 13 / 20 \| unit`, limit only: `label \| max 20` |

+ | Word-by-word comments on one sentence | `annot` | `# heading \| right note`, `[span]{note}`, `[wrong word]{!red note}`, `> footnote` |

+ | Metadata / title block | `kv [cols=2]` | `key: value`, `* wide cell: value` |

+ | Conclusion / warning | `callout <info\|ok\|warn\|err> title` | Markdown body |

+ | Multi-dimension comparison, can / cannot list | Markdown table | write ok / no / warn in the status column |

+ Selection rules:

+ - Conclusion first. The first panel or the lead gives the core answer; the following panels give the evidence.

+ - One panel, one question. With more than 8 panels, split the page or cut panels.

+ - Use `span` to give the densest panel more width; give a monospaced sentence (annot) at least span=2.

+ - Keep wide content out of a single column: tables with 4 or more columns, diagrams with a canvas wider than about 560px (`flow LR`, `sequence` with long labels). Without `span`, the CLI widens them automatically: a 4-column table takes 2 columns, 5 or more columns take a full row; write `span` explicitly for another width.

+ - Do not invent data. Without real numbers, do not use limits; mark illustrative data as "illustrative" in the description.

+ ## 5. STE controlled writing (the text in the draft)

+ `am render` checks automatically and only warns by default (`style: 80`); with `style: strict` a draft that fails produces no page; `style: off` turns the check off.

+ - One sentence says one thing.

+ - Use the active voice. Write steps in the imperative ("Close the valve", not "The valve should be closed").

+ - One word, one meaning. Call the same thing by the same name throughout.

+ - Sentence length limits: steps (ordered lists) 20 words in English / 35 characters in Chinese; descriptions 25 words in English / 45 characters in Chinese.

+ - No more than 6 sentences per paragraph. Use lists for complex content.

+ - In English, use common short words: use, not utilize; start, not commence; before, not prior to.

+ - In Chinese, do not use light verbs (`进行优化` → `优化`, `加以说明` → `说明`), do not chain more than three `的`, and do not use clichés (`赋能`, `闭环`, `至关重要`…).

+ - For counter-examples shown on purpose, use `~~strikethrough~~` or put them in a table row whose status is `no`; the check skips them.

+ ## 6. Explainer videos (am video, 3Blue1Brown style)

+ Use only when the user explicitly asks for a video ("make a video", "explain it as a video", "3b1b style", "explainer video"). Do not produce a video unasked in always-on mode either.

+ A video draft has the same format as a page draft, with one extra rule: lines starting with `>` are narration, one beat per line.

+ title: The TCP three-way handshake

+ subtitle: Why three

+ > Opening narration (optional).

+ ## Both ends are waiting

+ > First the client sends SYN to ask for a connection.

+ > [Server] answers with SYN-ACK.

+ > The client replies with ACK, and the connection is open.

+ - One `## ` is one scene. Put one component (or one table, one list) in a scene as the picture, and write 2–5 narration lines below it.

+ - When the Nth narration line plays, the picture shows step N. In flow / sequence / tree every source line is one step; timeline, limits, table rows and list items step by entry. So the line order of the component is the order of the explanation. When there are more narration lines than steps, the extra first lines serve as an opening and show nothing new.

+ - Write `[name]` in narration: the camera zooms in on the node or actor with that name and highlights it. The name must match how it is written in the component.

+ - Nodes with the same name in adjacent scenes move smoothly to their new position. To keep the viewer following one object, reuse the same name in the next scene.

+ - 3–6 scenes per video, one or two sentences per narration line.

+ - Narration is read aloud, so write it as speech, as if explaining to someone face to face: transitions like `你看`, `那问题来了`, `我们换个角度看` are fine, and characters' "lines" go in quotes. Do not write it like a manual (`客户端发送 SYN 报文以请求建立连接`). Sentence length is still subject to the STE check.

+ - The look follows the theme in the settings by default (usually the blueprint drawing style). When the user wants "that dark 3b1b style", write `theme: 3b1b` in the frontmatter.

+ - Narration voice: the default is `--voice auto`: ElevenLabs when `ELEVENLABS_API_KEY` is set, otherwise system TTS (macOS say), and subtitles only when neither is available. When the user says "no sound", add `--voice off`. When the user runs a local OpenAI-compatible speech service and has set `AM_TTS_URL`, use `--voice local`.

+ - The output is a single-file player page under `~/.answer-me-with-html/videos/` (audio embedded). When the user wants a video file, add `--mp4`; this needs Chrome, ffmpeg and Node.js 22+ on the machine, and export takes about 1.3 times the video length.

+ - Full syntax: `am help video`. In the terminal, reply with one sentence plus the player page path (and the MP4 path).