@wji.ai/cli 0.4.0 → 0.5.1

package/skill/social-media/SKILL.md

@@ -0,0 +1,152 @@
+---
+name: social-media
+description: Make and size content for social platforms on WJI through the `wji` CLI — the image and video specs of Instagram, TikTok, YouTube / Shorts, Facebook, X, LinkedIn, Pinterest, Threads, Snapchat, 小红书, 抖音, 快手, 视频号, B站, 微博 and 微信公众号 (ratio, pixels, duration, file size, safe zones, caption / title / hashtag limits, covers and thumbnails), what performs on each (the 3-second hook, loops, on-screen text), and the repurposing recipes: one master into every placement, a short-drama episode into vertical teasers and a poster set, an ad master into all its placements. Use whenever a task mentions social media / 社群 / 社交媒体, posting / 发文, Reels, Shorts, TikTok, 小红书 / 抖音 / 视频号, a cover / 封面, poster / 海报, thumbnail, teaser / 预告, or asks what size or length a platform wants. Combines with the short-drama and ads skills. Works together with the `wji` skill.
+---
+
+# Social media on WJI
+
+You are the person who knows every platform's numbers and turns one piece of work into the
+right post for each of them. **You write the spec sheet, the hooks and the copy**; the `wji`
+CLI keeps the plan as a dataset and generates the per-ratio images and videos on a canvas;
+local `sharp` or `ffmpeg` (when installed) crops to exact pixels. Nothing is generated until
+the user has said yes to the quote (or the message carried `-auto`, see the `wji` skill).
+
+```
+what & where ──▶ spec sheet ──▶ source assets ──▶ generate per ratio ──▶ covers ──▶ copy ──▶ post plan
+     │               │               │                  │                  │          │
+  platforms,     one row per     existing nodes /    images: native      thumbnail,  caption,
+  goal, market   surface from    short-drama /       ratio then crop;    poster,     hashtags,
+                 the tables      ads / new           video: regenerate   图文 cover   slot, label
+```
+
+`{baseDir}` = this skill. The `wji` skill governs every CLI call.
+
+| Read | When |
+| --- | --- |
+| `reference/platforms-global.md` | any Instagram / TikTok / YouTube / Facebook / X / LinkedIn / Pinterest / Threads / Snapchat question — the spec tables and safe zones |
+| `reference/platforms-china.md` | 抖音 / 快手 / 小红书 / 视频号 / B站 / 微博 / 公众号 — specs, and China-specific practice (AI label, titles, 图文) |
+| `reference/ratio-map.md` | before generating: which WJI model makes which ratio natively, what must be cropped and how to anchor the crop |
+| `reference/content-craft.md` | hooks, loops, overlays, captions and hashtags per platform, posting times, cover design, carousel / 图文 storytelling |
+| `reference/repurpose.md` | master → placements, drama episode → teaser + posters, ad master → placements, the deliverables checklist |
+| `reference/plan-template.md` | the post spec sheet — write one row per post before touching the canvas |
+
+## Operations
+
+### Where the plan lives
+
+Locally: `social/<campaign>/plan.md` (the spec sheet, one row per post, plus the copy and the
+deliverables) and `prompts/`. On WJI: the same plan as a dataset `SOCIAL <campaign>` in the
+workspace's **story** folder.
+
+```bash
+wji auth whoami --json && wji profile wallet
+wji ws use <workspaceId>
+wji ws app list                                                  # the Dataset app id → DS_APP
+wji --json ws fs --app DS_APP | jq -r '.. | objects | select(.content.semanticKey? == "story") | .id'   # → STORY
+wji dataset new STORY "SOCIAL <campaign>" -t other -d "<one line>" --json | jq -r .id                   # → PLAN
+wji fs set PLAN --merge content=@social/<campaign>/plan.md --merge viewMode=content
+wji canvas list                                                  # the masters, keyframes, sheets already there
+wji canvas nodes -c <canvas> --json | jq '.[] | {id,name,kind,assetId}'
+wji asset download <assetId…> -o /tmp/social                     # look before you write about it
+wji asset upload <file>                                          # the user's own material
+wji models get <model>                                           # the ratio list ratio-map.md summarises
+```
+
+### Generating per ratio
+
+One canvas `SOCIAL · <campaign>` (`wji canvas create "SOCIAL · <campaign>" --json | jq -r .id`),
+one row per platform surface:
+
+| Need | Command |
+| --- | --- |
+| image at a native ratio | `wji canvas add image -c SC -n "小红书 cover" --from <source nodes> -m <image model> -r 3:4 --resolution 2K --prompt-file prompts/xhs-cover.txt` — the source keyframe / KV / sheet first in `--from` |
+| video at the platform ratio | `wji canvas add video -c SC -n "Reels teaser A" --from <same references as the master> -m <video model> -r 9:16 -d 20 --prompt-file prompts/reels-a.txt` — **regenerated, never cropped** |
+| quote → yes → run | `wji canvas gen <nodeIds…>` (prints the cost, refuses) → tell the user → `wji canvas gen <nodeIds…> --yes --wait` |
+| adjust | `wji canvas set <node> -p … / -r … / -d …`, `wji canvas connect <from> <to>` |
+| one-off still | `wji gen image -m <model> -p "…" -r 4:5 --ref <assetId> --wait` |
+
+### Exact pixels
+
+A model generates a ratio, not a pixel size. When the placement needs exact pixels or a ratio no
+model has (1200×628, 1080×1260 视频号, 1146×717 B站, 900×383 公众号, banner sizes), generate at the
+nearest native ratio from `reference/ratio-map.md`, download the asset, and crop locally:
+`npx sharp-cli` / a five-line node script with `sharp` (`resize(w, h, { fit: 'cover', position })`)
+or `ffmpeg -i in.png -vf "crop=w:h:x:y,scale=W:H" out.png` — whichever is installed; if neither
+is, deliver the generated frame plus the crop box (left, top, width, height) and say so. Anchor
+every crop as `reference/ratio-map.md` §"Crop anchoring" says: faces, then product centre, then
+the headline zone. Upload the result with `wji asset upload` and add it to the canvas as a display
+node so the plan's ids point at the final file.
+
+## Before anything else
+
+1. **Ask what and where, in one message**: what is being promoted (a drama episode, an ad, a
+   product, an account), which platforms and surfaces (feed vs Reels vs Stories are different
+   posts), the goal (views, follows, clicks to the full episode, sales), the market and language
+   (mainland / overseas / both — it changes the platform list and the label rules). **Never guess
+   the platform.** Offer the usual sets: 短剧 launch = 抖音 + 小红书 + 视频号 (+ TikTok + Reels +
+   Shorts overseas); product = Instagram feed + Reels + TikTok + 小红书.
+2. **Write the spec sheet** (`reference/plan-template.md`): one row per post with the platform's
+   own numbers copied from the tables — ratio, pixels, duration cap, safe zone, caption / title /
+   hashtag limits, cover spec. Rows marked *(verify)* in the tables stay marked in the sheet.
+3. **Find the source material** before proposing generation: the canvases and datasets already
+   in the workspace, the user's files, or the other skills' work (next section). Generate new
+   material only for what does not exist.
+4. **Quote the whole plan** (`wji gen cost` per node kind) before the first generation.
+
+## Combining with other skills
+
+- **A short-drama project is present** (a folder with `project.json` and `episodes/`, or the
+  short-drama skill is installed beside this one at `../short-drama/`) → *drama mode*. Read the
+  episode with the engine: `node ../short-drama/scripts/short-drama.mjs render <project> script --ep N`
+  for the lines and `… render <project> segment E0N-01` per segment (or read
+  `storyboard.segments` in `<project>/episodes/E0N.json` directly); `… manifest <project> --ep N`
+  tells you the episode canvas id, and
+  `wji canvas nodes -c <E0N canvas>` lists its keyframes, sheets and clips. Then
+  `reference/repurpose.md` §"Drama episode → teaser + poster set": pick the hook line from the middle of the
+  episode, build the 4-beat 15–45 s teaser (hook 0–3 s → context → escalation → cut before the
+  payoff + 「主页看全集」) as **new 9:16 video nodes generated from the same character and scene
+  sheets** (never a crop of the 16:9 clips), 2–3 variants that differ only in the hook, and the
+  poster set (小红书 3:4, Instagram 4:5, Pinterest 2:3, YouTube thumbnail 16:9, B站 1146×717,
+  视频号 6:7) from the episode keyframes with the title zone kept clear. Record the node ids in
+  `plan.md`; do not write into the drama's `project.json`.
+- **An ads brief is present** (`ads/<product>/brief.md` or the `AD <product>` dataset) →
+  *campaign mode*. Read the brief and the `AD · <product>` canvas (KV, stills, clips, master
+  ratio). `reference/repurpose.md` §"Ad master → placements": one row per placement, KV
+  regenerated at native ratios or cropped for the rest, vertical / square video regenerated from
+  the same stills, per-platform copy written from the brief's CTA and legal lines, the AI-content
+  label toggled where the ads skill's `reference/compliance.md` says so.
+- **Neither** → standalone: the user's assets or fresh generation, same spec sheet.
+- If the material the user describes belongs to a skill that is **not installed**, say which one
+  (short-drama / ads) rather than rebuilding its data by hand.
+
+## Making the posts
+
+- **Images**: generate at the native ratio where one exists (`reference/ratio-map.md`), with the
+  source node first in `--from` so the subject stays the same; crop only for non-native sizes.
+  One ratio for every card of a carousel / 图文.
+- **Video**: one node per platform ratio, regenerated with the master's references and a prompt
+  reframed on the faces / product for vertical; `-d` under the surface's cap; captions and
+  on-screen text are overlays inside the safe zone, never generated.
+- **Covers and thumbnails**: face + ≤4 words, high contrast, the series template repeated
+  (`reference/content-craft.md` §"Cover and thumbnail design"); 小红书 cover is the hook of the 图文.
+- **Copy**: hook line, body, CTA, hashtags within the platform's limits (Instagram ≤5 hashtags,
+  小红书 title ≤20 chars, X 280) — written into `plan.md`, one block per post.
+- **Posting slots** from `reference/content-craft.md` are starting points, said as such.
+
+## Reporting
+
+After the spec sheet: the rows and what will be generated vs cropped, with the quote. After
+generation: the deliverables table from `reference/repurpose.md` (post, file / node, ratio, pixels,
+duration, cover, caption, hashtags, slot, AI label) and anything the user still has to do in
+their editor (captions, subtitles, crops you could not make).
+
+## Rules specific to this skill
+
+- **Ask before every generation**; a batch is one quote.
+- **Never invent a platform limit** — cite the table row; keep *(verify)* flags; if a platform
+  is not in the tables, say so and ask the user for its spec.
+- Video is regenerated at the target ratio, never cropped; images are cropped only when no model
+  has the ratio.
+- Text stays out of the platform's UI zones; one ratio per carousel; the drama's dialogue is
+  quoted verbatim in teasers.
+- Do not compile or store personal data of real people from the platforms; all-audiences content only.

package/skill/social-media/reference/content-craft.md

@@ -0,0 +1,124 @@
+# Content craft — hooks, loops, overlays, captions, covers, carousels
+
+What makes a post perform once the size is right: the first three seconds, the ending that
+re-plays, text that stays inside the safe zone, a caption shaped for each platform's reading
+pattern, a posting slot to start from, a cover that reads at thumbnail size, and a carousel that
+tells one story. Sizes and limits are quoted from platforms-global.md and platforms-china.md,
+not restated here; teaser and poster recipes built on these rules are in repurpose.md.
+
+## The first 3 seconds
+
+Feeds decide in the first swipe-length. The product, the face or the question is on screen by
+second 3, in motion, with no logo card, no fade-in and no "hi guys". Hook types, with a line
+each (drama and product examples side by side):
+
+| Hook type | Drama teaser | Product / brand |
+| --- | --- | --- |
+| Shocking line, mid-scene | 「你以为我不知道孩子是谁的？」 cut in on the reaction | "This is the last one we could get made." |
+| Result first, cause later | the slap, the arrest, the reveal — then 「三天前…」 | the after-state (clean pan, finished room), then the before |
+| Direct question | 「如果你婆婆当众撕了你的结婚证，你会怎么做？」 | "Why does every white sneaker turn yellow in a month?" |
+| Contradiction / mismatch | the bride in a wedding dress signing divorce papers | a luxury unboxing on a bus |
+| Countdown / stakes | 「还有十分钟，她就要嫁给别人了」 | "Three tests. One survives." |
+| Visual anomaly | one impossible detail in an ordinary frame (a wet footprint indoors) | the product doing the one thing rivals cannot |
+| Named audience | 「二婚的姐妹看过来」 | "If you edit on a phone, watch this." |
+
+Rules: one hook per cut, the first frame is already the strongest frame (it is also the cover),
+sound-off comprehension — the hook line is burned in as text. Write 2–3 hooks for the same body
+and let the platform pick (repurpose.md, variants).
+
+## Loop-friendly endings
+
+Reels, TikTok and 抖音 count re-watches. End on a frame that matches the first frame (same
+composition, same subject position) so the loop hides the seam; or end one beat *before* the
+answer the hook promised, so the viewer re-watches to catch it; or end on the CTA card that is
+also the cover. Never end on a logo fade or a black frame. For a drama teaser the ending is the
+cut before the payoff plus the line 「主页看全集 / full episode in bio」 (repurpose.md).
+
+## On-screen text and burned subtitles
+
+- Keep every word inside the safe zone of the 9:16 diagram (platforms-global.md): headline in the
+  upper safe band, subtitles at the lower edge of the safe band (≈y 1100–1240 on 1080×1920), never
+  behind the caption or the right rail.
+- Subtitles are burned in (most feeds autoplay muted): 2 lines maximum, ≤ 14 CJK chars or ≤ 32
+  Latin chars per line, high-contrast box or stroke, one style for the whole account.
+- Headline type ≥ 60 px on 1080×1920, ≤ 6 words / 8 chars; a second overlay only when the first
+  has left. Do not repeat the caption on screen.
+- Text is added after the crop and at the final ratio (ratio-map.md, crop anchoring); text
+  generated inside the picture is only for covers that are never cropped again.
+- 「AI生成」 label where required (platforms-china.md) is the platform's toggle, not an overlay
+  you design — but do not place other text where the platform paints its label (top-left on most
+  Chinese apps).
+
+## Caption structure per platform
+
+| Platform | Structure | Hashtags / tags | Length notes |
+| --- | --- | --- | --- |
+| Instagram | hook line (shown before "more") → 2–4 short lines → CTA (save / share / comment) | **≤5** (Dec 2025 cap) — 3 niche + 2 broad | 2,200 max; the first 125 chars are the post |
+| TikTok / 抖音 | one-line hook + a question that invites comments | 3–5 hashtags / 话题, one is the series tag | 4,000 max on TikTok; 抖音 shows ≈20 chars of title |
+| YouTube | title ≤ 60–70 chars shown; description: 2-line summary, links, chapters, disclosure | 3–5 hashtags at the end of the description | title 100 hard cap |
+| Facebook | short hook, link in the first comment or the post, CTA | 1–3 | shares outweigh hashtags |
+| X | the hook is the whole post; thread for detail | 1–2 or none | 280 |
+| LinkedIn | hook in the first two lines → line-broken story → question → 3 hashtags | 3 | 3,000; "see more" after ≈3 lines |
+| Pinterest | keyword title ≤ 100, description with 2–3 search phrases | none | description 500–800 *(verify)* |
+| Threads | one sentence; the picture carries the rest | none | 500 |
+| 小红书 | 标题 ≤ 20 with the keyword first → 正文 in short lines with emoji markers → 话题 tags | keyword + 3–6 话题 (#…#) | 正文 1,000 (长文 6,000) |
+| 视频号 / 公众号 | one-line 描述 with 话题; the article's first line is the hook | 1–3 话题 | limits not confirmed |
+| B站 | 标题 with the series and episode number; 简介 with timestamps | tags on upload (platform field) | limits not confirmed |
+
+A CTA is one verb: 关注 / follow, 主页看全集 / full episode in bio, save, comment the answer.
+Platform buttons (shop, link, subscribe) are not drawn into the picture.
+
+## Posting-time starting points
+
+Sprout Social 2026 aggregates, to be treated as **starting points** and replaced by the
+account's own insights after two weeks: Instagram Mon–Thu 10:00–15:00; TikTok Wed 14:00–17:00;
+LinkedIn Tue 11:00–17:00. Local time of the audience, not of the account. Other platforms and
+the Chinese apps: not confirmed in the research — plan lunchtime (12–13) and evening (20–22)
+slots in the audience's time zone and measure. Series content posts at the same slot every
+time; the second post of a series goes out within 24 h of the first while the hook is fresh.
+
+## Cover and thumbnail design
+
+- **Face + ≤ 4 words** (≤ 8 CJK chars): the face at 40–60 % of the frame height, looking at the
+  camera or at the text; the words in one colour band, one weight.
+- **High contrast**: light text on a darkened lower third or dark text on a light band; check
+  it at 120 px wide (the 小红书 / 快手 tile is half a phone).
+- **One template per series**: same title position, same colour, same type; the episode number
+  changes, nothing else. Recognition beats novelty in a grid.
+- **Ratio per platform** (ratio-map.md): 16:9 1280×720 YouTube; 3:4 小红书 / IG grid; 9:16 Reels
+  / TikTok / 抖音 with the text in the centre 60 % because the grid crops to a taller tile;
+  1146×717 B站 with the bottom-left clear; 6:7 视频号 composed for its 1:1 share crop.
+- Covers are generated **with** the text only at the final ratio (nano-banana-pro, gpt-image-2.5
+  or seedream-5-pro for reliable multilingual type); every other size gets the text overlaid
+  after the crop.
+
+## Carousel / 图文 storytelling
+
+1. **Cover as hook** — the question, the contrast or the result; it must work alone in the feed.
+2. **One idea per card**, one line of text per card, the same layout grid on every card.
+3. **Escalate**: cards 2–N answer the cover in order of surprise, not of logic; the strongest
+   proof sits two cards before the end.
+4. **Last card = CTA** (follow, save, 主页看全集, 领取), in the same template as the cover so the
+   loop back to card 1 feels designed.
+5. **One ratio for the whole set** (IG ≤ 20 slides, 小红书 ≤ 18 images, TikTok photo mode ≤ 35):
+   generate every card at the same `ratio` and crop to the same box.
+6. Caption repeats the cover's keyword in the first line; on 小红书 the 话题 tags close the body.
+
+## Trending audio
+
+Trending sounds lift reach on TikTok / 抖音 / Reels, but a business account may only use
+tracks from the platform's **commercially licensed library**; personal-account sounds are
+muted or the post is removed when the account is business-typed. AI-generated soundtracks
+(Seed Audio, generated per teaser) avoid the problem and can be reused across the series.
+Never lip-sync a drama clip to a licensed pop song for a paid promotion.
+
+## What to avoid
+
+- A logo intro, a fade-in, a title card before the hook.
+- Letterboxed 16:9 inside a 9:16 post (regenerate — ratio-map.md).
+- Text in the top 270 px or the bottom 670 px of a vertical frame; text under the right rail.
+- More than 5 hashtags on Instagram; hashtag walls anywhere; hashtags that do not exist yet.
+- Sub-1080-px sources, upscaled 1K frames, JPEG re-compression of a re-compression.
+- Cross-platform reposts with the other platform's watermark or overlay language.
+- Engagement bait ("like if…", fake polls), fake countdowns, fake UI buttons drawn into the frame.
+- Claiming AI footage is real footage; skipping the AI label where it is required.

package/skill/social-media/reference/plan-template.md

@@ -0,0 +1,171 @@
+# Plan template — the post spec sheet
+
+One spec sheet per post (one platform × one surface × one asset). It is written before any
+generation, filled from the platform row (platforms-global.md / platforms-china.md), the ratio
+row (ratio-map.md) and the craft rules (content-craft.md); the campaign's sheets together are
+the deliverables checklist of repurpose.md. The block below is the template; after it, one
+filled example — a 3-episode 短剧 launch on 小红书, 抖音 and Instagram Reels with a teaser and a
+poster per platform. Every figure in a sheet is copied from a reference row or marked
+"not confirmed"; nothing is invented in the sheet.
+
+## Fields
+
+| Field | Meaning | Where it comes from |
+| --- | --- | --- |
+| campaign | name of the launch / series / promotion | the user |
+| platform | 小红书, 抖音, Instagram … | the user |
+| surface | the row: 图文, video note, Reels, Stories, thumbnail … | platform file |
+| ratio | delivered ratio | platform row |
+| px | delivered pixel size | platform row |
+| duration cap | the surface's cap and the planned length | platform row; content-craft.md |
+| safe zone | the pixel bands text and faces avoid | platform row / 9:16 diagram |
+| source asset | episode + segment ids, KV id, uploaded file | short-drama storyboard / ads brief / user assets |
+| generation plan | model, `ratio`, `resolution`, `duration`, references (`@imageN`), prompt notes (framing sentence) | ratio-map.md |
+| crop | native ratio → target px, anchor | ratio-map.md, crop anchoring |
+| cover | file or "first frame"; template name | content-craft.md, covers |
+| caption | hook line + body + CTA, within the limit | content-craft.md, captions |
+| hashtags | count and list, within the cap | content-craft.md |
+| CTA | one verb | the brief / series plan |
+| posting slot | day + time in the audience's time zone; "starting point" or "from insights" | content-craft.md, posting times |
+| disclosure | the platform's AI toggle and its state; 「AI生成」 for China | platforms-china.md; repurpose.md §3 |
+| status | planned · quoted · generated · cropped · overlaid · scheduled · posted | the work |
+
+## Template block
+
+```
+campaign:         
+platform:         
+surface:          
+ratio:            
+px:               
+duration cap:      (surface cap) / planned:
+safe zone:        
+source asset:     
+generation plan:
+  model:          
+  ratio:          
+  resolution:     
+  duration:       
+  references:     @image1 = … · @image2 = …
+  prompt notes:   
+crop:              native → target, anchor:
+cover:            
+caption:          
+hashtags:          (n / cap)
+CTA:              
+posting slot:     
+disclosure:       
+status:           
+```
+
+## Filled example — 《穿越战神》 3-episode launch, 小红书 + 抖音 + Instagram Reels
+
+Six sheets: a teaser and a poster per platform. Beats and references are the same across the
+three teasers; only the ratio (all 9:16 here), the copy and the covers differ.
+
+```
+campaign:         穿越战神 E01–E03 launch, week 1
+platform:         抖音
+surface:          video
+ratio:            9:16
+px:               1080×1920
+duration cap:     60 min (verify) / planned: 30 s
+safe zone:        pixel bands not confirmed for 抖音 — using the 9:16 diagram union: x 120–960, y 270–1248
+source asset:     E01 storyboard segments 03 (turn), 05 (爽点), 07 (cliff); character sheets C01, C02; scene sheet S02 (the ancestral hall)
+generation plan:
+  model:          seedance-2.5-ref
+  ratio:          9:16
+  resolution:     1080p
+  duration:       4 segments × 7–8 s (hook 3 s inside segment 1)
+  references:     @image1 = C01 sheet · @image2 = C02 sheet · @image3 = S02 sheet · @audio1 = C01 voice sample
+  prompt notes:   vertical, faces at the upper third, hall built in depth (pillar foreground, altar behind); hook variant A = the line 「跪下的应该是你」 cut in cold; subtitles burned in at y 1100–1240
+crop:             none (video is regenerated at 9:16)
+cover:            first frame of variant A, title template 「穿越战神 · 第1集」 in the centre 60 %
+caption:          「跪下的应该是你。」 穿越战神 第1集 — 他回来了，这次跪的是谁？ 主页看全集
+hashtags:         4 / no fixed cap: #穿越战神 #短剧 #逆袭 #第1集
+CTA:              主页看全集
+posting slot:     Wed 20:00 CST — not confirmed for 抖音, starting point; replace from insights after week 1
+disclosure:       「AI生成」 toggle on (标识办法 2025-09-01)
+status:           quoted
+```
+
+```
+campaign:         穿越战神 E01–E03 launch, week 1
+platform:         小红书
+surface:          图文 (poster + 3 cards)
+ratio:            3:4
+px:               1242×1660
+duration cap:     — / 4 images (≤ 18)
+safe zone:        title inside the middle 70 %; the tile is half a screen
+source asset:     E01 爽点 keyframe (C01 standing over C02 in the hall); scene sheet S02
+generation plan:
+  model:          nano-banana-pro
+  ratio:          3:4
+  resolution:     2K
+  references:     @image1 = C01 sheet · @image2 = C02 sheet · @image3 = S02 sheet
+  prompt notes:   poster: two figures, C01 lit from the altar candles, title band lower third with 「穿越战神」 + 「第1集 · 跪下的应该是你」 rendered in the picture; cards 2–4 without text (overlaid after)
+crop:             3:4 2K frame → cover-fit to 1660 high → trim 1–2 px each side → 1242×1660
+cover:            card 1 (the poster) — template 「剧名 / 第N集 / one-line hook」
+caption:          标题 (18 chars): 穿越战神｜第1集他回来了跪的是谁 · 正文: 3 short lines with emoji markers, the keyword 穿越战神 in line 1, 主页看全集 as the last line
+hashtags:         6 / no fixed cap: #穿越战神 #短剧推荐 #逆袭 #穿越 #第1集 #AI短剧
+CTA:              关注 + 主页看全集
+posting slot:     Thu 12:30 CST — not confirmed for 小红书, starting point
+disclosure:       「AI生成」 toggle on
+status:           planned
+```
+
+```
+campaign:         穿越战神 E01–E03 launch, week 1
+platform:         Instagram
+surface:          Reels
+ratio:            9:16
+px:               1080×1920
+duration cap:     3 min in-app / planned: 30 s
+safe zone:        Meta unified (Mar 2026): 269 px top, 384–672 px bottom, 65 px sides
+source asset:     the 抖音 teaser's segments (same references), English subtitle layer regenerated
+generation plan:
+  model:          same clips as 抖音 (no new generation); overlay layer in English at the final ratio
+  ratio:          9:16
+  resolution:     1080p
+  duration:       30 s
+  references:     —
+  prompt notes:   hook variant B for this market: the result-first cut (the kneel) before the line
+crop:             none
+cover:            first frame of variant B; title in the centre — the grid tile is 3:4
+caption:          "You should be the one kneeling." Ep 1 of 穿越战神 — full episode in bio.
+hashtags:         5 / 5: #shortdrama #aidrama #cdrama #reels #ep1
+CTA:              full episode in bio
+posting slot:     Tue 12:00 local — Sprout 2026 starting point (Mon–Thu 10–15)
+disclosure:       Meta AI label per policy (auto-detected from Jun 2026; state it in the caption as well)
+status:           planned
+```
+
+```
+campaign:         穿越战神 E01–E03 launch, week 1
+platform:         Instagram
+surface:          feed poster (4:5)
+ratio:            4:5
+px:               1080×1350
+duration cap:     —
+safe zone:        avoid the outer 3 % per side (3:4 grid crop since Jan 2025)
+source asset:     the 小红书 poster's references
+generation plan:
+  model:          nano-banana-pro
+  ratio:          4:5
+  resolution:     2K
+  references:     @image1 = C01 sheet · @image2 = C02 sheet · @image3 = S02 sheet
+  prompt notes:   same composition as the 3:4 poster; English title band 「WARLORD RETURNS · EP 1」 rendered in the picture
+crop:             none (4:5 is native to nano-banana-pro)
+cover:            itself
+caption:          hook line + 2 lines + "full episode in bio"
+hashtags:         5 / 5
+CTA:              full episode in bio
+posting slot:     with the Reel, same day
+disclosure:       Meta AI label per policy
+status:           planned
+```
+
+The 抖音 poster sheet mirrors the 小红书 one at 9:16 (a native 9:16 generation, title in the
+centre 60 %), and the 抖音 teaser variant C (the direct question hook) is a fourth video sheet
+with only the hook segment regenerated. Six sheets, one references set, two image generations
+per ratio, four video segments plus two extra hook segments — that is the whole quote.

package/skill/social-media/reference/platforms-china.md

@@ -0,0 +1,94 @@
+# Platform specs — China (抖音, 快手, 小红书, 视频号, B站, 微博, 微信公众号)
+
+The same table shape as platforms-global.md for the mainland platforms: per surface, the ratio
+and pixel size, duration and file caps, the safe zone, the text limits, and the conventions that
+decide whether a post is read at all. Chinese trade terms are kept in Chinese (图文, 封面, 话题,
+标题) because that is how the platform's own upload screens name them. Rows marked *(verify)*
+had conflicting figures in the 2025–2026 research; "not confirmed" means no figure was found —
+say so in the plan rather than guess. Generation ratios and crop boxes per row are in
+ratio-map.md.
+
+## 抖音 (Douyin)
+
+| Surface | Ratio · px | Duration | File size | Safe zone | Text limits | Notes |
+| --- | --- | --- | --- | --- | --- | --- |
+| Video | 9:16 1080×1920 (16:9 accepted, letterboxed); 30 or 60 fps | 60 min *(verify; older figure 15 min)* | web upload ≤4 GB | pixel bands not confirmed — same layout as TikTok (right rail, bottom caption): use the 9:16 diagram in platforms-global.md until verified | 标题 ≈20 chars visible; 话题 tags (#…#) appended | product or hook inside 3 s; 抖音 ranks completion rate and re-watches |
+| 图文 | 3:4 or 9:16 images, one ratio per post | — | not confirmed | as video | 标题 ≈20 chars | image count cap not confirmed; swipes with music like TikTok photo mode |
+| 封面 | 9:16 frame (a chosen frame or an uploaded cover) | — | not confirmed | profile grid crops to a taller tile — keep cover text in the centre 60 % | cover text ≤ ≈8 chars readable at thumbnail size | series use one template: same title position, same colour band |
+
+## 快手 (Kuaishou)
+
+| Surface | Ratio · px | Duration | File size | Safe zone | Text limits | Notes |
+| --- | --- | --- | --- | --- | --- | --- |
+| Video | 9:16 1080×1920 | ≈10 min | 2–3 GB *(verify)* | not confirmed — use the 9:16 diagram | not confirmed | double-column feed on the home tab: the 封面 is a tile, so its text must survive being half-width |
+| 封面 | 9:16 or 3:4 | — | not confirmed | — | not confirmed | one idea, big type, face if there is one |
+
+## 小红书 (Xiaohongshu / RED)
+
+| Surface | Ratio · px | Duration | File size | Safe zone | Text limits | Notes |
+| --- | --- | --- | --- | --- | --- | --- |
+| 图文 note | 3:4 1242×1660 (or 1080×1440); 1:1 and 9:16 accepted | — | ≤18 images, ≤20 MB each | the feed card shows the first image at 3:4 — a 1:1 or 9:16 first image is cropped; titles inside the image sit in the middle 70 % | 标题 ≤20 chars; 正文 ≤1,000 (长文 6,000); 话题 tags inside the body | **one ratio per note**: the first image sets the frame for all; the cover is the hook (see content-craft.md) |
+| Video note | 9:16 or 3:4 | ≤15 min | not confirmed | not confirmed — use the 9:16 diagram | 标题 ≤20; 正文 ≤1,000 | 3:4 video shows larger in the two-column feed than 9:16 |
+| 封面 | 3:4 or 9:16 | — | ≤5 MB | two-column feed: the tile is half the screen width — cover text must read at that size | cover text ≤ ≈8 chars, ≤2 lines | 3:4 covers dominate the discovery feed; a 9:16 cover is cropped to 3:4 on the card |
+
+## 视频号 (WeChat Channels)
+
+| Surface | Ratio · px | Duration | File size | Safe zone | Text limits | Notes |
+| --- | --- | --- | --- | --- | --- | --- |
+| Feed video | 6:7 1080×1260 (largest in the feed); 9:16 1080×1920; 4:3 1080×810; 1:1 1080×1080; any ratio 0.33–3.0 accepted | web 3 s–8 h; phone ≤60 min | ≤2 GB | 9:16 plays with black bars in the feed until tapped — 6:7 fills the card without bars | 描述 limit not confirmed; 话题 tags supported | 6:7 has no native generation ratio — crop from 3:4 or 1:1 (ratio-map.md) |
+| 封面 | same ratio as the video; **朋友圈 share crops the cover to 1:1** | — | not confirmed | keep the title and face inside the central square of the cover | — | a 6:7 cover loses 90 px top and bottom in the 朋友圈 card |
+| Live / 直播 preview | 9:16 | — | — | — | — | not covered here |
+
+## B站 (Bilibili)
+
+| Surface | Ratio · px | Duration | File size | Safe zone | Text limits | Notes |
+| --- | --- | --- | --- | --- | --- | --- |
+| Video | 16:9 1920×1080 or 3840×2160 | not confirmed | not confirmed | — | 标题 and 简介 limits not confirmed | 横屏 first; vertical is accepted but shown pillar-boxed on desktop |
+| 封面 | 1146×717 (≈16:10) or 1920×1200 | — | ≤2–5 MB | **keep the bottom-left corner clear** (duration badge overlays it); the title of the card sits under the cover, not on it | cover text ≤ ≈10 chars | crop from 3:2 or 16:9 — see ratio-map.md |
+| 动态 (dynamic post) | 1:1 or 4:3 images | — | not confirmed | — | not confirmed | nine-grid like 微博 |
+
+## 微博 (Weibo)
+
+| Surface | Ratio · px | Duration | File size | Safe zone | Text limits | Notes |
+| --- | --- | --- | --- | --- | --- | --- |
+| 头条文章 cover | 1000×562 (safe area 1000×400) or 900×500 | — | not confirmed | the card crops top and bottom: keep the title inside the middle 400 px | article title limit not confirmed | crop from 16:9 — see ratio-map.md |
+| Post images | not confirmed | — | not confirmed | not confirmed | post text limit not confirmed | nine-grid: the first three images are seen; make the first the hook |
+| Video | *(verify)* | *(verify)* | *(verify)* | — | *(verify)* | the research produced no reliable 2026 figures for 微博 video |
+
+## 微信公众号 (WeChat Official Account)
+
+| Surface | Ratio · px | Duration | File size | Safe zone | Text limits | Notes |
+| --- | --- | --- | --- | --- | --- | --- |
+| 头图 / cover | 2.35:1 900×383 — **plus the 1:1 share crop** taken from its centre | — | not confirmed | title and face inside the central 383×383 square so the 1:1 share card still reads | article title limit not confirmed | crop from 21:9 — see ratio-map.md |
+| Secondary cover (次条) | 1:1 200×200, export at 2× (400×400) | — | not confirmed | — | — | small: one object or one face, no text |
+| 图文 body | images the width of the article column; 900 px wide matches the cover width (practice, not a platform rule) | — | not confirmed | — | body length not confirmed | see 图文 layout notes below |
+
+图文 layout notes: the article opens on the cover and the first line, so the first image after
+the title is a second hook, not a decoration; one image per point, captions under images in a
+lighter weight; a share card at the end repeats the CTA; the 1:1 share crop is what most
+readers see first in a chat, so the cover's centre square is the real cover.
+
+## China-specific practice
+
+- **「AI生成」 label.** 《人工智能生成合成内容标识办法》 has been in force since 2025-09-01: AI-generated
+  or AI-edited video, images and audio carry a visible 「AI生成」 label (most platforms add a
+  toggle on upload — switch it on) and the file keeps implicit metadata / watermark marking. Do
+  not strip the marking in the crop step; do not describe AI footage as real footage.
+- **Title style.** 小红书 标题 ≤20 chars and the platform hides more; 抖音 shows ≈20. Front-load the
+  keyword the search box will match (product, place, problem), then the twist. Number + result
+  patterns (「3个…」「第2集…」) and bracketed qualifiers (【】) read as native; clickbait without the
+  payoff in the body is down-ranked.
+- **Emoji and keyword conventions.** Emoji as bullet markers at line starts, not inside
+  sentences; the body repeats the title's keyword once in the first line; 话题 tags (#…#) go at
+  the end of the body, 3–6 on 小红书, and they are searchable — use the platform's suggested
+  spellings, not invented ones.
+- **图文 storytelling.** The cover is the hook (question, contrast, result), each following image
+  is one idea with one line of text on it, the last image is the CTA (follow / 主页看全集 / 领取).
+  One ratio for the whole set, one title template for the whole account.
+- **Cover text is the headline.** On 小红书 and 快手 the tile is half the screen: ≤8 chars, one
+  colour band behind the text, face or product filling the rest.
+- **Search first.** 小红书 and 抖音 surface posts by search as much as by feed: the title, the
+  cover text and the first body line should agree on one keyword.
+- **Platform video-style borrowing.** 抖音 audiences reject an obvious repost from TikTok (English
+  overlays, foreign sounds); regenerate the overlay layer in Chinese rather than translating on
+  top of the old one.