content-director
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseContent Director — Bundle (format router)
内容导演工具——合集版(格式路由工具)
A single front-door content director that packs four format playbooks and routes the user into the right one. Each format lives as a reference file under — once the format is locked, read that file and follow it verbatim; the front door itself only resolves the format:
formats/| Format | Format playbook | One-liner | Teleprompter? |
|---|---|---|---|
| Talking-to-camera | | The user speaks to the lens — storytime, hot-take, "things nobody tells you". Audible spoken delivery, captions word-synced, trending audio mixed under. The user films. | ✅ Yes — script needs reading aloud |
| Silent POV | | Silent acting, story told through on-screen captions — "POV: when X", "tell me without telling me". Trending sound baked in. The user films. | ❌ No — silent acting, follows a shot list, not a script |
| Dance | | AI-generated dance from the user's photo that copies a viral trend's choreography exactly. No filming, silent output (user attaches the sound at upload). | ❌ No — AI-generated, no human filming |
| Stitch / Duet | | React to a proven viral original — original plays first, hard cut to the user's response. The agent finds the video and writes the take; the user films their half. | ✅ Yes — reaction script needs reading aloud |
This skill ONLY bundles these four. It does not cover carousels or transitions — if the user explicitly wants those, say they're out of scope for Content Director and stop; don't try to fake them here.
Teleprompter handoff (talking + duet only). Once the talking or duet playbook finalizes a script the user approves, it ends with a teleprompter handoff described in : it calls with the approved script, creator metadata, and , emits the returned short live URL , renders the returned for phone scanning, and keeps the returned so the agent can poll for the uploaded . The MCP handoff row stores the script, browser , and recording ratio; the Vercel page fetches those with the token, shows the ratio on the start screen, records through that target-aspect canvas, and uploads through upload-return. It falls back to Share/Save if upload fails. Default is , but the playbook can pass , , or when the trend calls for a different recording shape. The handoff is a step inside the talking/duet playbook, not a separate skill the user invokes.
formats/teleprompter.mdmcp__plugin_pika_pika__create_teleprompter_handoffaspect_ratioteleprompter_urlhttps://teleprompter.pika.bot/r?t=...qr_image_urlstatus_urlpublic_urlupload_urlaspect_ratio9:1616:91:14:5This skill's whole job is Stage 0 — figure out the format (and maybe the exact trend) — then load that playbook. Everything after is the format playbook's pipeline, run verbatim. Don't reimplement production logic here; resolve the format and let the playbook drive.
这款统一入口的内容导演工具整合了四种格式剧本,可将用户引导至合适的创作流程。每种格式对应目录下的参考文件——一旦确定格式,请严格读取并遵循该文件内容;入口工具仅负责确定格式:
formats/| 格式 | 格式剧本 | 一句话说明 | 是否需要提词器? |
|---|---|---|---|
| 镜头前讲解(Talking-to-camera) | | 用户对着镜头讲话——故事分享、热门观点、“没人告诉你的事”风格。需清晰的口语表达,字幕与台词同步,背景搭配热门音频。由用户拍摄。 | ✅ 是——需要朗读脚本 |
| 无声POV | | 无声表演,通过屏幕字幕讲述故事——“POV: 当X发生时”、“暗示你是X但不明说”风格。内置热门音效。由用户拍摄。 | ❌ 否——无声表演,遵循镜头列表而非脚本 |
| 舞蹈 | | 根据用户照片生成AI舞蹈视频,精准复刻热门趋势的舞蹈动作。无需拍摄,输出为无声视频(用户上传时自行添加音效)。 | ❌ 否——AI生成,无需真人拍摄 |
| 合拍/对唱(Stitch / Duet) | | 对已验证的热门原创视频做出反应——先播放原视频,再硬切至用户的反应内容。Agent会找到合适的视频并撰写反应脚本,用户拍摄自己的部分。 | ✅ 是——需要朗读反应脚本 |
本工具仅整合以上四种格式,不支持轮播图或转场效果——如果用户明确要求这些内容,请告知其不在内容导演工具的服务范围内并终止流程;请勿尝试模拟相关功能。
提词器交接(仅适用于镜头前讲解和对唱格式)。当镜头前讲解或对唱剧本最终确定用户认可的脚本后,需按照中的说明完成提词器交接:调用接口,传入已认可的脚本、创作者元数据和参数,获取返回的短链接(格式为),展示返回的供手机扫码,并保存返回的以便Agent轮询上传后的。MCP交接记录会存储脚本、浏览器和录制比例;Vercel页面通过令牌获取这些信息,在启动界面显示比例,通过对应比例的画布录制视频,并通过上传返回接口完成上传。若上传失败,则回退至分享/保存功能。默认为,但如果趋势要求不同的录制比例,剧本可传入、或。交接流程是镜头前讲解/对唱剧本中的一个步骤,并非用户可单独调用的独立工具。
formats/teleprompter.mdmcp__plugin_pika_pika__create_teleprompter_handoffaspect_ratioteleprompter_urlhttps://teleprompter.pika.bot/r?t=...qr_image_urlstatus_urlpublic_urlupload_urlaspect_ratio9:1616:91:14:5本工具的核心职责是第0阶段——确定格式(可能包括具体趋势)——然后加载对应剧本。后续所有流程均由格式剧本驱动,需严格遵循其流程。请勿在此处重新实现生产逻辑;只需确定格式,交由剧本执行即可。
Parameters
参数
- handle (required) — IG or TikTok handle in any of /
@name/ full-URL form. Saved asname. Asked in Stage 0.state.handle - format (optional) — one of /
talking/pov/dance. If the user names it up front (e.g.duet), skip the format question and go straight to routing. If absent or "not sure", Stage 0 resolves it.content-director @ilor pov - brief (optional) — goal / camera comfort / filming constraints / language. Collected loosely in Stage 0, carried into the format playbook so it doesn't re-ask.
- handle(必填)——IG或TikTok账号,支持/
@name/ 完整URL格式。保存为name,在第0阶段收集。state.handle - format(可选)——可选值为/
talking/pov/dance。如果用户直接指定格式(例如duet),则跳过格式选择步骤,直接进入路由流程。若未指定或“不确定”,则在第0阶段确定格式。content-director @ilor pov - brief(可选)——创作目标/镜头拍摄舒适度/拍摄限制/语言。在第0阶段大致收集,带入格式剧本以避免重复询问。
Stage 0 — Pick a format (this is the whole skill)
第0阶段——选择格式(本工具的核心流程)
This stage has three moves. Always do 0a. Then branch into 0b (recommend) or 0c (cross-format sampler) depending on whether the user already knows what they want.
本阶段包含三个步骤。始终先执行0a,然后根据用户是否明确需求,分支执行0b(推荐)或0c(跨格式样本菜单)。
Step 0a — Intake (print verbatim, then stop and wait)
步骤0a——信息收集(严格按以下内容输出,然后等待用户回复)
If carries no handle, print this verbatim and wait — do not call any tool until the user replies:
$ARGUMENTSI'm your content director — I can build you four kinds of trend videos. Which one are you in the mood for?
- 🗣️ Talking-to-camera — you talk to the lens. Storytime, hot takes, "things nobody tells you", confessionals. Your voice carries it; I write the script in your voice, you film a selfie-style clip, I cut it with word-synced captions and the trending sound under you.
- 🎬 Silent POV — no talking. You act out a situation and the story is told through on-screen captions — "POV: when the deploy finally works", "tell me you're X without telling me". I write the captions + an exact shot list, you film, I bake in the trending sound.
- 💃 Dance — you don't even have to film. Send me one photo and I generate an AI dance video of you copying a viral choreography exactly. Silent output; you attach the sound on-platform at upload.
- 🤝 Stitch / Duet — react to a viral video. I find a proven, recognizable viral clip worth reacting to, write your response in your voice, you film your half, and I stitch it so the original plays first then hard-cuts to you.
Two things I need:
- Your Instagram or TikTok handle (required either way) —
,@you, or a full URL.you- Which format? Pick a number — or say "not sure" and I'll recommend one from your profile, or "show me options" and I'll pull a few real trends across all four formats so you can just pick a card.
Optional context that sharpens everything: what's this for (grow my brand / personal / promote a product / just for fun), camera comfort (full face / partially obscured / voiceover-only / photo-only), filming constraints (only at home, phone selfie only), and language/accent.
Once a reply arrives:
- Save the handle as and any optional context as
state.handle.state.brief - If the user picked a number / named a format → skip to Stage 1 (Route).
- If the user said "not sure" → go to 0b.
- If the user said "show me options" / "show me trends" / "pick a card for me" → go to 0c.
- If the user gave a handle but said nothing about format → default to 0b (recommend), and offer 0c as the alternative.
如果中未包含账号,严格输出以下内容并等待——在用户回复前请勿调用任何工具:
$ARGUMENTS我是你的内容导演——我可以帮你制作四种类型的趋势视频。你想尝试哪一种?
- 🗣️ 镜头前讲解——你对着镜头讲话。适合故事分享、热门观点、“没人告诉你的事”、自白类内容。由你的声音主导;我会用你的风格撰写脚本,你拍摄自拍风格的视频片段,我会为视频添加台词同步字幕,并搭配热门音频。
- 🎬 无声POV——无需讲话。你表演场景内容,通过屏幕字幕讲述故事——“POV: 当部署终于成功时”、“暗示你是X但不明说”风格。我会撰写字幕+精确的镜头列表,你负责拍摄,我会为视频内置热门音效。
- 💃 舞蹈——你甚至无需拍摄。发送一张你的照片,我会生成AI舞蹈视频,精准复刻热门舞蹈动作。输出为无声视频;你只需在平台上传时自行添加音效即可。
- 🤝 合拍/对唱——对热门视频做出反应。我会找到已验证、辨识度高的热门视频,用你的风格撰写反应内容,你拍摄自己的部分,我会将视频拼接为原视频先播放,再硬切至你的反应内容。
我需要你提供两项信息:
- 你的Instagram或TikTok账号(必填)——格式可为
、@you或完整URL。you- 选择哪种格式? 选择对应数字——或者说“不确定”,我会根据你的账号内容推荐合适的格式;或说“展示选项”,我会提供跨四种格式的真实趋势卡片供你选择。
可选补充信息(能优化创作效果):创作目的(打造品牌/个人分享/推广产品/娱乐)、镜头拍摄舒适度(全脸出镜/部分遮挡/仅旁白/仅照片)、拍摄限制(仅在家拍摄/仅手机自拍)、语言/口音。
收到用户回复后:
- 将账号保存为,将可选补充信息保存为
state.handle。state.brief - 如果用户选择了数字/指定了格式 → 跳过至第1阶段(路由)。
- 如果用户说“不确定” → 执行0b步骤。
- 如果用户说“展示选项”/“展示趋势”/“帮我选卡片” → 执行0c步骤。
- 如果用户提供了账号但未提及格式 → 默认执行0b(推荐),并提供0c作为备选。
Step 0b — Recommend a format from their profile
步骤0b——根据用户账号推荐格式
Scrape the profile once ( on ; fall back to on the public profile URL if it's empty / rate-limited — and say so). Prefer compact profile reads first: use with for profile/post discovery, then fetch raw posts only for the specific media URLs you actually need. Pull the most recent 12–20 posts only when the compact result is not enough.
mcp__plugin_pika_pika__scrape_socialstate.handlemcp__plugin_pika_pika__capture_websitedigest: truedigest_top_n: 12Identity-confirmation gate before profiling. Before you synthesize , confirm identity from the scrape or screenshot: display name, verified badge, follower count, bio, platform, and whether recent posts match the requested creator. Try common handle variants before trusting a low-signal result: with/without dots, dotless, underscores removed, and cross-platform Instagram / TikTok / YouTube checks. Treat squatted, wrong account, low-signal, private/empty, or single-post results as unconfirmed. When unconfirmed, stop and ask "Is this you?" with the evidence you saw (, verified badge status, display name, bio snippet, platform URL, recent-post summary) and offer the likely variant instead; do not synthesize or build before identity is confirmed. Load-bearing examples: can resolve to wrong IG/TikTok accounts while the real creator is on YouTube; should trigger a dotless variant check.
state.profileN followersstate.profile@johnnyharris@cleo.abram@cleoabramAfter identity is confirmed, set , then synthesize a short : niche, written voice (3 adjectives), spoken voice if any talking-head clips exist, aesthetic, body-language baseline (do they move / dance / talk on camera at all?), what already over-performs. Keep this in context — the format playbook will reuse it; do not let it re-scrape from scratch.
state.identity_confirmed = truestate.profilestate.profileThen recommend using this mapping (rank, don't hard-filter — see the trend-vs-voice separation rule):
| Signal in the profile | Lean format |
|---|---|
| Talks on camera, has takes/opinions, storytime energy, comfortable full-face | talking |
| Visual / situational / aesthetic-led, doesn't like talking, strong b-roll instinct | pov |
| Already dances or moves well, OR is camera-shy about live performance but fine being AI-generated, OR has no footage to work with | dance |
| Reactive / commentary niche, strong opinions on others' content, wants to ride existing virality | duet |
Present it as: "Based on your profile I'd lean {format} because {1–2 lines}. Want me to run with that, or see a few trends across all four formats first?" If they confirm → Stage 1. If they want options → 0c.
仅抓取一次用户账号内容(调用接口,传入;如果结果为空/触发限流,则回退调用接口抓取公开账号URL——并告知用户此情况)。优先使用精简的账号读取方式:设置和来发现账号/帖子内容,仅在需要时才抓取特定媒体URL的原始帖子。仅当精简结果不足时,才抓取最近12–20条帖子。
mcp__plugin_pika_pika__scrape_socialstate.handlemcp__plugin_pika_pika__capture_websitedigest: truedigest_top_n: 12身份确认前置校验。在生成之前,需通过抓取内容或截图确认身份:显示名称、认证标识、粉丝数量、简介、平台,以及最近的帖子是否匹配用户要求。在信任低信号结果之前,尝试常见的账号变体:带/不带点、无点格式、移除下划线,以及跨平台(Instagram/TikTok/YouTube)校验。将抢注账号、错误账号、低信号账号、私密/空账号或仅含单条帖子的结果视为未确认。如果身份未确认,停止操作并询问**“这是你的账号吗?”**,同时展示你获取的证据(粉丝、认证状态、显示名称、简介片段、平台URL、最近帖子摘要),并提供可能的正确账号变体;在身份确认前,请勿生成或构建。典型示例:可能指向错误的IG/TikTok账号,而真实创作者在YouTube;需触发无点格式的变体校验。
state.profileNstate.profile@johnnyharris@cleo.abram@cleoabram身份确认后,设置,然后生成简短的:细分领域、文字风格(3个形容词)、口语风格(如果存在镜头前讲话片段)、审美风格、肢体语言基准(是否在镜头前移动/跳舞/讲话?)、哪些内容表现较好。请保留该上下文——格式剧本会复用此信息;请勿让剧本重新抓取内容。
state.identity_confirmed = truestate.profilestate.profile然后根据以下映射关系推荐格式(按优先级排序,而非硬过滤——请遵循趋势与风格分离规则):
| 账号内容信号 | 推荐格式 |
|---|---|
| 有镜头前讲话内容、观点输出、故事分享风格、舒适全脸出镜 | talking |
| 视觉/场景/审美主导、不喜讲话、有较强的备用镜头意识 | pov |
| 已有舞蹈或动作内容,或者对真人出镜害羞但接受AI生成内容,或者无可用素材 | dance |
| 专注评论/反应类内容、对他人内容有明确观点、想要借助已有热度 | duet |
推荐话术示例:**“根据你的账号内容,我推荐你选择*{format}格式,原因是{1-2句话}。要直接开始制作,还是先看看跨四种格式的趋势选项?”* 如果用户确认 → 进入第1阶段。如果用户想要查看选项 → 执行0c步骤。
Step 0c — Cross-format sampler menu (~10 real cards across the four formats)
步骤0c——跨格式样本菜单(约10张覆盖四种格式的真实卡片)
This is the "give me a trend for each format and I'll choose" path. Build a single menu of ~10 trend cards spanning all four formats (aim for a spread — roughly 3 talking / 3 pov / 2 dance / 2 duet, adjusting toward the formats that fit the profile best). Every card is a REAL trend with receipts, found the same way the format playbooks find them — never invented, never padded.
Before building the sampler, require and . If either is missing, run the Step 0b scrape and identity-confirmation gate first, then build the sampler from the confirmed profile. Do not build sampler cards from an unconfirmed handle.
state.profilestate.identity_confirmed = trueUse each format's own research method and gate:
- talking / pov — fingerprinted or culturally-recognized viral formats. Reference clips ≥500K plays (broad) or ≥50K (niche). See the virality receipts gate and the trend fingerprint gate.
- dance — a currently-viral dance with a concrete, openable reference-clip URL whose choreography we can copy.
- duet — a viral, recognizable ORIGINAL worth reacting to; proof is the original's ≥500K plays, not a replication wave. See the duet reaction model.
Research order (don't skip — this order is the gate): discover named trends this week via WebSearch across 3+ creator-tool blogs (Later / Hootsuite / Buffer / OpusClip / Manychat) → capture each fingerprint (audio URL or verbatim opener) → verify replicators / play counts via (, , with such as the user's geo or when unknown, ) → tag each surviving trend with its format. Drop anything that can't show the receipts. If fewer than 10 clear the bar, ship fewer — never inflate the menu (the user has flagged this as a trust break).
mcp__plugin_pika_pika__scrape_socialtiktok/hashtagtiktok/keywordtiktok/trending-feedparams.regionUSinstagram/reels-searchCard format:
[N] {FORMAT BADGE: 🗣️ TALKING / 🎬 POV / 💃 DANCE / 🤝 DUET} • {Named trend (≤4 words)}
Fingerprint: {audio name + artist OR verbatim opener OR (duet) the original's name/what-it-is}
Template: {one sentence — the structure all replicators follow, OR (duet) the obvious take}
Requirements before picking: {none OR required disclosure/prop/location/phone orientation/source constraint, stated plainly}
Why it fits {handle}: {1 line in the user's-voice terms}
▶ Reference {clips/original} (real, openable, above threshold):
1. {URL} — {play_count} plays, {creator handle}, {date}
2. {URL} — {play_count} plays, {creator handle}, {date}
3. {URL} — {play_count} plays, {creator handle}, {date} (duet: 1 original URL + its play count is enough)Save the set as . Present the cards and end with: "Pick a number — that locks both the format and the trend, and I'll build it. Or tell me a format and I'll dig deeper into just that one."
state.samplerWhen the user picks a card, set from the card's badge and to that trend (carry the fingerprint + reference URLs forward), then go to Stage 1.
state.formatstate.pick此路径适用于“每种格式给我一个趋势选项,我来选择”的场景。构建一个包含约10张覆盖四种格式的趋势卡片的菜单(尽量均衡分布——大致3张talking/3张pov/2张dance/2张duet,可根据账号适配情况调整比例)。每张卡片均为带验证信息的真实趋势,采用与格式剧本相同的方式查找——请勿虚构或填充内容。
在构建样本菜单前,需确保存在且。如果缺少任一条件,先执行步骤0b的抓取和身份确认流程,再基于已确认的账号内容构建样本菜单。请勿基于未确认的账号构建样本卡片。
state.profilestate.identity_confirmed = true采用每种格式对应的调研方法和校验规则:
- talking / pov——已被识别的热门格式。参考视频需满足**≥50万播放量(通用领域)或≥5万播放量(细分领域)**。请遵循热度验证规则和趋势特征校验规则。
- dance——当前热门的舞蹈,需提供可打开的参考视频URL,且其舞蹈动作可被精准复刻。
- duet——热门、辨识度高的原创视频,值得做出反应;验证标准为原视频≥50万播放量,而非模仿视频的播放量。请遵循对唱反应模型规则。
调研顺序(请勿跳过——此顺序为校验流程):通过WebSearch从3+创作者工具博客(Later/Hootsuite/Buffer/OpusClip/Manychat)查找本周已命名的趋势 → 记录每个趋势的特征(音频URL或开场台词) → 通过接口(、、,可设置为用户所在地区,未知时设为,)验证模仿视频/播放量 → 为通过验证的趋势标记对应格式。移除所有无法提供验证信息的趋势。如果通过验证的趋势不足10个,就展示实际数量——请勿填充内容(用户会将填充内容视为信任破坏)。
mcp__plugin_pika_pika__scrape_socialtiktok/hashtagtiktok/keywordtiktok/trending-feedparams.regionUSinstagram/reels-search卡片格式:
[N] {格式标识: 🗣️ TALKING / 🎬 POV / 💃 DANCE / 🤝 DUET} • {趋势名称(≤4个单词)}
特征: {音频名称+艺术家 或 开场台词 或 (对唱)原视频名称/内容}
模板: {一句话说明——所有模仿视频遵循的结构,或(对唱)明确的反应方向}
选择前需满足: {无 或 明确说明所需的披露/道具/地点/手机方向/来源限制}
适配{handle}的原因: {1句符合用户风格的说明}
▶ 参考{视频/原视频}(真实可打开,满足播放量阈值):
1. {URL} — {播放量}播放,创作者账号{creator handle},发布日期{date}
2. {URL} — {播放量}播放,创作者账号{creator handle},发布日期{date}
3. {URL} — {播放量}播放,创作者账号{creator handle},发布日期{date} (对唱格式:仅需1个原视频URL及其播放量即可)将卡片集合保存为。展示卡片后,结尾话术:“选择对应数字——这会锁定格式和趋势,我将开始制作。或者告诉我你想要的格式,我会深入提供该格式的趋势选项。”
state.sampler当用户选择卡片后,将卡片标识中的格式设置为,将该趋势设置为(携带特征+参考URL),然后进入第1阶段。
state.formatstate.pickStage 1 — Load the format playbook
第1阶段——加载格式剧本
Once is known, read the matching playbook file and follow it verbatim — this is a file read, not a separate skill invocation:
state.format | Read playbook |
|---|---|
| |
| |
| |
| |
确定后,严格读取对应剧本文件并遵循其内容——此操作为文件读取,而非调用独立工具:
state.format | 读取的剧本文件 |
|---|---|
| |
| |
| |
| |
Step 1a — Loaded playbook capability surface
步骤1a——加载剧本的能力范围
Because this registered skill loads the format playbooks instead of registering separate slash skills, its frontmatter declares the union of MCP tools those playbooks may invoke:
required-capabilitiesmcp__plugin_pika_pika__scrape_socialmcp__plugin_pika_pika__task_statusmcp__plugin_pika_pika__capture_websitemcp__plugin_pika_pika__transcribe_audiomcp__plugin_pika_pika__analyze_mediamcp__plugin_pika_pika__create_teleprompter_handoffmcp__plugin_pika_pika__probe_mediamcp__plugin_pika_pika__edit_trimmcp__plugin_pika_pika__edit_concatmcp__plugin_pika_pika__edit_reframemcp__plugin_pika_pika__edit_transcodemcp__plugin_pika_pika__edit_video_upscalemcp__plugin_pika_pika__edit_audio_replacemcp__plugin_pika_pika__edit_audio_mixmcp__plugin_pika_pika__edit_audio_stitchmcp__plugin_pika_pika__edit_audio_trimmcp__plugin_pika_pika__edit_split_screenmcp__plugin_pika_pika__add_captionsmcp__plugin_pika_pika__extract_audio_from_videomcp__plugin_pika_pika__generate_reference_videomcp__plugin_pika_pika__render_html_animation
Any loaded playbook MCP worker can return instead of an inline URL/result when the server budget expires or a render runs in the background. When that happens, immediately call in a tight loop (no Bash, no sleep) until is , , or ; when completed, continue the playbook with the returned field as that tool's output. Do not proceed with placeholder URLs while a task is still or .
{task_id, status}mcp__plugin_pika_pika__task_status(task_id=<task_id>)statuscompletedfailedcancelledresultqueuedrunningRead the file from the skill directory, carry and into it, and run its pipeline.
state.handlestate.briefCritical rule — don't redo work you've already done. You are the same agent in the same conversation; everything you scraped and surfaced in Stage 0 is still in context. When you load the playbook:
- If the user picked a specific trend from the 0c sampler (is set) and
state.pickplusstate.profileexist → carry it in as the chosen trend. Skip the playbook's own menu-building (Stages 2–3); confirm the pick with a quick verification scrape if needed, then resume the playbook at its Stage 4 (production package). Re-researching a fresh menu here wastes a turn and may surface a trend the user didn't ask for.state.identity_confirmed = true - If is set but no confirmed profile exists → start the loaded playbook at Stage 1 so its identity-confirmation gate runs before production, but do not follow that Stage 1 handoff into Stage 2. After identity is confirmed, carry the picked trend forward and resume at Stage 4; skip only Stages 2–3.
state.pick - If you already built in 0b/0c and
state.profile→ reuse it. Do NOT re-scrape. Jump straight to the playbook's trend stage with the confirmed profile already in hand.state.identity_confirmed = true - If only the format is locked (no specific trend yet) and no confirmed profile exists → start the loaded playbook at Stage 1 so its identity-confirmation gate runs. If and
state.profilealready exist, resume at Stage 2 (trend research) and skip re-scraping.state.identity_confirmed = true
State it to the user in one line — "Building your {format} trend from here." — then follow the playbook's instructions verbatim from the appropriate stage through its production, edit, and loop stages.
由于本注册工具加载格式剧本而非注册独立的斜杠工具,其前置声明需包含这些剧本可能调用的所有MCP工具:
required-capabilitiesmcp__plugin_pika_pika__scrape_socialmcp__plugin_pika_pika__task_statusmcp__plugin_pika_pika__capture_websitemcp__plugin_pika_pika__transcribe_audiomcp__plugin_pika_pika__analyze_mediamcp__plugin_pika_pika__create_teleprompter_handoffmcp__plugin_pika_pika__probe_mediamcp__plugin_pika_pika__edit_trimmcp__plugin_pika_pika__edit_concatmcp__plugin_pika_pika__edit_reframemcp__plugin_pika_pika__edit_transcodemcp__plugin_pika_pika__edit_video_upscalemcp__plugin_pika_pika__edit_audio_replacemcp__plugin_pika_pika__edit_audio_mixmcp__plugin_pika_pika__edit_audio_stitchmcp__plugin_pika_pika__edit_audio_trimmcp__plugin_pika_pika__edit_split_screenmcp__plugin_pika_pika__add_captionsmcp__plugin_pika_pika__extract_audio_from_videomcp__plugin_pika_pika__generate_reference_videomcp__plugin_pika_pika__render_html_animation
当服务器预算耗尽或渲染在后台运行时,任何加载的剧本MCP工具可能返回而非内联URL/结果。此时需立即调用接口进行循环查询(无需Bash或等待),直到变为、或;完成后,使用返回的字段作为该工具的输出,继续执行剧本流程。在任务处于或状态时,请勿使用占位URL继续流程。
{task_id, status}mcp__plugin_pika_pika__task_status(task_id=<task_id>)statuscompletedfailedcancelledresultqueuedrunning从工具目录读取文件,将和带入剧本,并执行其流程。
state.handlestate.brief关键规则——请勿重复已完成的工作。你是同一对话中的同一Agent;第0阶段抓取和展示的所有内容仍在上下文中。加载剧本时:
- 如果用户从0c样本菜单中选择了特定趋势(已设置),且
state.pick存在且state.profile→ 将该趋势带入剧本。跳过剧本自身的菜单构建流程(第2–3阶段);若需验证,可快速抓取确认,然后从剧本的**第4阶段(生产打包)**继续执行。在此处重新调研新菜单会浪费流程,且可能展示用户未选择的趋势。state.identity_confirmed = true - 如果已设置但未确认账号身份 → 从加载剧本的第1阶段开始执行,以便其身份确认流程在生产前运行,但请勿跟随第1阶段的交接进入第2阶段。身份确认后,带入已选趋势并从第4阶段继续;仅跳过第2–3阶段。
state.pick - 如果已在0b/0c阶段构建且
state.profile→ 复用该信息,请勿重新抓取。直接进入剧本的趋势阶段,已确认的账号信息已准备就绪。state.identity_confirmed = true - 如果仅确定了格式(无特定趋势)且未确认账号身份 → 从加载剧本的第1阶段开始执行,以便其身份确认流程运行。如果存在且
state.profile,则从**第2阶段(趋势调研)**继续,跳过重新抓取步骤。state.identity_confirmed = true
用一句话告知用户:“从此处开始为你制作{format}趋势视频。”,然后从对应阶段开始严格遵循剧本说明执行生产、编辑和循环流程。
Stage 2 — Loop (format switching)
第2阶段——循环(格式切换)
After the playbook delivers, it runs its own Stage-7 loop ("do another from this menu?"). Layer one extra option on top: "…or want to switch formats? Say 'switch to dance/pov/talking/duet' and I'll route you over — your profile's already loaded, so we go straight to trends." On a format switch, set the new , keep and , and re-enter Stage 1 (load the new format's playbook, resume at its Stage 2). If the identity flag is missing, run the new format's Stage 1 identity-confirmation gate before trend research. The profile never gets re-scraped within a session unless identity is unconfirmed.
state.formatstate.profilestate.identity_confirmed = true剧本交付后,会执行自身的第7阶段循环(“从该菜单再制作一个?”)。在此基础上添加一个额外选项:“…或者想要切换格式?说‘switch to dance/pov/talking/duet’,我会将你引导至对应格式——你的账号信息已加载,可直接进入趋势选择。” 当切换格式时,设置新的,保留和,然后重新进入第1阶段(加载新格式的剧本,从其第2阶段继续)。如果身份标识缺失,则在趋势调研前执行新格式的第1阶段身份确认流程。除非身份未确认,否则在会话期间请勿重新抓取账号内容。
state.formatstate.profilestate.identity_confirmed = trueWhat NOT to do
禁止操作
- Don't reimplement production here. This skill resolves the format and loads the playbook. The script-writing, shot lists, generation, and edit pipelines live in the format playbooks under — run those, don't paraphrase them.
formats/ - Don't re-scrape the profile after Stage 0. One scrape per session; carry into the format playbook and any format switch.
state.profile - Don't rebuild a menu when the user already picked a card in 0c. Carry the pick into the playbook's Stage 4. Re-researching burns a turn and risks drifting off the chosen trend.
- Don't invent or pad the cross-format sampler. Every card needs real reference links + play counts at threshold. Fewer real cards beats ten padded ones — see the virality receipts gate.
- Don't filter trends down to the user's exact niche. Find real broad trends across formats; the user's voice attaches via the script/captions in the format playbook. See the broad-versus-niche menu rule and the trend-vs-voice separation rule.
- Don't surface carousel or transition trends. Out of scope for this bundle — they're not part of Content Director.
- Don't skip the format question when the user is unsure. Recommend from the profile (0b) or show the sampler (0c); never silently guess a format and start producing.
- Don't proceed without a handle. Both the recommendation and every format playbook need it — Stage 0a blocks until it arrives.
- 请勿在此处重新实现生产逻辑。本工具仅负责确定格式并加载剧本。脚本撰写、镜头列表、生成和编辑流程均位于目录下的格式剧本中——请执行这些剧本,请勿改写内容。
formats/ - 第0阶段后请勿重新抓取账号内容。每个会话仅抓取一次;将带入格式剧本和任何格式切换流程。
state.profile - 当用户已从0c样本菜单选择卡片时,请勿重新构建菜单。将已选趋势带入剧本的第4阶段。重新调研会浪费流程,且可能偏离用户选择的趋势。
- 请勿虚构或填充跨格式样本菜单。每张卡片需包含真实参考链接+符合阈值的播放量。真实卡片数量少优于10张填充卡片——请遵循热度验证规则。
- 请勿将趋势过滤至用户的精确细分领域。查找跨格式的真实通用趋势;用户的风格会通过格式剧本中的脚本/字幕体现。请遵循通用与细分菜单规则以及趋势与风格分离规则。
- 请勿展示轮播图或转场趋势。不在本合集的服务范围内——不属于内容导演工具。
- 当用户不确定时,请勿跳过格式选择步骤。根据账号内容推荐(0b)或展示样本菜单(0c);请勿擅自猜测格式并开始制作。
- 无账号信息时请勿继续流程。推荐功能和所有格式剧本均需账号信息——第0a阶段会阻塞流程直到获取账号信息。