Menu
大师智囊团：收到用户的决策、竞争、执行、方向、情绪类问题时，自动匹配2-4位思维方式最相关的跨时代大师，以各自的心智模型给出具体、可执行、带分歧的建议。 显式触发：「智囊团」「让大师看看」「XX会怎么看」「召集顾问」。 隐式触发：「我该不该…」「纠结」「选A还是B」「帮我决策」「被卡住了」「坚持不下去」「竞品/对手怎么应对」「方向迷茫」「很内耗」。 不在一般性知识问答、写作、编码任务上触发。
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Add captions to a talking-head video. ONE catalog (CATALOG.md) of 36 visual identities behind two engines: column-flow (captions composited INTO the scene — matte occlusion + mix-blend; cream/ink/editorial/keynote/documentary/loud/neon/glitch/chrome/velocity) and themed constitutions (anchor/ordnance/terminal/neonsign/stardust/stomp/scoreboard/transit/vhs/arcade/dossier/laser/thunder/hologram/biolume/aurora/spectrum/papercut/popup/chalkboard/graffiti/brush/inkwater/ransom/lastpage/nightcity — e.g. a glyph-decode climax, a neon sign WRITTEN stroke by stroke, or the quiet `anchor` rail default). Route by identity, never by mode. Trigger on "captions/subtitles", "embed/cinematic captions", "VFX captions", "炸/特效/酷炫字幕", a named identity, or top-tier motion-graphics asks. Embedding every word is wrong for most talking-head content — `anchor` is the verbatim default. Runs locally end-to-end (transcribes and mattes the subject itself, no API key). Requires hyperframes and a single-subject clip (multi-shot clips are s
Turn arbitrary text — an article, notes, a topic, a brief — into a faceless explainer video: there is no site or footage to capture, so the visuals are invented per scene (typography, abstract graphics, diagrams, data-viz). Use for topic explainers, concept breakdowns, how-tos, listicles. Not a product promo (/product-launch-video) or a site tour (/website-to-video). Unclear → /hyperframes.
Import Figma content into a HyperFrames composition — rendered assets, brand tokens, components, storyboard sections → reconstructed motion (frames read as states, not slides) (REST/CLI), Figma Motion animations (MCP), and shaders (MCP source / native export). Use when the user pastes a figma.com link or asks to bring a Figma design, frame, logo, brand, or animation into a video/composition.
The fallback workflow for authoring or editing any custom HyperFrames composition at any length or format — longer / multi-scene pieces, brand and sizzle reels, montages, title cards, static loops, freeform builds. Use only when no specialized workflow fits the input; routing table at /hyperframes.
All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus Lottie, Three.js, Anime.js, CSS keyframes, Web Animations API, TypeGPU). Use for any motion or animation task: pick 2-4 rules and compose, or load a blueprint, or look up runtime-specific API (e.g. GSAP eases / Lottie player / Three.js mixer). Also covers auditing an existing composition's choreography (animation map) and 24 named text-animation effects. HyperFrames-native: single paused timeline, seek-safe, deterministic.
HyperFrames CLI dev loop. Use when running npx hyperframes init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, render, publish, feedback, lambda, doctor, browser, info, upgrade, skills, compositions, docs, benchmark, telemetry, transcribe, tts, or remove-background (validate/inspect/layout are deprecated aliases covered by check), or when troubleshooting the HyperFrames build/render environment. Entry point for AWS Lambda cloud rendering (`hyperframes lambda deploy / render / progress / destroy / policies / sites`).
| name | master-advisory |
| description | 大师智囊团：收到用户的决策、竞争、执行、方向、情绪类问题时，自动匹配2-4位思维方式最相关的跨时代大师，以各自的心智模型给出具体、可执行、带分歧的建议。 显式触发：「智囊团」「让大师看看」「XX会怎么看」「召集顾问」。 隐式触发：「我该不该…」「纠结」「选A还是B」「帮我决策」「被卡住了」「坚持不下去」「竞品/对手怎么应对」「方向迷茫」「很内耗」。 不在一般性知识问答、写作、编码任务上触发。 |
不是12个人的圆桌合唱,是按问题点将、强制有反方的作战会议。
references/ 下,只加载被匹配到的那几位,不要全量加载。roster.md 速查表(管辖域/首问/天然反方)。召集大师之前,先做两件事:
① 问题是真问题吗?
| 信号 | 处理 |
|---|---|
| 问题清晰、约束具体、有真实选项 | 放行 → Step 1 |
| 需要改写,但只是收窄/明确化,没动问题本质 | 改写后注明「我按XX理解往下答,不对请纠正」,直接推进 |
| 改写动了问题本质(如「该不该辞职」改成「切换条件是什么」) | 必须停下,把重述交用户确认后再召集 |
| 用户在宣泄情绪而非求解 | 不召集智囊团,正常陪伴对话 |
② 关键约束够不够? 大师的建议必须挂钩用户的具体处境(红线4)。若当前上下文缺少做判断必需的约束(财务底线/时间窗/利益相关方/已尝试过什么),门卫先收齐再召集——上下文不足时强行开会,产出的只能是通用建议,等于违规。
门卫合计最多3问,不许连环追问变成审讯。
| 问题类型 | 典型表达 | 方向位 | 机制位 | 反方位 |
|---|---|---|---|---|
| 决策取舍 | 该不该/选哪个/值不值 | 芒格 | 纳瓦尔 | 马斯克 |
| 竞争博弈 | 对手/竞品/后发/以弱胜强 | 孙子 | 芒格 | 稻盛和夫 |
| 执行卡壳 | 推不动/坚持不住/反复失败 | 曾国藩 | 达里奥 | 马斯克 |
| 方向迷茫 | 职业/定位/长期往哪走 | 纳瓦尔 | 稻盛和夫 | 荣格 |
| 情绪内耗 | 人际冲突/自我怀疑/愤怒嫉妒 | 荣格 | 曾国藩 | 老子 |
| 系统复盘 | 流程/组织/同类错误重犯 | 达里奥 | 芒格 | 老子 |
| 突破约束 | 资源不够/都说不可能 | 马斯克 | 孙子 | 芒格 |
席位职能(默认3位,复杂问题4位):
规则:
快诊模式:问题量级小(单一场景、可逆、影响期<1个月)→ 只出2位(方向位+反方),每人判断1句+动作1条,分歧1句,总长半屏。重大不可逆决策才走完整格式。
references/ 加载被点将者的档案。〈问题重述〉 一句话。若门卫改写过问题,在此注明。
── 每位大师(含反方)──
【他会先问你】 一个问题,来自档案里的首问协议
【判断】 必须引用用户问题中的具体细节,3-5句
【动作】 1-2条,今天就能做的
〈分歧〉 必写。他们在哪里不同意;这个分歧取决于用户的什么前提;
什么信号出现时该听谁的。
〈一句话收束〉 综合后的最小行动建议。
留一个真问题:各大师的首问多数是修辞性的(问完自答)。但若某位大师的判断实质依赖用户的答案(答A则听甲、答B则听乙),该问题不许自答假设——在〈分歧〉中明确标注「这个问题只有你能答,答案决定听谁的」,把它留给用户。每次会诊最多留1个。
新增大师档案用 女娲 · Skill造人术 蒸馏,须过三重验证(跨域复现/生成力/排他性),必含:管辖域、首问协议、心智模型(3-5)、决策启发式、表达DNA、反模式、研究维度、诚实边界。写入 references/[name].md 并在 roster.md 登记。