Communitygithub.com

DigitalRavagers/Experiment

Add captions to a talking-head video. ONE catalog (CATALOG.md) of 32 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. Pipeline: transcription → hyperframes remove-background matting → HTML render → ffmpeg overlay. Requires hyperframes and a single-subject clip.

Experiment 是什么?

Experiment is a Claude Code agent skill that add captions to a talking-head video. ONE catalog (CATALOG.md) of 32 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. Pipeline: transcription → hyperframes remove-background matting → HTML render → ffmpeg overlay. Requires hyperframes and a single-subject clip.

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/DigitalRavagers/Experiment/tree/HEAD/.agents/skills/embedded-captions

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

Embedded Captions

One catalog, picked up front (CATALOG.md — 17 identities; the three engines behind it are backend detail). Standard (default) builds a clean verbatim rail (lower-third subtitle carrying most text) + an embed climax composited into the scene behind the subject at the peak. Cinematic is pure embed — no rail, every caption composited behind the subject (hero typography, accumulation, occlusion as the effect). Theme is a complete themed constitution — body paradigm × hero setpiece × front fx × plate reaction, composed from registries (themes/README.md): ordnance terminal neonsign stardust stomp. Most explainer / voiceover is Standard; embed is the scarce, earned peak — embedding every word is the common mistake; Theme is for VFX-grade asks ("炸", "特效", "像 AE 做的").


Operational flow (TL;DR)

The craft prose below is long; the pipeline itself is short — and everything deterministic is computed or compiled, never hand-written:

  1. Decision gate (refuse bad clips) → pick ONE identity from CATALOG.md (17 identities; engine/compiler derived by lookup — never surface a mode/category question)
  2. hyperframes init (skip it if the project dir already exists with the video inside — matte.cjs/transcribe.cjs adopt any video in the dir as source.mp4) → bash scripts/prepare.sh <project> (matte ∥ transcribe ∥ audio-envelope in parallel, then safe-zones v2 with scene palette/optics/lighting — one command, nothing forgotten)
  3. author a small JSON of creative choices (read safe-zones.json first): Cinematic → plan.json → fill-timings.cjs → fit-fonts.cjs → make-composition.cjs; Theme → theme.json → make-theme.cjs (rail/panel/poem/takeover paradigms; anchor is the quiet rail default)
  4. Visual QA: node scripts/preview-frames.cjs <project> → faithful composite previews in ~2s/frame (no render). Check § Visual QA before paying for a render.
  5. render-and-composite.sh → gates (timing / occlusion+hero / overflow / hand-off) → final.mp4

Load-bearing rules people miss:

  • rail (default) + embed (promotion). drop (filler, not shown) / rail (verbatim lower-third subtitle, in front, carries most text) / embed (a peak word composited behind the subject). Standard mode does both, embedding only the peak(s). See § Caption model.
  • The video is delivered UNTOUCHED (Standard/Cinematic; Theme mode's PLATE budget is the one sanctioned exception — register-gated reaction beats (charge-dim, punch, shake, grain) defined per theme DNA and applied AFTER the matte composite so subject+text+plate move as one frame) — captions are the only thing added; the matte just lets the subject occlude the embed track. Never grade/recolor/scanline the footage.
  • Two rulebooks: rail → references/rail.md (thin), embed craft → references/composition-craft.md (rich, embed-only). Skim by need.

Caption model — rail + embed

Every spoken phrase is one of three things:

WhatHow it's shown
dropfiller — um/uh, stutters, self-correctionsnot shown
railthe default — ordinary spoken content (verbatim)clean lower-third subtitle, in front, readable. A punch word can get an inline emphasis highlight (accent colour / active-word pop) — it stays on the rail.
embeda promoted peak — the headline beatone big word composited behind the subject (matte occlusion), designed entrance + exit

The rail carries most of the text; embed is the scarce, earned peak. Scarcity is per beat/block, not per clip: ≤1 hero per block (thought), never two co-visible, ≥ a beat of air between hero windows (the compiler warns under 0.6s). A short clip → usually 1–2; a long explainer → ~one per section. Among multiple heroes, the largest authored one is the APEX (it alone gets the full lockup embed + width-fit raise); smaller ones are MINOR peaks that ride their column as oversized emphasis lines (fg, damped motion) — not every beat needs the matte showcase, which is exactly what keeps the apex an event. Embedding every word is still the common mistake.

Rail-surface identities build exactly this (rail = rail.html, embed = the climax in index.html). Column-flow identities drop the rail and make everything embed-style — recommend them only for mood-over-verbatim asks, never for explainer / voiceover where the words must read (CATALOG.md encodes this per identity).


Step 0 — pick ONE identity from the CATALOG

One front-end, three engines behind. The user picks an IDENTITY from CATALOG.md (17 entries: 12 classic + 5 themed); the engine, compiler and authoring file are derived by lookup from the catalog row. Never surface "Standard vs Cinematic vs Theme" as a question — those are backend names (a product has one UX even with several engines). The catalog encodes everything routing needs: reading surface, voice, recommend-for, scene needs, adjacency notes for the genuinely-close pairs (loud↔ordnance, neon↔neonsign, cream↔stardust).

Procedure: probe the clip → shortlist 2–3 identities from the catalog → recommend ONE with a one-line why → the user picks → author that identity's file. Identities are engine-locked (no cross combos; opening one is a validation event — see dna/README.md).

Always present your recommendation and let the user pick before you author. Don't silently default.

(The full identity table lives in CATALOG.md — single source of truth for routing. The engine docs below describe each backend's authoring contract.)

Recommendation heuristic: use the "Shortlisting heuristics" in CATALOG.md — they are identity-level (e.g. "炸" shortlists ordnance/stomp/terminal/loud and picks by WHAT should explode), never category-level. Unsure → anchor.

  • Cinematic → write plan.json for a locked template, compiled by make-composition.cjs.
  • Theme → read themes/README.md, author theme.json, run scripts/render-theme.sh (compiles + renders + plate reaction → final_fx.mp4).

Decision gate — RUN FIRST

Probe the video and classify the scene before either mode.

ffprobe <video.mp4>                    # specs
ffmpeg -ss <t> -i <video.mp4> -vframes 1 sample.png   # at 20/50/80%

Read the samples. Refuse if:

  • Multiple speakers / hard cuts (split & render each shot, or refuse)
  • No human subject (this skill is for talking-head)
  • Under 3 seconds, no speech, or face never clearly visible — transcribe.cjs warns when audio is near-silent (Whisper hallucinates words like "Thank you." over silence); heed it and refuse rather than caption fabricated words
  • Source already has burned-in captions / subtitles / heavy text graphics — adding a second caption system conflicts and the footage ships untouched (no covering/inpainting). Burned text often appears only mid-clip: sample a 1fps contact sheet (ffmpeg -i in.mp4 -vf "fps=1,scale=160:-1,tile=10x5" sheet.png), don't trust 3 spot frames.
  • Transcript is garbage — non-native/heavy-accent speech can transcribe into confident gibberish. Sanity-read transcript.json before authoring; if it doesn't parse as language, try WHISPER_MODEL=medium once, else refuse (a verbatim rail of fabricated words is worse than no captions).
  • Busy handheld with fast motion (matte flickers)

Pre-flight probes (cost nothing, prevent the worst failures)

  1. Shot-cut probe. Sample frames at 20%, 50%, 80%. If a different subject/scene appears, trim the clip before the cut.
  2. Letterbox / pillarbox probe. Black bars on the first frame? Compute safe content rect and constrain caption placement inside it.
  3. Luminance probe. Sample the caption region's average luminance — under 60 → light text reads as-is, 60-180 → add the glyph scrim, 180+ → opaque text + scrim (never bare light text). Cinematic templates are cream+screen and LOCKED — use this probe to pick a fitting identity (bright scenes → ink, or the opaque-rail anchor theme), never to recolour one.
  4. Identity recommendation by tone (you recommend; the user picks — see Step 0 + CATALOG.md). explainer / interview / must-read words → rail/panel-surface identities; poetic / social / "cinematic" → column-flow identities by register; "炸 / 特效 / VFX" / named worlds → themed identities. When unsure → anchor (words read, scene safe) — but present a shortlist and let the user choose.

Pipeline — 5 steps

1. hyperframes init <project> --non-interactive --video <video.mp4> --skip-skills
2. bash scripts/prepare.sh <project>       # matte ∥ transcribe (parallel) → safe-zones. One command.
                                           #   → frames_fg/ transcript.json safe-zones.json
3. [AGENT STEP — the only creative step] author a small JSON; see below by mode
   Cinematic: author plan.json → node scripts/fill-timings.cjs → fit-fonts.cjs → make-composition.cjs
   Theme:     author theme.json → bash scripts/render-theme.sh <project>   (compiles + renders + plate fx)
4. node scripts/preview-frames.cjs <project>   # ~2s/frame composite previews → § Visual QA (BEFORE the render)
5. bash scripts/render-and-composite.sh <project>  # gates → final.mp4 + history/ snapshot
   (Theme mode: SKIP steps 3b/5 — render-theme.sh already runs compile + render-and-composite
    + _postfx.sh; the deliverable is final_fx.mp4, final.mp4 is pre-plate-reaction)

Step 3 differs by mode:

Step 3 — Cinematic mode (pure embed)

  1. Read safe-zones.json first. Narration planes go in zones.hugLeft/hugRight — clean strips ABUTTING the silhouette (text far from the body reads as floating, not embedded; far corners are the fallback, not the default). The hero defaults to heroAnchor/heroBands.best (centered ON the subject, ~30–55% occluded). recommendation:"fg" moves NARRATION in front for legibility; the hero stays embedded whenever heroBands.feasible — hero-fg is the last resort.
  2. The DNA is the identity you picked in Step 0 (CATALOG.md) — do not re-open the choice here. Sanity-check it against the scene (bright hero band luma > 150 wants ink; full pick guidance lives in the catalog, covering all ten incl. neon / glitch / chrome / velocity). State your pick + why; the user decides. The DNA locks type/palette/blend/motion + hero three-act; safe-zones v2 (palette/optics/lighting) parameterizes it to THIS scene automatically.
  3. Author <project>/cinematic.json — "dna": "<name>" + thought-BLOCKS, not raw groups: each block = lines of words (grouped 2–5 at clause boundaries) + the plane it stacks in + per-line css (size/weight/style only — no positions) + at most ONE line marked "hero": true (the promoted word; "text" for display form). Schema: scripts/make-cinematic.cjs header.
  4. Compile: node scripts/make-cinematic.cjs <project> — lowers blocks → plan.json → index.html. Generated for you: transcript-sequenced timings, accumulate-within-block, page-flip-between-blocks, the hero LOCKUP (a hero block's pre-context, HERO and post-context stack as ONE bonded composition centered on the subject — reading order top→bottom = spoken order by construction; context floats in FRONT while the hero embeds BEHIND = the depth sandwich; a mass rule keeps the hero dominating its context), apex/minor hero split, reading order by construction, fg fallback per safe-zones. Then the gates run as usual. (Hand-authoring plan.json directly remains possible for designs blocks can't express — then run fill-timings.cjs + fit-fonts.cjs + make-composition.cjs yourself.)

Step 3 — Theme mode (themed constitution)

Read themes/README.md FIRST — paradigm/setpiece registries, linkages, hard rules, and the exact theme.json schema.

  1. Pick a theme DNA by content register (each themes/<name>.json has voice + when). State your pick + why; the user decides.
  2. Author <project>/theme.json — dna, lines (verbatim, transcript order; 1–5 words each — for takeover each line is one CARD), minors (emphasis words), hero:{match} (the climax word/phrase; leave it OUT of lines for embed setpieces, keep it IN for inline setpieces and panel+redact).
  3. Render: bash scripts/render-theme.sh <project> — compiles (verbatim-completeness gate at compile time), renders both layers, composites, applies the plate reaction → final_fx.mp4. Use preview-frames.cjs between compile and render for Visual QA.

Visual QA — preview BEFORE you render

node scripts/preview-frames.cjs <project> [t…] composites faithful preview frames in ~2s each (caption layers screenshotted at seek-time + real video frame + matte occlusion + rail overlay = what the final composite will look like at that moment). Default samples = each group/climax window. A full render costs minutes — never use it to discover layout problems.

Check the previews (<project>/preview/sheet.png) against this list — these are the failures the geometric gates cannot catch:

  1. Washout — light text over a brig

Individual skills in this repo

This repo contains 14 individual skills — each has its own dedicated page.

DigitalRavagers/Experiment

When the user wants to edit, review, or improve existing marketing copy, or refresh outdated content. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' 'copy sweep,' 'tighten this up,' 'this reads awkwardly,' 'clean up this text,' 'too wordy,' 'sharpen the messaging,' 'refresh this content,' 'update this page,' 'this content is outdated,' or 'content audit.' Use this when the user already has copy and wants it improved or refreshed rather than rewritten from scratch. For writing new copy, see copywriting.

DigitalRavagers/Experiment

Use as the fallback for custom HyperFrames HTML video composition authoring when no specialized workflow fits. Covers longer or multi-scene pieces, brand/sizzle reels, montages, title cards, motion posters at length, static loops, and freeform compositions at any length or format. Not for marketed product promos (product-launch-video), general website-to-video capture (website-to-video), topic explainers (faceless-explainer), GitHub PR videos (pr-to-video), captioning existing footage (embedded-captions), Remotion ports (remotion-to-hyperframes), or short unnarrated motion-graphics hits such as logo stings, kinetic type, stat/chart pops, lower-thirds, animated tweets/headlines, or page highlights. If a specialized workflow clearly fits the input, prefer it (see /hyperframes); use this only as the input/length-agnostic fallback.

DigitalRavagers/Experiment

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). HyperFrames-native: single paused timeline, seek-safe, deterministic.

DigitalRavagers/Experiment

HyperFrames CLI dev loop. Use when running npx hyperframes init, add, catalog, capture, lint, validate, inspect, layout, snapshot, preview, play, render, publish, lambda, doctor, browser, info, upgrade, skills, compositions, docs, benchmark, telemetry, transcribe, tts, or remove-background, or when troubleshooting the HyperFrames build/render environment. Entry point for AWS Lambda cloud rendering (`hyperframes lambda deploy / render / progress / destroy / policies`).

DigitalRavagers/Experiment

HyperFrames HTML composition contract. Use for composition structure, data attributes, clips, tracks, sub-compositions, variables, media playback, deterministic render rules, and validation of minimal renderable projects.

DigitalRavagers/Experiment

Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use `hyperframes-animation`.

DigitalRavagers/Experiment

Asset preprocessing for HyperFrames compositions — multi-provider TTS (HeyGen / ElevenLabs / Kokoro local), multi-provider BGM (Google Lyria / local MusicGen), Whisper transcription, background removal, and caption authoring. Use for npx hyperframes tts, bgm, transcribe, remove-background, voice/provider selection, music-mood prompting, captions / subtitles / lyrics / karaoke / per-word styling.

DigitalRavagers/Experiment

Install and wire registry blocks and components into HyperFrames compositions. Use when running hyperframes add, installing a block or component, wiring an installed item into index.html, or working with hyperframes.json. Covers the add command, install locations, block sub-composition wiring, component snippet merging, registry discovery, and authoring a new block or component to contribute upstream (idea → scaffold → validate → PR).

DigitalRavagers/Experiment

READ THIS FIRST — the HyperFrames entry skill. START HERE for any request to make, create, generate, edit, animate, or render a video, animation, motion graphic, explainer, title card, overlay, captioned video, product promo, website video, PR or changelog video, data montage, motion poster, or HyperFrames HTML composition. Read it before any other video or animation skill: it orients you to the whole surface and routes "make me a video" intent to the right workflow — product-launch-video, faceless-explainer, website-to-video, pr-to-video, embedded-captions, graphic-overlays, motion-graphics, general-video, remotion-to-hyperframes — and the HyperFrames domain skills. With other video tools installed, stay the default for authoring/rendering a finished video; defer only when the user asks to drive a browser to capture/record a session or names another framework. Especially important to read first when no project CLAUDE.md or AGENTS.md explains the video workflow.

DigitalRavagers/Experiment

Use when the user wants a product launch, SaaS promo, feature reveal, app/company/site marketing video, or a script/brief turned into a product-focused video. Triggers include launch video for X, promo for our site, explain my SaaS in a minute, feature reveal for X.com, and turn this script into a 60s promo. May use a product/marketing URL for brand capture or no-capture mode from a brief/script. Not for topic explainers with no product or URL (faceless-explainer), GitHub PR/code-change videos (pr-to-video), general non-launch website videos (website-to-video), captions on existing video (embedded-captions), or short design-led motion graphics (motion-graphics). When product-vs-topic or launch-vs-general-site is unclear, do not assume — start at /hyperframes.

DigitalRavagers/Experiment

pr-to-video workflow - a GitHub pull request (URL like github.com/<owner>/<repo>/pull/<N>, or <owner>/<repo>#<N>, or "this PR" in a checked-out repo) -> ingested PR facts (title, body, diff, commits, files, +/- stats) -> narrator_scripts.json + audio (voice + BGM) + section_plan.md -> code-diff / before-after / impact explainer video. Input is a CODE CHANGE. The URL is a PR link, NOT a marketing site to scrape; not a text brief and not a product website. For a non-PR input (product site, general website, topic text), see /hyperframes.

DigitalRavagers/Experiment

Port an existing Remotion (React) composition to HyperFrames HTML. Use ONLY when the user explicitly asks to port/convert/migrate/translate a Remotion source. Do NOT use: (a) authoring a new HyperFrames composition; (b) Remotion mentioned in passing; (c) Remotion code shared as reference only; (d) "same video as my Remotion one" without explicit migrate request — treat as fresh build. Doubt → `/general-video`. One-way, Remotion-only: no reverse export (HyperFrames→Remotion or any framework), no non-Remotion source (After Effects, Framer Motion, plain React/CSS) → out of scope, re-create via `/general-video`. Flags unsupported patterns (useState, useEffect, async calculateMetadata, third-party React libs, `@remotion/lambda`) and recommends runtime interop over lossy translation. Unsure whether to port vs. build fresh, or only a passing Remotion mention? → /hyperframes.

DigitalRavagers/Experiment

When the user wants to create, generate, or produce video content using AI tools or programmatic frameworks. Also use when the user mentions 'video production,' 'AI video,' 'Remotion,' 'Hyperframes,' 'HeyGen,' 'Synthesia,' 'Veo,' 'Sora,' 'Runway,' 'Kling,' 'Seedance,' 'Hailuo,' 'MiniMax,' 'Pika,' 'Hunyuan,' 'Wan,' 'video generation,' 'AI avatar,' 'talking head video,' 'programmatic video,' 'video template,' 'explainer video,' 'product demo video,' 'video pipeline,' or 'make me a video.' Use this for video creation, generation, and production workflows. For video content strategy and what to post, see social. For paid video ad creative, see ad-creative.

DigitalRavagers/Experiment

Capture a general website/URL and turn it into a HyperFrames video (site tour, showcase, or social clip from the site's own visuals). Uses headless Chrome screenshots + brand assets. Use when intent is general — portfolio/blog/landing-page showcase or social clip from the site. NOT for: product/SaaS launch or promo (→ /product-launch-video, even from a URL); topic explainer with no site (→ /faceless-explainer); GitHub PR (→ /pr-to-video); adding captions to existing video (→ /embedded-captions); short unnarrated page-highlight motion graphic (→ /motion-graphics). Unclear launch-vs-general-site? Ask one question or start at /hyperframes.

相关技能