@mevdragon/vidfarm-devcli 0.16.0 → 0.18.0

package/.agents/skills/farmville-saas-ux/references/tokens.md

@@ -0,0 +1,271 @@
+# Farmville SaaS — Design Tokens
+
+The complete design system as CSS custom properties. Paste the `:root` block below into your global
+stylesheet and reference the variables everywhere — never hand-pick ad-hoc hex/px values, or the system
+drifts. Values are the real ones distilled from Fillout.com (a Tailwind-v4 default scale + a custom
+honey-gold brand palette + rounded display type).
+
+## Table of contents
+1. Fonts (loading + stacks)
+2. The `:root` token block (copy-paste)
+3. Color rationale
+4. Typography scale & usage
+5. Radius, shadow, spacing rationale
+6. Glass / blur
+7. Motion
+
+---
+
+## 1. Fonts
+
+**Display / headings — `Hanken Grotesk`.** Fillout uses a proprietary rounded grotesque called
+*blMelody*. Hanken Grotesk is the closest free, warm, rounded grotesque with an excellent bold. Good
+alternates, all free on Google Fonts, in order of similarity: **Figtree**, **Gantari**, **Onest**,
+**Plus Jakarta Sans**. If you have a license for blMelody, use it and keep Hanken as the fallback.
+
+**Body / UI — `Inter`.** Exact match to Fillout. Free.
+
+```html
+<link rel="preconnect" href="https://fonts.googleapis.com">
+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
+<link href="https://fonts.googleapis.com/css2?family=Hanken+Grotesk:wght@400;500;600;700;800&family=Inter:wght@400;500;600;700&display=swap" rel="stylesheet">
+```
+
+Rules of thumb:
+- Headlines, section titles, big numbers, the logo → **Hanken Grotesk** (or blMelody).
+- Body copy, labels, buttons, nav items, form fields → **Inter**.
+- Never set body copy in the display font, and never set a huge headline in Inter — the mix is the point.
+
+---
+
+## 2. The `:root` token block
+
+```css
+:root {
+  /* ---- Fonts ---- */
+  --font-display: "Hanken Grotesk", "blMelody", ui-sans-serif, system-ui, sans-serif;
+  --font-body:    "Inter", ui-sans-serif, system-ui, -apple-system, sans-serif;
+  --font-mono:    ui-monospace, "SFMono-Regular", Menlo, Monaco, Consolas, monospace;
+
+  /* ---- Signature accent: HONEY GOLD (the one "joy" color) ---- */
+  --gold-500:  #ffc738;   /* primary accent */
+  --gold-400:  #ffd66f;   /* lighter */
+  --gold-300:  #f8d884;   /* soft */
+  --gold-600:  #f6c744;   /* focus-ring gold */
+  --gold-700:  #fcb900;   /* deep / hover */
+  --gold-tint: #fff5e4;   /* pale wash bg */
+  --gold-tint2:#ffe9cc;   /* warm cream */
+
+  /* ---- Ink & neutral scale (Tailwind neutral) ---- */
+  --ink:        #171717;  /* primary text, dark buttons, footer */
+  --ink-950:    #0a0a0a;  /* deepest */
+  --n-900:      #171717;
+  --n-800:      #262626;
+  --n-700:      #404040;  /* heading text on light */
+  --n-600:      #525252;
+  --n-500:      #737373;  /* secondary / body text */
+  --n-400:      #a3a3a3;  /* muted, placeholders, disabled */
+  --n-300:      #d4d4d4;  /* strong border */
+  --n-200:      #ededed;  /* hairline border (default) */
+  --n-150:      #f0f0f0;
+  --n-100:      #f5f5f5;  /* section tint background */
+  --n-50:       #fbfbfb;  /* page background */
+  --white:      #ffffff;  /* card surface */
+
+  /* ---- Support pastels (icon tiles, nodes, illustration accents) ---- */
+  --sky:        #3f9fe0;  --sky-tint:    #e2effd;   /* hero sky / info */
+  --violet:     #9f5bde;  --violet-tint: #e4ddfd;   /* AI / smart */
+  --green:      #22c55e;  --green-tint:  #dcfce7;   /* branch / success / nature */
+  --coral:      #f97316;  --coral-tint:  #ffe9cc;   /* energy / warm */
+  --red:        #ef4444;  --red-tint:    #fee2e2;   /* destructive */
+
+  /* ---- Semantic roles ---- */
+  --bg:            var(--n-50);
+  --bg-section:    var(--n-100);
+  --surface:       var(--white);
+  --border:        var(--n-200);
+  --border-strong: var(--n-300);
+  --text:          var(--n-700);
+  --text-muted:    var(--n-500);
+  --text-faint:    var(--n-400);
+  --accent:        var(--gold-500);
+
+  /* ---- Radius (curves are signature — nothing sharp) ---- */
+  --r-sm:  4px;
+  --r-md:  6px;     /* inputs, small chips */
+  --r-lg:  8px;     /* small buttons */
+  --r-xl:  12px;    /* buttons, icon tiles */
+  --r-2xl: 16px;    /* cards, nodes */
+  --r-3xl: 24px;    /* big feature cards, image frames, nav pill */
+  --r-full: 9999px; /* nav bar, pill buttons, badges, avatars */
+
+  /* ---- Shadows (diffuse, low-opacity = soft sunlight, never harsh) ---- */
+  --shadow-xs: 0 1px 2px 0 #0000000d;
+  --shadow-sm: 0 1px 3px 0 #0000001a, 0 1px 2px -1px #0000001a;
+  --shadow-md: 0 4px 6px -1px #0000001a, 0 2px 4px -2px #0000001a;
+  --shadow-lg: 0 10px 15px -3px #0000001a, 0 4px 6px -4px #0000001a;
+  --shadow-xl: 0 20px 25px -5px #0000001a, 0 8px 10px -6px #0000001a;
+  --shadow-2xl:0 25px 50px -12px #00000040;
+  --shadow-card:  0 1px 2px #0000000d, 0 8px 24px -12px #00000014; /* lifted-card ambient */
+  --shadow-nav:   0 4px 24px -8px #00000026, 0 1px 2px #0000000d;  /* floating glass nav */
+  --ring-gold:    0 0 0 3px var(--gold-600), 0 0 14px rgba(246,199,68,.4); /* focus */
+
+  /* ---- Type scale (rem) ---- */
+  --text-xs:  0.75rem;   --lh-xs:  1rem;
+  --text-sm:  0.875rem;  --lh-sm:  1.25rem;
+  --text-base:1rem;      --lh-base:1.5rem;
+  --text-lg:  1.125rem;  --lh-lg:  1.75rem;
+  --text-xl:  1.25rem;   --lh-xl:  1.75rem;
+  --text-2xl: 1.5rem;    --lh-2xl: 2rem;
+  --text-3xl: 1.875rem;  --lh-3xl: 2.25rem;
+  --text-4xl: 2.25rem;   --lh-4xl: 2.5rem;
+  --text-5xl: 3rem;      --lh-5xl: 1.05;
+  --text-6xl: 3.75rem;   --lh-6xl: 1.0;
+  --text-7xl: 4.5rem;    --lh-7xl: 1.0;
+  --display:  clamp(3rem, 7vw, 6rem);   /* hero headline, fluid */
+
+  /* ---- Font weights ---- */
+  --fw-normal: 400;  --fw-medium: 500;  --fw-semibold: 600;
+  --fw-bold: 700;    --fw-extrabold: 800;
+
+  /* ---- Tracking / leading ---- */
+  --track-tighter: -0.05em;
+  --track-tight:   -0.025em;   /* headings default */
+  --track-normal:  0em;
+  --lh-tight: 1.1;  --lh-snug: 1.25;  --lh-normal: 1.5;  --lh-relaxed: 1.6;
+
+  /* ---- Spacing (4px base) ---- */
+  --sp-1: 4px;  --sp-2: 8px;   --sp-3: 12px; --sp-4: 16px; --sp-5: 20px;
+  --sp-6: 24px; --sp-8: 32px;  --sp-10:40px; --sp-12:48px; --sp-16:64px;
+  --sp-20:80px; --sp-24:96px;  --sp-32:128px;
+  --section-y: clamp(4rem, 9vw, 7rem);   /* vertical rhythm between sections */
+  --container: 75rem;                     /* 1200px, max content width */
+  --gutter:    clamp(1rem, 4vw, 2rem);
+
+  /* ---- Glass / blur ---- */
+  --glass-bg:   rgba(251,251,251,0.8);
+  --glass-blur: 16px;
+
+  /* ---- Motion ---- */
+  --ease: cubic-bezier(0.22, 1, 0.36, 1);   /* gentle ease-out */
+  --dur-fast: 150ms;  --dur: 220ms;  --dur-slow: 320ms;
+}
+
+/* Baseline application */
+html { font-size: 16px; }
+body {
+  font-family: var(--font-body);
+  color: var(--text);
+  background: var(--bg);
+  -webkit-font-smoothing: antialiased;
+  text-rendering: optimizeLegibility;
+}
+h1,h2,h3,h4 {
+  font-family: var(--font-display);
+  font-weight: var(--fw-extrabold);
+  letter-spacing: var(--track-tight);
+  line-height: var(--lh-tight);
+  color: var(--ink);
+}
+```
+
+---
+
+## 3. Color rationale
+
+- **Honey-gold `#ffc738` is the whole personality.** It is the *only* saturated brand color. Use it
+  where you want a smile: the footer's primary CTA, star ratings, a "Publish" chip, the logo, a small
+  underline/highlight, a hover glow. If you find yourself using gold on more than ~5–10% of a screen,
+  pull back — its power is scarcity. Never pair it with a second competing bright brand color.
+- **Charcoal `#171717` is the workhorse.** Primary buttons on light backgrounds, primary text, the
+  footer surface. It reads premium and calm and lets the gold pop.
+- **Everything else is the neutral gray scale.** Backgrounds alternate `#fbfbfb` (page) ↔ `#f5f5f5`
+  (tinted section) ↔ `#ffffff` (cards). Borders are the near-invisible `#ededed` hairline. Text steps
+  down `#171717` → `#404040` → `#737373` → `#a3a3a3`.
+- **Support pastels are for tiny surfaces only** — icon tiles, workflow nodes, illustration accents,
+  chart dots. Each has a saturated glyph color + a pale tint background (violet on `#e4ddfd`, green on
+  `#dcfce7`, etc.). They add life without stealing the gold's job.
+- **The illustrated hero introduces sky-blue and green** as *painted* colors, not UI colors. That's
+  intentional — the warmth lives in the artwork, the UI stays disciplined.
+
+---
+
+## 4. Typography scale & usage
+
+| Element | Font | Size | Weight | Tracking | Line-height |
+|---|---|---|---|---|---|
+| Hero headline | display | `--display` (clamp 3→6rem) | 800 | -0.03em | 1.0 |
+| Section title | display | `--text-5xl`/`4xl` | 800 | -0.025em | 1.05 |
+| Card / feature title | display | `--text-xl`/`2xl` | 700 | -0.02em | 1.2 |
+| Subhead / lede | body | `--text-lg`/`xl` | 400 | 0 | 1.5 |
+| Body copy | body | `--text-base` | 400 | 0 | 1.6 |
+| Small / caption | body | `--text-sm` | 400/500 | 0 | 1.4 |
+| Button label | body | `--text-sm`/`base` | 600 | 0 | 1 |
+| Badge / eyebrow | body | `--text-sm` | 500 | 0 | 1 |
+| Big stat number | display | `--text-5xl`+ | 700 | -0.02em | 1 |
+
+**Two-tone hero trick:** split the headline across two lines and set the first line to a translucent
+white and the second to solid white for a soft-to-strong reveal:
+
+```css
+.hero-h1 { font: 800 var(--display)/1.0 var(--font-display); letter-spacing:-0.03em; color:#fff; }
+.hero-h1 .soft { color: rgba(255,255,255,0.55); }
+```
+```html
+<h1 class="hero-h1"><span class="soft">Forms that</span><br>do it all</h1>
+```
+
+On light backgrounds, headings are ink `#171717`; subheads are `#737373`.
+
+---
+
+## 5. Radius, shadow, spacing rationale
+
+- **Radius is a personality dial and it's turned way up.** Interactive elements are *fully* rounded
+  (nav, buttons, badges → `--r-full`). Containers are generously rounded (cards `16px`, big cards &
+  image frames `24px`). Only truly small utility elements go as low as `4–6px`. When in doubt, round
+  more. A single sharp corner breaks the whole cozy feeling.
+- **Shadows imitate soft ambient sunlight**, not hard drop-shadows. They're always large-radius and
+  low-opacity (`#0000001a` ≈ 10% black; the biggest is 25%). Use `--shadow-card` on resting cards and
+  `--shadow-nav` on the floating nav. On hover, step a card from `--shadow-card` to `--shadow-lg` and
+  nudge it up 2px.
+- **Spacing is generous and rhythmic.** Sections get `--section-y` (≈ 6rem) of vertical padding.
+  Content maxes at `--container` (1200px) and stays centered with `--gutter` side padding. Inside
+  cards, pad `24–40px`. Whitespace *is* the premium signal — don't crowd.
+
+---
+
+## 6. Glass / blur
+
+The floating nav and any sticky "feature tab" bar use frosted glass:
+
+```css
+.glass {
+  background: var(--glass-bg);              /* rgba(251,251,251,0.8) */
+  backdrop-filter: blur(var(--glass-blur)); /* 16px */
+  -webkit-backdrop-filter: blur(var(--glass-blur));
+  border: 1px solid var(--border);
+  box-shadow: var(--shadow-nav);
+}
+```
+Over the illustrated hero, use a whiter translucent fill (`rgba(255,255,255,0.7)`) so nav text stays legible.
+
+---
+
+## 7. Motion
+
+Gentle and springy, never bouncy-cartoonish. One easing curve (`--ease`, a soft ease-out) and short
+durations (150–320ms). The canonical interactions:
+
+- **Card hover:** `transform: translateY(-2px)` + shadow `--shadow-card` → `--shadow-lg`.
+- **Button hover:** slight brightness/darken + `--shadow-md`; the trailing `→` arrow nudges right ~3px.
+- **Focus:** `box-shadow: var(--ring-gold)` — the gold glow ring.
+- **Section reveal (optional):** fade-up 12px over 320ms as it enters the viewport.
+
+```css
+.card { transition: transform var(--dur) var(--ease), box-shadow var(--dur) var(--ease); }
+.card:hover { transform: translateY(-2px); box-shadow: var(--shadow-lg); }
+.btn .arrow { transition: transform var(--dur) var(--ease); }
+.btn:hover .arrow { transform: translateX(3px); }
+:where(a,button,input,textarea):focus-visible { outline: none; box-shadow: var(--ring-gold); }
+```

package/.agents/skills/vidfarm-media/SKILL.md

@@ -1,11 +1,11 @@
 ---
 name: vidfarm-media
-description: Media resolution for video workflows — narration TTS, word-level timings, BGM, SFX, and image/clip sourcing through vidfarm. Use when a video needs audio (voiceover/narration, music, sound effects), caption word timings, or media assets. Ships the shared audio engine scripts/audio.mjs (audio_request.json → audio_meta.json) used by faceless-explainer, product-launch-video, and general-video; documents vidfarm tts/stt BYOK primitives, the keyless local Kokoro + whisper.cpp engines, and My Files / clip-library / generation sourcing. No third-party media accounts — everything is user-owned or generated on the user's keys.
+description: Media resolution for video workflows — narration TTS, voice-matched speech regeneration ("same speaker, new words"), word-level timings, BGM, SFX, and image/clip sourcing through vidfarm. Use when a video needs audio (voiceover/narration, music, sound effects), rewording of existing narration in the original speaker's voice, caption word timings, or media assets. Ships the shared audio engine scripts/audio.mjs (audio_request.json → audio_meta.json) used by faceless-explainer, product-launch-video, and general-video; documents vidfarm tts/stt BYOK primitives, the keyless local Kokoro + whisper.cpp engines, and My Files / raws library / generation sourcing. No third-party media accounts — everything is user-owned or generated on the user's keys.
 ---
 
 # vidfarm-media
 
-One engine and one rule. The engine: `scripts/audio.mjs` turns a neutral `audio_request.json` into narration files, word timings, a music bed, and SFX — written into the project and described by one meta JSON. The rule: **no third-party media accounts, ever** — audio and images are the user's own files, found in the user's My Files / clip library, generated on the user's provider keys, or produced by keyless local models. If a source needs a sign-up, it is not a source.
+One engine and one rule. The engine: `scripts/audio.mjs` turns a neutral `audio_request.json` into narration files, word timings, a music bed, and SFX — written into the project and described by one meta JSON. The rule: **no third-party media accounts, ever** — audio and images are the user's own files, found in the user's My Files / raws library, generated on the user's provider keys, or produced by keyless local models. If a source needs a sign-up, it is not a source.
 
 ## Preflight (run once, before the brief)
 
@@ -63,6 +63,7 @@ Contract points:
 | Narration, promptable voice (BYOK) | `vidfarm tts "…" --style "calm, warm narrator"` | Local-first on your env key; `--voice alloy`/`Kore`…; `--cloud` = saved-key platform job → `POST /api/v1/primitives/audio/speech` |
 | Narration, zero keys | `npx hyperframes tts "…" -v af_heart --json` | Kokoro-82M, local, WAV + duration in JSON |
 | Transcript + SRT (BYOK) | `vidfarm stt <file\|url>` | Gemini key labels speakers; OpenAI whisper-1 gives real word timestamps |
+| Reword existing narration in the (approximate) original voice | `POST /api/v1/primitives/audio/regenerate-speech` (platform job on saved keys; no devcli command yet) | One job: listens to a video/audio source, profiles the speaker (needs a Gemini key), rewords the transcript per `rewrite_instruction` (or takes exact `text`), regenerates with the closest preset voice + matched style. Always an approximation — OpenAI/Gemini cannot clone voices. Details: `references/tts.md` |
 | Word timings, zero keys | `npx hyperframes transcribe <audio> --json` | whisper.cpp; writes word-level `transcript.json` |
 | Captions straight into a composition | `vidfarm captions generate <dir>` | whisper-1 real timings when an OpenAI key exists; estimates otherwise |
 
@@ -80,6 +81,6 @@ Voices, styles, formats, and the exact word-timestamp paths: `references/tts.md`
 Same ownership rule, different surfaces:
 
 - **My Files** — `vidfarm files --search "<meaning>"`; annotate assets with `vidfarm annotate-file <id> --notes "…"` so search finds them later; write with `vidfarm put-file`.
-- **Clip library** — `vidfarm clips search "<text>"` over clips hunted from the user's long-form footage (`vidfarm clips scan <video>`).
+- **Raws library** — `vidfarm raws search "<text>"` over raws hunted from the user's long-form footage (`vidfarm raws scan <video>`).
 - **Generate on the user's keys** — `vidfarm generate image|video --prompt "…"` (BYOK primitives; `--place <dir>` drops the result straight into a composition).
 - Never hotlink or scrape third-party stock; a capture workflow's own screenshots and the user's brand assets are always fair game.

package/.agents/skills/vidfarm-media/references/tts.md

@@ -21,7 +21,26 @@ vidfarm tts "Welcome back to the channel" --style "calm, warm bedtime narrator"
   - Gemini (`gemini-*-tts`, TitleCase, also the default family for OpenRouter TTS): `Kore, Puck, Charon, Aoede, Fenrir, Leda, Orus, Zephyr, Achernar, Achird, Algenib, Algieba, Alnilam, Autonoe, Callirrhoe, Despina, Enceladus, Erinome, Gacrux, Iapetus, Laomedeia, Pulcherrima, Rasalgethi, Sadachbia, Sadaltager, Schedar, Sulafat, Umbriel, Vindemiatrix, Zubenelgenubi`
 - **Formats**: `--format mp3|wav` (default mp3). `--json` prints `{ ok, provider, model, out, … }`.
 
-## Keyless local TTS — Kokoro-82M
+## Voice-matched regeneration — "same speaker, new words"
+
+```bash
+# Platform job on saved keys (no devcli command yet); poll the returned job_id.
+POST /api/v1/primitives/audio/regenerate-speech   # alias: /api/v1/primitives/regenerate-speech
+{ "tracer": "…", "payload": {
+    "source_url": "…",                 # video or audio; video audio is demuxed automatically
+    "rewrite_instruction": "mention the summer sale instead of the discount code",
+    "text": "…",                       # OR: the exact new script (one of the two is required)
+    "voice": "…", "instructions": "…", # optional preset override / extra style guidance
+    "provider": "…", "model": "…", "language": "…", "output_format": "mp3|wav"
+} }
+```
+
+One job: listens to the source, profiles the dominant speaker with an audio-native Gemini call (verbatim transcript + gender/age/accent/pace/pitch/energy profile + a dense style direction + the closest preset in both voice families), rewords the transcript per `rewrite_instruction` (keeping length and rhythm) or takes the exact `text`, then regenerates via TTS with the matched preset + profiled style instructions. Result: durable `audioUrl`, `script`, `original_transcript`, `voice_profile`, `voice_match`, plus a `regenerate-speech.json` artifact.
+
+- **Honesty rule (non-negotiable): this is an approximation, never a clone.** Neither OpenAI nor Gemini exposes voice cloning through their public APIs — both offer preset voices with style steering only (actual cloning is sales-allowlisted at both, e.g. OpenAI "Custom Voices", Google Chirp 3 Instant Custom Voice). `voice_match` says `"approximate"` or `"none"`; always present it that way to the user. True self-serve cloning would need an ElevenLabs/Cartesia-class provider or a local OSS model (F5-TTS, CosyVoice, XTTS-v2, Chatterbox) — none are wired into vidfarm today.
+- **Voice profiling needs a saved Gemini key** (it is the audio-native LLM). With only openai/openrouter keys the job degrades gracefully: STT transcript + reword still work, but the voice is a default or explicitly passed preset and `voice_match` is `"none"`.
+- Sources over ~40 minutes of speech must be trimmed first (same cap as `/audio/transcribe`).
+- To swap the result into a composition: mute the original span (`/videos/mute` or the layer's volume), then place `audioUrl` as a new audio layer.
 
 ```bash
 npx hyperframes tts "Welcome back" -v af_heart -o line.wav --json   # {"ok":true,"durationSeconds":…,"outputPath":…}

package/SKILL.director.md

@@ -208,11 +208,11 @@ Use it whenever you need to know what the video says or shows: writing/translati
 - **Editor chat (frontend AI)** exposes this as the optional `video_context` tool — the copilot calls it on demand.
 - **Desktop agents (Claude Code / Codex)**: fetch the `video-context.json` route directly (e.g. `vidfarm api GET /api/v1/compositions/<forkId>/video-context.json`) to ground edits in what the video says and shows.
 
-## Clip hunting (long-form → short-form clips)
+## Raws (long-form → short-form raws)
 
-Mine a **long-form** video (podcast, stream VOD, webinar, any YouTube/TikTok/IG/X URL, or an upload) into a library of tagged, searchable **short clips**. This is the `/clips` surface — browse it at `https://vidfarm.cc/clips` (the Library page's "Finished / Clips" toggle).
+Mine a **long-form** video (podcast, stream VOD, webinar, any YouTube/TikTok/IG/X URL, or an upload) into a library of tagged, searchable **raws**. This is the `/raws` surface — browse it at `https://vidfarm.cc/library/raws` (the Library page's "Approved / Raws" tabs).
 
-**Start a hunt** — `POST /clips/scan` (async: returns `202 { scan_id }` immediately):
+**Start a hunt** — `POST /raws/scan` (async: returns `202 { scan_id }` immediately):
 
 ```jsonc
 {
@@ -228,34 +228,34 @@ Mine a **long-form** video (podcast, stream VOD, webinar, any YouTube/TikTok/IG/
   // Hunt controls (all optional; also expressible inline in the prompt):
   "ranges": ["12:30-15:45", "20:00-22:10"],  // ONLY hunt these source windows — big cost saver on long videos
   "target_duration_sec": 30,                 // SOFT length band, not a hard cut: 10→5-20s, 30→20-40s, 60→40-80s, 120→80-160s
-  "aspect": "9:16",                          // crop every clip: 9:16 | 16:9 | 4:3 | 1:1 (synonyms: vertical/portrait, horizontal/landscape, square)
+  "aspect": "9:16",                          // crop every raw: 9:16 | 16:9 | 4:3 | 1:1 (synonyms: vertical/portrait, horizontal/landscape, square)
   "crop_focus": "center",                    // center | top | bottom | left | right (top biases toward faces)
   "avoid_text": true,                        // prefer scenes WITHOUT burned-in captions/on-screen text — a scene-SELECTION filter, NEVER GhostCut on the source
   "tracer": "my-campaign"                    // rolls up all the hunt's billing/observability events
 }
 ```
 
-- **Poll** `GET /clips/scan/:scanId` until the source `status` is `complete` (or `failed` — crashed pipelines are reconciled to `failed`, pollers never spin).
-- **Results**: `GET /clips/feed?source=<source_video_id>` (or the whole library), hybrid search via `POST /clips/search` `{ query: "someone looks confused" }`, per-clip download at `GET /clips/:clipId/download`. Clips carry taxonomy tags, a description, a transcript, an `aspect` field when cropped, the hunt's `tracer`, and (with a gemini/openai key) a semantic embedding.
+- **Poll** `GET /raws/scan/:scanId` until the source `status` is `complete` (or `failed` — crashed pipelines are reconciled to `failed`, pollers never spin).
+- **Results**: `GET /raws/feed?source=<source_video_id>` (or the whole library), hybrid search via `POST /raws/search` `{ query: "someone looks confused" }`, per-raw download at `GET /raws/:clipId/download`. Raws carry taxonomy tags, a description, a transcript, an `aspect` field when cropped, the hunt's `tracer`, and (with a gemini/openai key) a semantic embedding.
 - **Billing** — **AWS compute only** (`clip_scan_lambda` GB-seconds + Step Functions transitions, a fraction of a cent for typical hunts; the 202 response includes a `compute_estimate`). The AI tagging/refine runs on **your saved provider key (BYOK)** and is never wallet-billed. Submission is wallet-gated (402 when empty).
-- **The original stays temporary** — URL-ingested and uploaded sources live ONLY in your temp folder (`users/…/temporary/clip-sources/…`) with a hard **30-day TTL** (auto-deleted from S3 + the temp-file list). The hunted clips themselves are durable.
-- **Captions rule** — "no captions / no on-screen text" hunts are handled by scene SELECTION (the refine pass drops text-heavy scenes). **Never run GhostCut caption removal on a long-form source** (it is hard-capped at ~15 minutes); to actually erase burned-in text, apply `POST /api/v1/primitives/videos/remove-captions` to individual FINISHED clips afterwards.
+- **The original stays temporary** — URL-ingested and uploaded sources live ONLY in your temp folder (`users/…/temporary/clip-sources/…`) with a hard **30-day TTL** (auto-deleted from S3 + the temp-file list). The hunted raws themselves are durable.
+- **Captions rule** — "no captions / no on-screen text" hunts are handled by scene SELECTION (the refine pass drops text-heavy scenes). **Never run GhostCut caption removal on a long-form source** (it is hard-capped at ~15 minutes); to actually erase burned-in text, apply `POST /api/v1/primitives/videos/remove-captions` to individual FINISHED raws afterwards.
 
 **devcli (local-first — this is the default way to hunt on your own machine):**
 
 ```bash
 # Local machine power: local ffmpeg + your local claude/codex CLI subscription (no API key needed)
-vidfarm clips scan ./podcast.mp4 --range "12:30-15:45" --duration 30 --aspect vertical --no-text \
+vidfarm raws scan ./podcast.mp4 --range "12:30-15:45" --duration 30 --aspect vertical --no-text \
   --prompt "guest reaction moments"
 
 # Provider keys are the fallback (--provider gemini|openai|openrouter); the cloud pipeline is the
 # EXPLICIT backup, never the default:
-vidfarm clips scan --cloud ./podcast.mp4 --duration 30 --aspect 9:16 --tracer my-campaign
-vidfarm clips scan --cloud --url "https://youtube.com/watch?v=…" --range "0:00-10:00"
+vidfarm raws scan --cloud ./podcast.mp4 --duration 30 --aspect 9:16 --tracer my-campaign
+vidfarm raws scan --cloud --url "https://youtube.com/watch?v=…" --range "0:00-10:00"
 
 # Then search/reuse the library
-vidfarm clips search "confused reaction after reading a message"
-vidfarm clips export <clip-ids…> --to ./picks
+vidfarm raws search "confused reaction after reading a message"
+vidfarm raws export <raw-ids…> --to ./picks
 ```
 
 Local scans persist to a SQLite library under `~/.vidfarm` (free compute, subscription-powered evaluation); `--cloud` uploads to your temp folder (30-day TTL) or passes `--url`, runs the deployed pipeline, and bills AWS compute only.
@@ -546,10 +546,10 @@ Send a stable `tracer` on export so retries are traceable and filterable in job
 | `vidfarm get-file <id> [dest] [--print]` | (resolve id → view_url, then stream/print) | read one My Files asset |
 | `vidfarm put-file <file> [--folder <p>] [--as <name>] [--content/--stdin] [--notes "…"]` | `POST /api/v1/user/me/attachments/upload` | write into My Files (persistent) |
 | `vidfarm annotate-file <id\|name> --notes "…"` | `PATCH /api/v1/user/me/attachments/:id` | set metadata notes on one My Files entry (vector-embedded) |
-| `vidfarm clips scan <video> [--range MM:SS-MM:SS] [--duration <s>] [--aspect 9:16] [--no-text] [--prompt "…"]` | (LOCAL: local ffmpeg + local claude/codex agent → `~/.vidfarm` SQLite) | hunt long-form video into short clips on this machine |
-| `vidfarm clips scan --cloud <video\|--url <url>> [--tracer <id>]` | temp-file presign/PUT/finalize + `POST /clips/scan` + poll | BACKUP: run the hunt on the deployed pipeline (bills AWS compute only) |
-| `vidfarm clips search "…"` / `clips match "…"` / `clips list` / `clips sources` | (local library; NL→criteria via local agent or provider key) | search/reuse the clip library |
-| `vidfarm clips preset list\|run\|save` / `clips export <ids…> --to <dir>` | (local library) | saved queries; copy clip MP4s out |
+| `vidfarm raws scan <video> [--range MM:SS-MM:SS] [--duration <s>] [--aspect 9:16] [--no-text] [--prompt "…"]` | (LOCAL: local ffmpeg + local claude/codex agent → `~/.vidfarm` SQLite) | hunt long-form video into short-form raws on this machine |
+| `vidfarm raws scan --cloud <video\|--url <url>> [--tracer <id>]` | temp-file presign/PUT/finalize + `POST /raws/scan` + poll | BACKUP: run the hunt on the deployed pipeline (bills AWS compute only) |
+| `vidfarm raws search "…"` / `raws match "…"` / `raws list` / `raws sources` | (local library; NL→criteria via local agent or provider key) | search/reuse the raws library |
+| `vidfarm raws preset list\|run\|save` / `raws export <ids…> --to <dir>` | (local library) | saved queries; copy raw MP4s out |
 | `vidfarm lint <dir\|composition.html>` | (local static validation) | pre-publish composition check: timing, overlaps, preset names, media src |
 | `vidfarm stills <dir> [--at 0,2.5,…]` | (local in-process render of PNG frames) | visually verify an edit without a full render |
 | `vidfarm doctor` | (local environment triage) | check ffmpeg/node/keys/agent CLI/poisoned env before debugging anything else |
@@ -574,10 +574,10 @@ Each user has a persistent **My Files** filesystem — their own uploaded videos
 
 ### Metadata notes + vector search (find assets by meaning)
 
-Every My Files entry carries an optional **`notes`** field — free-form metadata describing what the file *is*, who/what it depicts, and when to use it. Notes are **vector-embedded** on save (same BYOK embedding seam as the clip library: gemini → openai key auto-pick; no key fail-softs to keyword-only), so the library is searchable by *meaning*, not just filename:
+Every My Files entry carries an optional **`notes`** field — free-form metadata describing what the file *is*, who/what it depicts, and when to use it. Notes are **vector-embedded** on save (same BYOK embedding seam as the raws library: gemini → openai key auto-pick; no key fail-softs to keyword-only), so the library is searchable by *meaning*, not just filename:
 
 - **Annotate** — `vidfarm annotate-file <id|name> --notes "Sprite card for Zara, our mascot: front/side/back views, teal jacket. Use as the reference image whenever generating Zara."` (`PATCH /me/attachments/:id`, body `{ notes }`; empty string clears). Or set notes at write time: `vidfarm put-file zara.png --folder acme/characters/zara --notes "…"`. Web copilot: `browse_files action=annotate` (or `notes` on `action=write`).
-- **Search** — `vidfarm files --search "the fox mascot reference sheet"` (`POST /me/attachments/search`, body `{ query, folder_path?, limit? }`) returns ranked hits with `similarity` + `keyword_match`, mirroring `/clips/search`: keyword survivors over name/folder/notes are semantically re-ranked, and when nothing keyword-matches it relaxes to a pure semantic pass. Web copilot: `browse_files action=search`.
+- **Search** — `vidfarm files --search "the fox mascot reference sheet"` (`POST /me/attachments/search`, body `{ query, folder_path?, limit? }`) returns ranked hits with `similarity` + `keyword_match`, mirroring `/raws/search`: keyword survivors over name/folder/notes are semantically re-ranked, and when nothing keyword-matches it relaxes to a pure semantic pass. Web copilot: `browse_files action=search`.
 - **Annotate what you'll want back.** Filenames alone don't survive months of accumulation — any asset a future session should find (character refs, logo variants, recurring backgrounds, key briefs) deserves notes at save time. `list`/`read` responses include each file's `notes`, so a scan of a folder doubles as a manifest of what's in it.
 
 ### Character consistency (recurring characters, mascots, spokespeople)
@@ -719,7 +719,7 @@ Remove burned-in captions/subtitles/on-screen text from any video URL (GhostCut-
 - Response: standard primitive job (`202 { job_id }`). The job probes the source, submits to GhostCut, polls to completion server-side (typically a few minutes), and mirrors the result. Poll `GET /api/v1/primitives/jobs/:jobId` until `status: "succeeded"`, then read `primary_file_url` / `video.file_url` (`captionsRemovedVideoUrl` in the output).
 - Billing: `~$0.10 per 30 seconds` of source video (per-chunk, 1-chunk minimum; `ghostcut_subtitle_removal` cost center), plus the small probe cost.
 - For the CURRENT fork's decompose flow, don't re-run this primitive — the caption-free mirror already exists via `GET /api/v1/compositions/:forkId/remove-video-captions`.
-- **Short clips only — hard cap ~15 minutes** (`GHOSTCUT_MAX_DURATION_SEC`, default 900s). Never point this at a long-form source: for "clips without captions" from a long video, run a clip hunt with `avoid_text: true` (scene selection — see "Clip hunting") and, if needed, apply this primitive to the individual FINISHED clips.
+- **Short clips only — hard cap ~15 minutes** (`GHOSTCUT_MAX_DURATION_SEC`, default 900s). Never point this at a long-form source: for "clips without captions" from a long video, run a raws hunt with `avoid_text: true` (scene selection — see "Raws") and, if needed, apply this primitive to the individual FINISHED raws.
 
 Example:
 

package/SKILL.platform.md

@@ -247,13 +247,13 @@ Configuration: `GHOSTCUT_KEY` and `GHOSTCUT_SECRET` env vars per stage. Pass-thr
 
 ## Clip hunting pipeline (long-form → short-form)
 
-`POST /clips/scan` starts a Step Functions STANDARD workflow (`…ClipScanWorkflow`): `probe_and_detect` → `Map(process_scene, maxConcurrency 5)` → `finalize`, all three states dispatching the same `infra/lambda/clip-scan.ts` on an `action` field. Business logic lives in the shared `src/services/clip-curation/` core (also consumed by devcli and the Hono API), with the hunt controls in `hunt.ts`:
+`POST /raws/scan` starts a Step Functions STANDARD workflow (`…ClipScanWorkflow`): `probe_and_detect` → `Map(process_scene, maxConcurrency 5)` → `finalize`, all three states dispatching the same `infra/lambda/clip-scan.ts` on an `action` field. Business logic lives in the shared `src/services/clip-curation/` core (also consumed by devcli and the Hono API), with the hunt controls in `hunt.ts`:
 
 - **`hunt_spec`** — windows (time ranges; ffmpeg input-seeks per window so only the requested footage is DECODED — the actual cost saving), a soft `duration_band` (`resolveDurationBand`: 10→5-20s, 30→20-40s via ±target/3), output `aspect` + `crop_focus` (smart-centre ffmpeg crop applied to clips, thumbnails, AND tagging keyframes so the model judges the framed output), `avoid_text` (rides the keep/drop/merge refine pass as a selection filter), and `source_url` (RapidAPI ingest → the user's temp folder). The spec travels as ONE opaque JsonPath object through the state machine, so new hunt fields are Lambda-code-only changes — no state-machine redeploy.
 - **Sources are temporary** — URL ingests and uploads land at `users/{id}/temporary/clip-sources/…` with a hard 30-day TTL enforced three ways: tag-scoped S3 lifecycle (`vidfarm-temp=1`, tagged server-side at temp-file finalize/upload), native DynamoDB TTL (`expires_at_epoch_seconds`, top-level on the item), and the list-route sweep. Hunted clips (`clips/{owner}/…`) are durable.
 - **Billing: AWS compute ONLY.** Every Lambda invocation post-hoc bills its GB-seconds to the `clip_scan_lambda` cost center (idempotent on `awsRequestId`); `finalize` adds `step_functions_standard` scaled by scene count (3 + N transitions); URL ingest adds the existing `rapidapi_video_download` pass-through. `jobId = scan_id`, and the caller's `tracer` rides every event (gsi2-tracer rollups). The BYOK tagging/embedding spend (gemini/openai/openrouter keys in the state input) is deliberately never wallet-billed. Submission is wallet-gated (`assertWalletCanQueueJobs` → 402); the 202 response carries a pre-scan `compute_estimate`.
-- **Failure reconciliation** — the workflow has no failure hook into records, so `GET /clips/scan/:scanId` lazily `DescribeExecution`s a running scan and flips the scan+source records to `failed` (or `complete`) so pollers converge.
-- **devcli is LOCAL-FIRST** — `vidfarm clips scan` runs local ffmpeg and, by default, the user's local claude/codex CLI subscription (`LocalAgentClipClient`, implementing the same `ClipHuntModelClient` interface as the API providers; refine's model call lives on the client as `decideScenes` to make them swappable). Provider keys are the fallback; `--cloud` is the explicit backup that presign-uploads to the temp folder and drives this pipeline.
+- **Failure reconciliation** — the workflow has no failure hook into records, so `GET /raws/scan/:scanId` lazily `DescribeExecution`s a running scan and flips the scan+source records to `failed` (or `complete`) so pollers converge.
+- **devcli is LOCAL-FIRST** — `vidfarm raws scan` runs local ffmpeg and, by default, the user's local claude/codex CLI subscription (`LocalAgentClipClient`, implementing the same `ClipHuntModelClient` interface as the API providers; refine's model call lives on the client as `decideScenes` to make them swappable). Provider keys are the fallback; `--cloud` is the explicit backup that presign-uploads to the temp folder and drives this pipeline.
 - **Bundling gotcha** — the clip-scan and primitive-media Lambdas bundle `ffmpeg-static`/`ffprobe-static` with `forceDockerBundling: true`: ffmpeg-static downloads the binary for the platform it is installed on, so a mac-local bundle ships a darwin ffmpeg the Lambda cannot exec (`exit 126`). They also need `VIDFARM_DATA_DIR=/tmp/vidfarm` because `config.ts` mkdirs at import.
 
 ## Editor Chat
@@ -266,7 +266,7 @@ Configuration: `GHOSTCUT_KEY` and `GHOSTCUT_SECRET` env vars per stage. Pass-thr
 
 The chat model uses the **caller's provider keys**. No Vidfarm-owned model calls happen in this path.
 
-Beyond the Editor Action API, the chat harness registers shared tools defined in **two synced copies** (`src/app.ts` for the in-process dev server and `infra/lambda/editor-chat.ts` for the deployed Lambda — keep them in lockstep): `http_request` (allowlisted REST/primitive calls), `frontend_action` (tracer/thread state), `video_context`, `load_skill`, and `browse_files`. `load_skill` is the copilot's knowledge-on-demand seam: it fetches vendored skill-pack content (SKILL.md or a reference file) from the host's public `/skill/:name` + `/skill-pack/:name/files/*` mirror routes (backed by `.agents/skills/`, shipped in the api Docker image), size-capped, with the pack catalog + one-liners defined once in `EDITOR_CHAT_SKILL_PACKS` (`src/editor-chat.ts`) and shared by both copies. The stream-loop guardrails (`redactUnverifiedJobIds`, `buildEditorChatGuardrailNotice`, async-job handoff text) also live in `src/editor-chat.ts` and are imported by both copies — never re-implement them locally. `editor_action`'s `replace_composition_html` is lint-gated in the tool `execute` via `src/services/composition-lint.ts` (a rejected result carries `rejected: true` + `lint_errors` and omits `action_type`, so the browser never applies it). `browse_files` reads **and writes** the caller's My Files library — `action=list`/`search`/`read`/`write`/`annotate`. `write` saves a text file (md/txt/csv/json/srt/vtt) via `POST /me/attachments/upload`, or **imports a durable media URL** into the library when `source_url` is passed (how a generated `character_sprite_card.png` gets persisted instead of stranding in a job result). `annotate` sets free-form metadata `notes` on any entry (`PATCH /me/attachments/:id`); notes are **vector-embedded server-side** (BYOK, same gemini→openai auto-pick seam as clip search; no key fail-softs to keyword-only) and `search` runs the hybrid keyword+semantic lookup over every file's name/folder/notes via `POST /me/attachments/search` — the My Files mirror of `/clips/search`. Write+annotate are what let the copilot persist Getting Started context (About.md, awareness-levels.md, persuasive-angles.md, ad-hooks.md) and character-consistency pairs (`about_character.md` + `character_sprite_card.png`) namescoped under a product/offer folder; the system prompt in `src/editor-chat.ts` drives when to save and annotate. The devcli mirrors are `vidfarm put-file [--notes]`, `annotate-file`, and `files --search`.
+Beyond the Editor Action API, the chat harness registers shared tools defined in **two synced copies** (`src/app.ts` for the in-process dev server and `infra/lambda/editor-chat.ts` for the deployed Lambda — keep them in lockstep): `http_request` (allowlisted REST/primitive calls), `frontend_action` (tracer/thread state), `video_context`, `load_skill`, and `browse_files`. `load_skill` is the copilot's knowledge-on-demand seam: it fetches vendored skill-pack content (SKILL.md or a reference file) from the host's public `/skill/:name` + `/skill-pack/:name/files/*` mirror routes (backed by `.agents/skills/`, shipped in the api Docker image), size-capped, with the pack catalog + one-liners defined once in `EDITOR_CHAT_SKILL_PACKS` (`src/editor-chat.ts`) and shared by both copies. The stream-loop guardrails (`redactUnverifiedJobIds`, `buildEditorChatGuardrailNotice`, async-job handoff text) also live in `src/editor-chat.ts` and are imported by both copies — never re-implement them locally. `editor_action`'s `replace_composition_html` is lint-gated in the tool `execute` via `src/services/composition-lint.ts` (a rejected result carries `rejected: true` + `lint_errors` and omits `action_type`, so the browser never applies it). `browse_files` reads **and writes** the caller's My Files library — `action=list`/`search`/`read`/`write`/`annotate`. `write` saves a text file (md/txt/csv/json/srt/vtt) via `POST /me/attachments/upload`, or **imports a durable media URL** into the library when `source_url` is passed (how a generated `character_sprite_card.png` gets persisted instead of stranding in a job result). `annotate` sets free-form metadata `notes` on any entry (`PATCH /me/attachments/:id`); notes are **vector-embedded server-side** (BYOK, same gemini→openai auto-pick seam as clip search; no key fail-softs to keyword-only) and `search` runs the hybrid keyword+semantic lookup over every file's name/folder/notes via `POST /me/attachments/search` — the My Files mirror of `/raws/search`. Write+annotate are what let the copilot persist Getting Started context (About.md, awareness-levels.md, persuasive-angles.md, ad-hooks.md) and character-consistency pairs (`about_character.md` + `character_sprite_card.png`) namescoped under a product/offer folder; the system prompt in `src/editor-chat.ts` drives when to save and annotate. The devcli mirrors are `vidfarm put-file [--notes]`, `annotate-file`, and `files --search`.
 
 ## Primitives
 

package/dist/src/account-pages-legacy.js

@@ -880,10 +880,10 @@ export function renderSettingsPage(input) {
                   </div>
                   <div class="profile-field">
                     <div class="profile-field-head">
-                      <label for="about">Profile notes</label>
+                      <label for="about">Product / offer description</label>
                       <button type="submit" data-profile-about-save disabled>Save</button>
                     </div>
-                    <textarea id="about" name="about" placeholder="What should your operators or collaborators know about this account?" data-profile-about data-initial-value="${escapeAttribute(input.about ?? "")}">${escapeHtml(input.about ?? "")}</textarea>
+                    <textarea id="about" name="about" placeholder="Describe your product or offer — what it is, who it's for, and the promise. Swipe mode uses this to auto-recut templates into ads for you." data-profile-about data-initial-value="${escapeAttribute(input.about ?? "")}">${escapeHtml(input.about ?? "")}</textarea>
                   </div>
                 </form>
                 <section class="files-card" data-files-card>