cueframe 0.4.9 → 0.6.0

package/dist/skills/cueframe-scene-shot/SKILL.md

@@ -5,6 +5,14 @@ description: Author a CueFrame 3D world-object shot as canonical SceneShotSpecV2
 
 # CueFrame scene shots
 
+## Scope and capability policy
+
+User intent and acceptance criteria override this recipe's aesthetic defaults. Silent, typography-only, uncaptioned and slow work are valid; no universal narration, footage, CTA, beat count or score target. Contracts, factual fidelity, media bindings and current source revisions remain mandatory.
+
+Read available tools and current project; preserve the chosen local/hosted lane. Supported local work needs no hosted registration. Do not silently install, authenticate, switch projects or upload local content. Before metered hosted work, check `get_account`, entitlements, balance and quotes. Desktop setup: https://docs.cueframe.ai.
+
+For scoped revisions, preserve unrelated timing, media, audio and shared brand-kit state. Edit affected content; inspect relevant frames, continuous motion and affected audio. No restarted intake, new approval pause, paid judge or final export by default. Judge only when useful; scores never override acceptance failures. Stop/report after two no-improvement passes. See [preview workflow](../cueframe-compose-loop/references/preview-workflow.md).
+
 Use `scene.add` and `scene.update` through `apply_composition`. Author the scene JSON; CueFrame owns the generated wrapper, preparation, resource admission, previews, and export.
 
 Before authoring, read `cueframe://scene-shot`. It serves the canonical generated `SceneShotSpecV2` schema, exact operation contracts, supported brand tokens, refusal rules, and a copyable nested slab-and-page recipe. Do not infer fields from an older example.

package/dist/skills/cueframe-storyboard/SKILL.md

@@ -1,28 +1,24 @@
 ---
 name: cueframe-storyboard
 description: >-
-  Use BEFORE composing when starting a NEW video from scratch and you need to plan its structure — turning a rough ask ("make a launch video", "30s promo", "an explainer for our API") into a concrete beat flow. Owns the intake + storyboard step: interview the user for the brief, resolve the format from the platform, and lay out the hook→body→cta beats that drive the compose workflow. Triggers on "plan a video", "storyboard", "structure this video", "outline the video", "where do I start", or any new-video ask that has no structure yet. Hand off to composing-video for per-beat craft.
+  Use BEFORE composing when starting a NEW video from scratch and you need to plan its structure — turning a rough ask ("make a launch video", "30s promo", "an explainer for our API") into a concrete beat flow. Owns the intake + storyboard step: interview the user for the brief, resolve the format from the platform, and plan beats from the leading material and requested format. Triggers on "plan a video", "storyboard", "structure this video", "outline the video", "where do I start", or any new-video ask that has no structure yet. Hand off to composing-video for per-beat craft.
 ---
 
 # CueFrame Storyboard: brief → flow
 
-This is a new-video planning workflow. For revisions to an approved plan, preserve its structure
-and use `cueframe-compose-loop`'s [preview workflow](../cueframe-compose-loop/references/preview-workflow.md)
-to verify the requested change; do not restart intake, Director authoring, or final export by default.
+## Scope and capability policy
 
-> **The bar:** the `video-craft-standards` skill (GET /v1/skills/video-craft-standards) defines DONE for every artifact class — per-class MUST checklists and kill criteria. Read it before composing and score against it before rendering. When this skill and that document disagree, the standards win.
+User intent and acceptance criteria override this recipe's aesthetic defaults. Silent, typography-only, uncaptioned and slow work are valid; no universal narration, footage, CTA, beat count or score target. Contracts, factual fidelity, media bindings and current source revisions remain mandatory.
 
+Read available tools and current project; preserve the chosen local/hosted lane. Supported local work needs no hosted registration. Do not silently install, authenticate, switch projects or upload local content. Before metered hosted work, check `get_account`, entitlements, balance and quotes. Desktop setup: https://docs.cueframe.ai.
 
-## The one idea
+For scoped revisions, preserve unrelated timing, media, audio and shared brand-kit state. Edit affected content; inspect relevant frames, continuous motion and affected audio. No restarted intake, new approval pause, paid judge or final export by default. Judge only when useful; scores never override acceptance failures. Stop/report after two no-improvement passes. See [preview workflow](../cueframe-compose-loop/references/preview-workflow.md).
 
-**You are the planner.** You have the user, the whole conversation, the brand, and the judgment — you are
-the smartest thing in this loop. CueFrame is the hands. This skill is the **intake + structure** step:
-turn intent into a concrete **beat flow** *before* you seed a composition, so the curated workflow (media →
-components → seed) executes a plan instead of a guess. Craft — grounded-vs-slop, the verify loop — belongs
-to the sibling **composing-video** skill; this skill gets you a flow, then hands off to it.
+This is a new-video planning workflow. For revisions to an approved plan, preserve its structure
+and use `cueframe-compose-loop`'s [preview workflow](../cueframe-compose-loop/references/preview-workflow.md)
+to verify the requested change; do not restart intake, Director authoring, or final export by default.
 
-Do not offload the *thinking* to CueFrame. There is no server that plans the video for you, and you would
-not want one — it would be a blind model with none of your context. Plan here, in the open, with the user.
+Plan here from the user's context. Direct authoring uses the available composition/component tools; hosted Director authoring is an optional execution lane when `create_brief` and `compose` are actually exposed. Neither lane substitutes for deciding the user's acceptance criteria.
 
 ## 1. Interview for the brief — ask only what you can't infer
 
@@ -32,7 +28,7 @@ infer**, and STATE what you assume for the rest. Never wall them with a form.
 - **Goal / intent** *(required)* — what is this video FOR? launch, promo, explainer, demo, teaser, recap.
 - **Platform** *(sets the format)* — reels / tiktok / shorts → **9:16, ~20s** · youtube → **16:9, ~45s** ·
   linkedin / x → **1:1, ~20s** · web → **16:9, ~30s**. (Or an explicit aspect ratio + duration.)
-- **Audience**, **tone** (punchy / premium-calm / playful / authoritative), **CTA**, **must-includes**
+- **Audience**, **tone** (punchy / premium-calm / playful / authoritative), optional **CTA**, **must-includes**
   (a number, a name, a screen), **references** (a style to echo), **brand kit**.
 
 If the ask is "make a launch video for our API," you already have goal + a hint of audience — ask "Reels,
@@ -41,48 +37,25 @@ you'd rather it feel calm/premium."* One or two questions, not seven.
 
 ## 2. Structure the flow — the storyboard
 
-Lay the duration into **beats** using the fixed editorial vocabulary
-**hook → context → body → proof → cta → outro** (use what the piece needs — most short-form is
-hook → body → cta). For each beat decide:
+Lay the requested duration into **beats** using the available editorial vocabulary
+**hook → context → body → proof → cta → outro** (use only what the piece needs; no fixed count or required CTA). For each beat decide:
 
 - a one-line **intent** (what this beat does for the viewer),
 - a **duration** (they sum to the target; the hook earns attention in ~3s),
-- a **media need** — real footage is the strongest grounding and CueFrame's home turf, so reach for it
-  first; otherwise `generate` a *purposeful* clip (a diagram of the real mechanism, the real UI) or `find`
-  stock. Animated text over a gradient is not grounding — it's the slop default,
-- an optional **graphic** (a lower-third, title, CTA card),
-- a **caption** and/or a **VO/script** line.
-
-**Ground it, don't invent it.** Pick every graphic/scene from `list_catalog` (filter by `useCase`/`tier`)
-— never hardcode hex or positions or name a component that doesn't exist. Theme from the brand kit. If
-you're planning over real footage, read `get_media_context` (detected faces + transcript) so beat timing,
-crops, and captions land on what's actually there.
-
-## 3. Show the flow, then persist it as a Brief
-
-Show the user the beat list **first** — a five-line outline. It is cheap to change here and expensive to
-change after a render, so this is where you converge on structure. On their go, **persist the plan with
-`create_brief`** — the beats/goal/format/gates you just elicited map 1:1 onto its fields, and the plan stops
-being chat-ephemeral (it survives the session, carries a cost quote, and is honored field-by-field):
-
-1. `import_media` / `generate_media` for each beat's media need,
-2. `create_brief` — goal, audience, platform/format, durationSec, tone, cta, locale, and the beats
-   (each with its editorial intent and, when you're cutting real footage, MOMENT PINNING
-   `source: {mediaId, startSec, endSec}` from the transcript — honored to-the-frame or refused).
-   Relay the response's **quote** (compose + estimated render) BEFORE composing.
-3. `compose { briefId }` — the Director authors FROM your brief; every field is honored or the
-   compose is refused loudly naming the field. Gates: put `holdAt: ["layout"]` in the brief's `gates` when
-   the user wants to approve the storyboard mid-flight; `autoApprove: true` for hands-off.
-4. `score_composition` / `consult` to fix the weakest beat,
-5. `create_render` for the MP4.
-
-**Two graphic media — pick per beat, and review accordingly:** a `card` (verbatim HTML in
-`seededGraphics`) is a STATIC graphic — cheap, approve it from a still; a **component**
-(`create_component`, `useCurrentFrame`) is MOTION — a still is one frame, so preview it before trusting it.
-Seeded graphics you author into the brief are carried VERBATIM as locked clips — the Director never
-re-authors them; `exclusions` bans graphic kinds you never want it to author.
-
-Then load **composing-video** and apply its craft to make each beat good.
+- a **media need**, if any: actual footage, product action, sourced data, diagrams, typography or abstract motion as requested,
+- optional graphics, captions and voice; preserve requested silence and deliberate holds.
+
+Choose the leading material first: narration, recorded speech, product action, visual/music motion or observational sequence. Read `get_media_context` when source facts or transcript timings affect the plan. Discover existing primitives with `list_catalog` when available; custom authored graphics are also valid. Never invent a catalog entry, media ID, transcript or factual product capture.
+
+## 3. Execute the plan in the available lane
+
+Give a concise outline when useful. Continue within existing authorization; request approval only when the user requested a review gate or a decision is genuinely missing.
+
+**Direct authoring:** use the exposed composition operations and existing project assets, then the scoped preview workflow. A local project does not require hosted registration, `create_brief`, `compose` or a paid judge. Read the actual local contracts; desktop setup is documented at https://docs.cueframe.ai.
+
+**Hosted Director, when available and selected:** check `get_account` and current quotes before metered imports, generation or composition. Persist the accepted plan with `create_brief`, including only supported fields. Pin recorded moments with `source: {mediaId, startSec, endSec}` where supported. Relay its compose/render quote before `compose {briefId}`. Use `holdAt` only for a requested gate and `autoApprove` only when authorized and supported. Do not silently upload local content or move to a different project to obtain this lane.
+
+Review with stills plus motion/audio evidence appropriate to the affected content. Cards can animate; a still alone cannot verify their motion. Use `score_composition` for broader review only when useful; export with `create_render` when final delivery is requested. Then load **composing-video** for applicable craft guidance.
 
 ## Related skills & positioning
 
@@ -100,5 +73,4 @@ This skill owns **structure/intake**; its siblings own execution and craft — d
 
 You own the **vision** (the one idea and the flow for *this* video) and **data correctness** (a wrong
 number you supply is rendered faithfully — the mistake is yours). CueFrame owns being faithful, legible,
-and giving you real footage + real components to plan against. Reason from this; skip the whole flow only
-for a re-render of an approved composition or a single trivial one-off.
+and giving you real footage + real components to plan against. Reason from this; use this planning flow only when new work needs structure.

package/dist/skills/every-format-from-one-edit/SKILL.md

@@ -5,6 +5,14 @@ description: Derives content-aware 9:16, 1:1, and 4:5 siblings from one finished
 
 # Every format from one edit
 
+## Scope and capability policy
+
+User intent and acceptance criteria override this recipe's aesthetic defaults. Silent, typography-only, uncaptioned and slow work are valid; no universal narration, footage, CTA, beat count or score target. Contracts, factual fidelity, media bindings and current source revisions remain mandatory.
+
+Read available tools and current project; preserve the chosen local/hosted lane. Supported local work needs no hosted registration. Do not silently install, authenticate, switch projects or upload local content. Before metered hosted work, check `get_account`, entitlements, balance and quotes. Desktop setup: https://docs.cueframe.ai.
+
+For scoped revisions, preserve unrelated timing, media, audio and shared brand-kit state. Edit affected content; inspect relevant frames, continuous motion and affected audio. No restarted intake, new approval pause, paid judge or final export by default. Judge only when useful; scores never override acceptance failures. Stop/report after two no-improvement passes. See [preview workflow](../cueframe-compose-loop/references/preview-workflow.md).
+
 You finish ONE edit; you get back its siblings for every platform — 9:16 for
 Reels/TikTok/Shorts, 1:1 and 4:5 for feeds — derived content-aware from the master,
 subject-tracked rather than letterboxed, each judged and rendered on its own. The edit decisions
@@ -54,9 +62,8 @@ A correction to one sibling does not require rendering the master or the other u
    note repeats it. If a sibling needs a different bed, `search_resources` honoring the brand
    kit's `musicMood` and swap it on that sibling only.
 6. **Judge each sibling as its own artifact.** `score_composition` per sibling with the
-   master's vision as `editorialIntent`. A 9:16 sibling is a social reel and answers to that
-   class's checklist — hook inside 2 seconds still applies in the new crop. Fix worst-first to
-   ≥ 7.5.
+   master's vision as `editorialIntent`. Changing aspect ratio does not change the approved editorial intent, pacing or acceptance criteria. Fix worst-first to
+   meet the applicable acceptance criteria.
 7. **Render each approved sibling.** `create_render` → `wait_job (kind:"render")` per
    composition. One final render per approval; iterate with previews.
 
@@ -64,15 +71,14 @@ A correction to one sibling does not require rendering the master or the other u
 
 Quoted from `video-craft-standards` (cross-cutting rules — every artifact):
 
-> **MUST** Safe-area respected: no critical copy in the outer ~8% of frame.
+> **DEFAULT** Safe-area respected: no critical copy in the outer ~8% of frame.
 
-> **MUST** One final render per approval; iterate with previews, not renders.
+> **DEFAULT** One final render per approval; iterate with previews, not renders.
 
-> **MUST** Delivery never ends with "done": the last message carries the output link and where
+> **DEFAULT** Delivery never ends with "done": the last message carries the output link and where
 > to find it, plus the intentional-silence note if any.
 
-And the class rule that governs each sibling: a derived 9:16 answers to §1 (Social reel) —
-*"**MUST (K)** The hook lands inside 2 seconds"* — a derived 16:9 to its own class. Derivation
+And the class rule that governs each sibling: apply the original brief at the new dimensions; aspect ratio alone does not impose a social-reel hook or pacing. Derivation
 changes the frame, never the bar.
 
 ## Delivering

package/dist/skills/extracting-brand-kits/SKILL.md

@@ -6,6 +6,14 @@ description: >-
 
 # Extracting brand kits: reference pixels → a kit the engine honors
 
+## Scope and capability policy
+
+User intent and acceptance criteria override this recipe's aesthetic defaults. Silent, typography-only, uncaptioned and slow work are valid; no universal narration, footage, CTA, beat count or score target. Contracts, factual fidelity, media bindings and current source revisions remain mandatory.
+
+Read available tools and current project; preserve the chosen local/hosted lane. Supported local work needs no hosted registration. Do not silently install, authenticate, switch projects or upload local content. Before metered hosted work, check `get_account`, entitlements, balance and quotes. Desktop setup: https://docs.cueframe.ai.
+
+For scoped revisions, preserve unrelated timing, media, audio and shared brand-kit state. Edit affected content; inspect relevant frames, continuous motion and affected audio. No restarted intake, new approval pause, paid judge or final export by default. Judge only when useful; scores never override acceptance failures. Stop/report after two no-improvement passes. See [preview workflow](../cueframe-compose-loop/references/preview-workflow.md).
+
 ## The one idea
 
 **No summarization anywhere in the path.** A reference described in prose converges on house style

package/dist/skills/launch-video/SKILL.md

@@ -5,6 +5,14 @@ description: Turns screen recordings and product footage into a 30–90 second 1
 
 # Launch video
 
+## Scope and capability policy
+
+User intent and acceptance criteria override this recipe's aesthetic defaults. Silent, typography-only, uncaptioned and slow work are valid; no universal narration, footage, CTA, beat count or score target. Contracts, factual fidelity, media bindings and current source revisions remain mandatory.
+
+Read available tools and current project; preserve the chosen local/hosted lane. Supported local work needs no hosted registration. Do not silently install, authenticate, switch projects or upload local content. Before metered hosted work, check `get_account`, entitlements, balance and quotes. Desktop setup: https://docs.cueframe.ai.
+
+For scoped revisions, preserve unrelated timing, media, audio and shared brand-kit state. Edit affected content; inspect relevant frames, continuous motion and affected audio. No restarted intake, new approval pause, paid judge or final export by default. Judge only when useful; scores never override acceptance failures. Stop/report after two no-improvement passes. See [preview workflow](../cueframe-compose-loop/references/preview-workflow.md).
+
 You bring real screen recordings or product footage plus the one outcome the feature delivers;
 you get back a 30–90 second 16:9 announcement that opens on the payoff, shows the actual product
 doing the real thing, builds under a bed or narration, and lands on a single CTA.
@@ -50,34 +58,32 @@ affected window and regressions without automatically rerunning the full-film ju
    HTML in the brand's type and palette — persisted first, then shelled with
    `applyMotionPreset` in a FOLLOWING `apply_composition` call. One CTA on the end card, held
    long enough to read, plus the date if there is one.
-6. **Audio that builds — required.** `search_resources` for a bed honoring the brand kit's
+6. **Audio when requested or appropriate.** Preserve explicit silence; otherwise: `search_resources` for a bed honoring the brand kit's
    `musicMood`, energy arcing toward the reveal; place it `audioRole:"music"`,
    `materializeGrid { grid:"beat" }`, and land beat boundaries and the reveal on the grid. If
    narrated: the VO is the rhythm authority instead — cut to the voice and duck the bed under
-   it. Silence is almost never right for a launch; if chosen anyway, record the decision and
-   reason in the delivery note.
+   it. Explicit silence is a supported creative choice.
 7. **Caption narration.** For transcribed voice, save the edits first, then call
    `captions.fromComposition` with the narration track ID in a separate `apply_composition`
    call. Speech clips must have saved duration matching playable source duration divided by
    playbackRate. Re-run after later edits. Use authored word timings for generated VO without a
-   transcript, and style legibly via `setCaptionStyle`. Captions are mandatory when narrated.
+   transcript, and style legibly via `setCaptionStyle`. Caption narration when requested or appropriate; preserve an explicit uncaptioned format.
 8. **Preview, judge, one render.** `preview_frame` at t=0, hook-end, the reveal, and the end
    card; describe each still — is that a REAL capture on screen? Then `score_composition` with
-   the payoff line as `editorialIntent`; fix worst-first to ≥ 7.5; `create_render` →
+   the payoff line as `editorialIntent`; fix relevant acceptance failures; `create_render` →
    `wait_job (kind:"render")`.
 
 ## What good looks like
 
-Quoted from `video-craft-standards` §2 (Launch film / feature announcement) — the full checklist
-wins:
+Quoted from `video-craft-standards` §2 (Launch film / feature announcement) — these are format defaults:
 
-> **MUST (K)** Payoff-first hook: the OUTCOME, not the feature name ("Close the books two days
+> **DEFAULT** Payoff-first hook: the OUTCOME, not the feature name ("Close the books two days
 > faster" beats "Introducing the reconciliation module"). No throat-clearing.
 
-> **MUST** Narration or a bed that builds toward the reveal; pacing tightens as the payoff
-> approaches. **MUST** Real product surface: actual UI/screens/output — never mocked.
+> **DEFAULT** Narration or a bed that builds toward the reveal; pacing tightens as the payoff
+> approaches. **DEFAULT** Real product surface: actual UI/screens/output — never mocked.
 
-> **MUST** End card with a single CTA. **MUST** Captions present when narrated.
+> **DEFAULT** End card with a single CTA. **DEFAULT** Captions present when narrated.
 
 And cross-cutting: *"Footage carries the video: real footage / real UI / real data ≥60% of
 runtime for footage-first classes."*

package/dist/skills/make-a-social-reel/SKILL.md

@@ -5,6 +5,14 @@ description: Turns footage into a finished 9:16 social reel — hook inside 2 se
 
 # Make a social reel
 
+## Scope and capability policy
+
+User intent and acceptance criteria override this recipe's aesthetic defaults. Silent, typography-only, uncaptioned and slow work are valid; no universal narration, footage, CTA, beat count or score target. Contracts, factual fidelity, media bindings and current source revisions remain mandatory.
+
+Read available tools and current project; preserve the chosen local/hosted lane. Supported local work needs no hosted registration. Do not silently install, authenticate, switch projects or upload local content. Before metered hosted work, check `get_account`, entitlements, balance and quotes. Desktop setup: https://docs.cueframe.ai.
+
+For scoped revisions, preserve unrelated timing, media, audio and shared brand-kit state. Edit affected content; inspect relevant frames, continuous motion and affected audio. No restarted intake, new approval pause, paid judge or final export by default. Judge only when useful; scores never override acceptance failures. Stop/report after two no-improvement passes. See [preview workflow](../cueframe-compose-loop/references/preview-workflow.md).
+
 You hand over footage (a file URL, a talk, a product moment); you get back a 9:16 reel of 8–30
 seconds that opens on its strongest image, cuts on the music, carries brand-grade type, and ends
 on a deliberate beat — with a download link, not a "done".
@@ -32,20 +40,17 @@ Use `cueframe-compose-loop`'s [preview workflow](../cueframe-compose-loop/refere
 for layout and motion evidence. A follow-up tweak preserves the approved brief; inspect the
 affected window and regressions without automatically rerunning the full-film judge or export.
 
-
 0. **Find the claim (before anything else).** Interrogate the brand/material
    for its tension — what it believes that its category doesn't — and write
    the claim in one sentence. Derive the shot list, the bed's mood/tempo, the
-   pacing, and every card's copy FROM that sentence. If you cannot state the
-   claim, you are not ready to compose (video-craft-standards: the
-   controlling idea is kill-level).
+   pacing, and every card's copy FROM that sentence. Use the requested visual experience as intent when the piece makes no factual claim.
 
 1. **Import and read the footage.** `import_media` (public https URL), poll `list_media` until
    ready, then `get_media_context` — faces, transcript, word timings. The context tells you
    where the hook lives; don't guess.
 2. **Pick the hook before you touch the timeline.** The strongest image, motion, or claim in the
    footage — the outcome, not the feature name, is the hook. If the best moment is at 0:47, the
-   reel opens at 0:47. No logo-first cold opens, ever.
+   reel opens at 0:47. A logo-first opening remains valid when explicitly requested.
 3. **Seed the timeline.** `new_composition` at 9:16, then `apply_composition`: clips trimmed to
    the beats you chose, a new visual beat at least every ~4 seconds. Cut TO moments; never let a
    clip run out.
@@ -56,7 +61,7 @@ affected window and regressions without automatically rerunning the full-film ju
    palette-as-fields, considered alignment — persisted first, then shelled with
    `applyMotionPreset` in a FOLLOWING `apply_composition` call. Catalog text primitives are
    utility only.
-6. **Decide the audio — required, never skipped.** Search a bed with `search_resources` honoring
+6. **Honor requested silence or existing audio.** When a bed is appropriate, search a bed with `search_resources` honoring
    the brand kit's `musicMood`, place it as an `audioRole:"music"` clip, then `materializeGrid`
    `{ grid:"beat" }` and land your cut points and transition midpoints on the markers. If the
    piece is genuinely better silent, that is a decision — record it and its reason in the
@@ -71,28 +76,27 @@ affected window and regressions without automatically rerunning the full-film ju
    don't karaoke a beat with no speech.
 8. **Look, then get judged.** `preview_frame` at t=0, hook-end, and every beat boundary;
    describe each still in words before scoring it. Then `score_composition` with your one-line
-   vision as `editorialIntent` — fix the worst criterion first. Ship at composite ≥ 7.5, budget
-   3–5 passes.
+   vision as `editorialIntent` — fix the worst criterion first. Meet the applicable acceptance criteria; budget
+   up to 3–5 passes only for broader review.
 9. **One final render.** `create_render` → `wait_job (kind:"render")`. Iterate with previews,
    not renders.
 
 ## What good looks like
 
-Quoted from `video-craft-standards` §1 (Social reel) — the full checklist wins over this skill
-wherever they disagree:
+Quoted from `video-craft-standards` §1 (Social reel) — these are defaults for this format, subject to the scope policy above:
 
-> **MUST (K)** The hook lands inside 2 seconds: the strongest image, motion, or claim opens the
+> **DEFAULT** The hook lands inside 2 seconds: the strongest image, motion, or claim opens the
 > piece. No logo-first cold opens, no fade-in-from-black preambles.
 
-> **MUST** Typography is poster-grade: composed plates/fields in the brand palette, considered
-> alignment and scale. **K:** centered white text floating on footage.
+> **DEFAULT** Typography is poster-grade: composed plates/fields in the brand palette, considered
+> alignment and scale. **Consider:** centered white text floating on footage.
 
-> **MUST** Pacing is cut-driven: a new visual beat at least every ~4s […] **MUST** Ends on a
+> **DEFAULT** Pacing is cut-driven: a new visual beat at least every ~4s […] **DEFAULT** Ends on a
 > deliberate beat: tagline, logo, or CTA lockup — not a clip running out.
 
 And the cross-cutting audio rule:
 
-> **MUST** Audio is decided, never defaulted […] **K:** a render whose silence nobody chose.
+> **DEFAULT** Audio is decided, never defaulted […] **Consider:** a render whose silence nobody chose.
 
 ## Delivering
 

package/dist/skills/rebrand-a-video/SKILL.md

@@ -5,6 +5,14 @@ description: Swaps the brand kit under an existing video and re-renders — toke
 
 # Rebrand a video
 
+## Scope and capability policy
+
+User intent and acceptance criteria override this recipe's aesthetic defaults. Silent, typography-only, uncaptioned and slow work are valid; no universal narration, footage, CTA, beat count or score target. Contracts, factual fidelity, media bindings and current source revisions remain mandatory.
+
+Read available tools and current project; preserve the chosen local/hosted lane. Supported local work needs no hosted registration. Do not silently install, authenticate, switch projects or upload local content. Before metered hosted work, check `get_account`, entitlements, balance and quotes. Desktop setup: https://docs.cueframe.ai.
+
+For scoped revisions, preserve unrelated timing, media, audio and shared brand-kit state. Edit affected content; inspect relevant frames, continuous motion and affected audio. No restarted intake, new approval pause, paid judge or final export by default. Judge only when useful; scores never override acceptance failures. Stop/report after two no-improvement passes. See [preview workflow](../cueframe-compose-loop/references/preview-workflow.md).
+
 You bring a finished video and a new brand (a kit, a website, or new colors/fonts/logo); you get
 the same video back wearing the new identity — everything bound to brand tokens re-themes at
 render, and the few graphics that hardcoded the old brand get found and fixed. Change one line,
@@ -23,9 +31,7 @@ Then back to the brand — most of this job is a kit definition and an audit.
   in.
 - **The new brand** (required): an existing kit id, a website to `extract_brand_kit` from
   (colors/fonts only — ask for logo, tagline, voice), or explicit values for `create_brand_kit`.
-- **Same identity or a new one?** Restyling THIS brand → upsert the same kit id and every
-  composition pointing at it re-themes. White-labeling for someone else → a NEW kit, so the
-  original stays intact.
+- **Scope:** a title/color/logo correction edits only affected clip values or bindings. Do not upsert a shared kit for one local correction. A project-wide brand change must be explicit: a same-kit upsert affects every referencing composition. For a new identity, use a new kit when supported. Styling preserves layout; a full redesign requires explicit scope.
 - **Tone shift**: does the new brand change the music mood too? Check the kit's `musicMood`
   intent.
 
@@ -35,7 +41,7 @@ Use `cueframe-compose-loop`'s [preview workflow](../cueframe-compose-loop/refere
 for affected graphics and saved-composition checks. Inspect motion if the kit changes timing;
 keep the final re-render separate from previews used to resolve individual styling corrections.
 
-1. **Pin the new brand as a kit.** `extract_brand_kit` or `create_brand_kit`; show the kit and
+1. **For an explicit project-wide brand change, pin the new brand as a kit.** `extract_brand_kit` or `create_brand_kit`; show the kit and
    get sign-off — it is the contract. Then bind it: upsert in place (same kit id) to restyle,
    or point the project at the new kit for a white-label. The kit lives on the PROJECT, not on
    a composition op.
@@ -56,31 +62,27 @@ keep the final re-render separate from previews used to resolve individual styli
 5. **Fix the holdouts surgically.** `apply_composition` edits per offending clip: rebind card
    fields to `$brand:` tokens (so the NEXT rebrand really is one line), swap the old-wordmark
    media, re-grade footage toward the new palette. A replaced card gets re-shelled with
-   `applyMotionPreset` in a FOLLOWING call. The §3 test governs every card you touch: if the
-   old brand's hex would still look correct in it, the layout was never bespoke — rebuild it,
-   don't tint it.
-6. **Re-decide the audio — required.** A brand swap is a mood swap: check the bed against the
+   `applyMotionPreset` in a FOLLOWING call. If the requested scope is styling, retain its layout; rebuild only for an explicitly requested redesign.
+6. **Review audio only when in scope.** A styling correction preserves existing audio and timing; for a broader brand change: check the bed against the
    new kit's `musicMood`. Wrong mood → `search_resources` a replacement (license recorded),
    same role and ducking, `materializeGrid` re-run if cut timing shifts. Still right → say so
    in the delivery note. If the piece was intentionally silent, confirm that decision still
    fits the new brand and restate it.
-7. **Judge against the NEW brand, render once.** `score_composition` with the new brand facts
-   as `brandContext` — the brand axis is exactly the check this job needs. Fix worst-first to
-   ≥ 7.5, then `create_render` → `wait_job (kind:"render")`.
+7. **Preview the affected styling.** Check the changed color/logo/text and relevant regressions against the requested values. For broader brand review, use `score_composition` only when useful and within budget. Export with `create_render` only for requested final delivery.
 
 ## What good looks like
 
 Quoted from `video-craft-standards` §3 (Brand-identity reel) — the bespoke test applies to every
 card in any class:
 
-> **MUST** Every graphic is bespoke to the brand: its type, its palette as fields, its layout
-> system. **K:** any layout that would look correct with another brand's hex swapped in.
+> **DEFAULT** Every graphic is bespoke to the brand: its type, its palette as fields, its layout
+> system. **Consider:** any layout that would look correct with another brand's hex swapped in.
 
-> **MUST** Footage color and brand palette agree — grade toward the palette or choose footage
+> **DEFAULT** Footage color and brand palette agree — grade toward the palette or choose footage
 > that lives in it.
 
-And cross-cutting: *"**MUST** Brand/text graphics are AUTHORED — `kind:"card"` HTML (your
-typography, layout, palette-as-fields) […] **K:** a brand graphic rendered from a catalog text
+And cross-cutting: *"**DEFAULT** Brand/text graphics are AUTHORED — `kind:"card"` HTML (your
+typography, layout, palette-as-fields) […] **Consider:** a brand graphic rendered from a catalog text
 primitive."*
 
 ## Delivering

package/dist/skills/video-craft-standards/SKILL.md

@@ -1,30 +1,28 @@
 ---
 name: video-craft-standards
-description: The definition of DONE for every video made with CueFrame — per-artifact checklists (social reel, launch film, brand reel, talking-head clip) with kill criteria. Read this BEFORE composing and score your work against it BEFORE rendering. Other skills quote this document; when a skill and this document disagree, this document wins. Triggers on "is this good enough", "quality bar", "what should a finished reel have", "review my video", or any request to make a video when no other skill has stated the bar.
+description: Craft defaults and applicable review checklists for CueFrame videos (social reel, launch film, brand reel, talking-head clip). User intent and requested scope govern their application; factual fidelity and tool contracts remain mandatory. Triggers on "is this good enough", "quality bar", "what should a finished reel have", "review my video", or any request to make a video when no other skill has stated the bar.
 ---
 
 # Video-Craft Standards — what "finished" means
 
-This is the single source of truth for output quality. A video that misses a
-MUST for its artifact class is **not done** — fix it or explicitly record why
-the rule doesn't apply. Kill criteria (**K**) mean: do not render; fix first.
+## Scope and capability policy
 
-## Why this exists
+User intent and acceptance criteria override this recipe's aesthetic defaults. Silent, typography-only, uncaptioned and slow work are valid; no universal narration, footage, CTA, beat count or score target. Contracts, factual fidelity, media bindings and current source revisions remain mandatory.
 
-Every quality dimension nobody measures decays to the laziest default:
-template titles, silent reels, centered white text on footage. Each class
-below is the checklist a good human editor carries implicitly. Score against
-it with stills (`preview_frame`) and the judge (`score_composition`) before
-your one final render.
+Read available tools and current project; preserve the chosen local/hosted lane. Supported local work needs no hosted registration. Do not silently install, authenticate, switch projects or upload local content. Before metered hosted work, check `get_account`, entitlements, balance and quotes. Desktop setup: https://docs.cueframe.ai.
+
+For scoped revisions, preserve unrelated timing, media, audio and shared brand-kit state. Edit affected content; inspect relevant frames, continuous motion and affected audio. No restarted intake, new approval pause, paid judge or final export by default. Judge only when useful; scores never override acceptance failures. Stop/report after two no-improvement passes. See [preview workflow](../cueframe-compose-loop/references/preview-workflow.md).
+
+These are aesthetic defaults for the named formats, not universal delivery gates. Apply only the checklist items relevant to the requested artifact; a silent typography study needs neither footage nor narration, and a title correction needs only affected evidence. User acceptance criteria govern delivery. The labels below describe recommendations; do not reject explicit creative choices using a default or a judge score.
 
 ## The controlling idea — the rule above every rule
 
-- **MUST (K)** Before composing, write the video's CLAIM in one sentence —
+- **DEFAULT** For new work, consider stating the video's CLAIM in one sentence —
   the thing a viewer should be able to repeat afterward ("real bread takes
   48 hours and you can taste every one of them"). Not a vibe, not a tagline:
   a claim with tension (what does this brand/story believe that its category
   doesn't?).
-- **MUST (K)** Every channel is EVIDENCE for the claim, in harmony:
+- **DEFAULT** Each included channel serves the requested intent, in harmony:
   - **Footage** — each clip earns its place as proof of the claim, chosen
     from the claim's shot list, not from search-term aesthetics.
   - **Sound** — the bed's mood and TEMPO embody the claim (a "slow" claim
@@ -34,7 +32,7 @@ your one final render.
     platform convention when the claim demands it.
   - **Type/cards** — copy advances the argument; the tagline lands as the
     CONCLUSION the beats have earned, never as a caption.
-- **Kill tests:** (1) beats reorderable without changing what the video
+- **Review prompts:** (1) beats reorderable without changing what the video
   says; (2) any channel (bed, shot, card) that would fit a different claim
   equally well; (3) a viewer who watched it cannot state the claim.
 
@@ -46,83 +44,78 @@ For scoped corrections and preview selection, use `cueframe-compose-loop`'s
 motion and listen to affected audio, not only stills or judge scores. Keep the user's explicit
 scope and acceptance criteria; approved simulated UI is not evidence of a real product capture.
 
-- **MUST** Brand/text graphics are AUTHORED — `kind:"card"` HTML (your
+- **DEFAULT** Brand/text graphics are AUTHORED — `kind:"card"` HTML (your
   typography, layout, palette-as-fields) shelled with `applyMotionPreset`,
   or a custom component. Catalog text primitives are for utility only.
-  **K:** a brand graphic rendered from a catalog text primitive.
-- **MUST** Audio is decided, never defaulted: a music bed (curated packs via
+  **Consider:** a brand graphic rendered from a catalog text primitive.
+- **DEFAULT** Audio is decided, never defaulted: a music bed (curated packs via
   `import_resource {kind:"music-pack"}`) or ambience/loops (Freesound via
   `search_resources kind:"sfx"`), honoring the brand kit's `musicMood`;
   cut to the beat via `materializeGrid` when the bed drives pacing — OR an
   explicit intentional-silence decision recorded in your delivery note with
-  the reason. **K:** a render whose silence nobody chose.
-- **MUST** Footage carries the video: real footage / real UI / real data
-  ≥60% of runtime for footage-first classes. Text alone is not a video.
-- **MUST** Every stock asset's provenance is recorded (provider, id, author).
-- **MUST** Safe-area respected: no critical copy in the outer ~8% of frame.
-- **MUST** One final render per approval; iterate with previews, not renders.
-- **MUST** Delivery never ends with "done": the last message carries the
+  the reason. **Consider:** a render whose silence nobody chose.
+- **DEFAULT** Footage carries the video: real footage / real UI / real data
+  ≥60% of runtime for footage-first classes. Typography-only work is a valid requested format.
+- **DEFAULT** Every stock asset's provenance is recorded (provider, id, author).
+- **DEFAULT** Safe-area respected: no critical copy in the outer ~8% of frame.
+- **DEFAULT** One final render per approval; iterate with previews, not renders.
+- **DEFAULT** Delivery never ends with "done": the last message carries the
   output link and where to find it, plus the intentional-silence note if any.
 
 ## 1. Social reel — 9:16 · 8–30s
 
-- **MUST (K)** The hook lands inside 2 seconds: the strongest image, motion,
+- **DEFAULT** The hook lands inside 2 seconds: the strongest image, motion,
   or claim opens the piece. No logo-first cold opens, no fade-in-from-black
   preambles.
-- **MUST** Typography is poster-grade: composed plates/fields in the brand
-  palette, considered alignment and scale. **K:** centered white text
+- **DEFAULT** Typography is poster-grade: composed plates/fields in the brand
+  palette, considered alignment and scale. **Consider:** centered white text
   floating on footage.
-- **MUST** Pacing is cut-driven: a new visual beat at least every ~4s; static
+- **DEFAULT** Pacing is cut-driven: a new visual beat at least every ~4s; static
   holds >4s need motion inside the frame (reframe push, kenBurns, animated
   card) or they die.
-- **MUST** Ends on a deliberate beat: tagline, logo, or CTA lockup — not a
+- **DEFAULT** Ends on a deliberate beat: tagline, logo, or CTA lockup — not a
   clip running out.
 - **SHOULD** Cuts land on the music grid when a bed exists.
 
 ## 2. Launch film / feature announcement — 16:9 · 30–90s
 
-- **MUST (K)** Payoff-first hook: the OUTCOME, not the feature name
+- **DEFAULT** Payoff-first hook: the OUTCOME, not the feature name
   ("Close the books two days faster" beats "Introducing the reconciliation
   module"). No throat-clearing ("in this video we're going to…").
-- **MUST** Narration or a bed that builds toward the reveal; pacing tightens
+- **DEFAULT** Narration or a bed that builds toward the reveal; pacing tightens
   as the payoff approaches.
-- **MUST** Real product surface: actual UI/screens/output — never mocked.
-- **MUST** End card with a single CTA.
-- **MUST** Captions present when narrated.
+- **DEFAULT** Real product surface: actual UI/screens/output — never mocked.
+- **DEFAULT** End card with a single CTA.
+- **DEFAULT** Captions present when narrated.
 
 ## 3. Brand-identity reel — 9:16 · 12–20s (the showcase class)
 
 Everything in §1, plus:
-- **MUST** Three-beat arc: opening brand moment (wordmark treatment) →
+- **DEFAULT** Three-beat arc: opening brand moment (wordmark treatment) →
   middle craft/proof beat (the subject's world, with an editorial device —
   numbered chapter, pull-quote, stat) → closing tagline lockup.
-- **MUST** Every graphic is bespoke to the brand: its type, its palette as
-  fields, its layout system. **K:** any layout that would look correct with
+- **DEFAULT** Every graphic is bespoke to the brand: its type, its palette as
+  fields, its layout system. **Consider:** any layout that would look correct with
   another brand's hex swapped in.
-- **MUST** Footage color and brand palette agree — grade toward the palette
+- **DEFAULT** Footage color and brand palette agree — grade toward the palette
   or choose footage that lives in it.
 
 ## 4. Talking-head clip — any aspect · 15–60s
 
-- **MUST (K)** Hook = the strongest sentence, first. Cut TO the moment;
+- **DEFAULT** Hook = the strongest sentence, first. Cut TO the moment;
   never open on wind-up.
-- **MUST** Active-speaker reframe (`focus: active-speaker` / `face`) — a
+- **DEFAULT** Active-speaker reframe (`focus: active-speaker` / `face`) — a
   moving camera, not a static center crop.
-- **MUST** Captions timed to the saved edited timeline (`captions.fromComposition`
+- **DEFAULT** Captions timed to the saved edited timeline (`captions.fromComposition`
   after the clip edits; re-run after later edits). Speech clips must have saved duration matching playable source duration divided by
   playbackRate.
   The focused behind-the-speaker LOOK is an overlay text layer at
   `zPlane:"behind-subject"` where the footage allows. Use caption-layer
   `zPlane:"behind-subject"` only when the user explicitly wants every running
   caption behind the speaker and the legibility gate accepts it.
-- **MUST** Dead air and false starts cut (`addExcludedRange` /
+- **DEFAULT** Dead air and false starts cut (`addExcludedRange` /
   `cutAndRipple`).
 
 ## Scoring discipline
 
-Before the final render: (1) pull stills at each beat boundary and describe
-each one to yourself BEFORE judging it; (2) walk the class checklist and list
-every MUST as pass/fail; (3) any K fails → fix, re-preview; (4) run
-`score_composition` when the budget allows and fix the worst criterion first.
-The checklist is the floor; the judge is the critic; neither substitutes for
-looking at the frames.
+Check the requested criteria against appropriate real evidence: affected stills, continuous motion and audio when relevant. Broader review can use `score_composition` when useful and within budget; it is not mandatory for a scoped correction. The hosted judge includes a fixed caption criterion and can penalize intentionally uncaptioned work; do not add captions solely to improve that score. These skill changes do not change judge behavior. Failed user acceptance criteria remain failures regardless of score. Stop and report remaining gaps after two passes without improvement; export only for requested final delivery.

package/dist/supportedAgents.js

@@ -1,2 +1,2 @@
 #!/usr/bin/env node
-import"./chunk-MCQRX24V.js";import{agents as c}from"add-mcp";var o=["claude-code","cursor","codex","vscode","windsurf","zed","antigravity","github-copilot-cli"];function s(e){let t=o.indexOf(e);return t===-1?o.length:t}var a=Object.entries(c).filter(([e,t])=>e!=="gemini-cli"&&(t.supportedTransports??[]).includes("http")).map(([e,t])=>({id:e,label:t.displayName??e})).sort((e,t)=>s(e.id)-s(t.id)||e.id.localeCompare(t.id));function p(e=4){let t=a.map(i=>i.label),n=t.slice(0,e).join(", "),r=t.length-e;return r>0?`${n} \u2014 and ${r} more`:n}export{a as SUPPORTED_AGENTS,p as supportedAgentsSentence};
+import"./chunk-3QSA3EBY.js";import{agents as c}from"add-mcp";var o=["claude-code","cursor","codex","vscode","windsurf","zed","antigravity","github-copilot-cli"];function s(e){let t=o.indexOf(e);return t===-1?o.length:t}var a=Object.entries(c).filter(([e,t])=>e!=="gemini-cli"&&(t.supportedTransports??[]).includes("http")).map(([e,t])=>({id:e,label:t.displayName??e})).sort((e,t)=>s(e.id)-s(t.id)||e.id.localeCompare(t.id));function p(e=4){let t=a.map(i=>i.label),n=t.slice(0,e).join(", "),r=t.length-e;return r>0?`${n} \u2014 and ${r} more`:n}export{a as SUPPORTED_AGENTS,p as supportedAgentsSentence};