cueframe 0.11.0 → 0.11.4

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

@@ -6,13 +6,7 @@ description: >-
 
 # CueFrame Storyboard: brief → flow
 
-## 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 the [project and capability policy](../composing-video/references/project-policy.md) for scope, current state and metered work.
 
 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)

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

@@ -5,13 +5,7 @@ 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).
+Use the [project and capability policy](../composing-video/references/project-policy.md) for scope, current state and metered work.
 
 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,
@@ -61,7 +55,7 @@ A correction to one sibling does not require rendering the master or the other u
    the bed is present and the silence decision, if any, still holds; the sibling's delivery
    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
+6. **Inspect each sibling as its own artifact.** Use `score_composition` only when useful for broader review and within budget, with the
    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
@@ -69,17 +63,7 @@ A correction to one sibling does not require rendering the master or the other u
 
 ## What good looks like
 
-Quoted from `video-craft-standards` (cross-cutting rules — every artifact):
-
-> **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.
-
-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.
+Use the relevant [craft review questions](../video-craft-standards/SKILL.md) and the [preview workflow](../cueframe-compose-loop/references/preview-workflow.md). Judge the brief's actual intent, visual relationships, timing and sound; format suggestions do not override the requested treatment. The cross-cutting rules in the [format standards](../video-craft-standards/references/format-standards.md) apply to every sibling. Apply the original brief at the new dimensions: aspect ratio alone does not impose a social-reel hook or pacing, and derivation changes the frame, never the bar.
 
 ## Delivering
 

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

@@ -6,13 +6,7 @@ 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).
+Use the [project and capability policy](../composing-video/references/project-policy.md) for scope, current state and metered work.
 
 ## The one idea
 

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

@@ -5,13 +5,7 @@ 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).
+Use the [project and capability policy](../composing-video/references/project-policy.md) for scope, current state and metered work.
 
 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
@@ -56,8 +50,7 @@ affected window and regressions without automatically rerunning the full-film ju
    product video.
 5. **Cards for the claims and the end card.** Key lines and the closing CTA are `kind:"card"`
    HTML in the brand's type and palette, animated in its CSS or with
-   `clip.setKeyframes` in a FOLLOWING `apply_composition` call. One CTA on the end card, held
-   long enough to read, plus the date if there is one.
+   `clip.setKeyframes` in a FOLLOWING `apply_composition` call. When the brief calls for a CTA, use one, on the end card, held long enough to read; include a date only when relevant.
 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
@@ -68,25 +61,12 @@ affected window and regressions without automatically rerunning the full-film ju
    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`. 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 relevant acceptance failures; `create_render` →
-   `wait_job (kind:"render")`.
+8. **Inspect and deliver.** `preview_frame` at t=0, hook-end, the reveal, and the end
+   card; describe each still and ask whether a real capture is on screen; distinguish actual captures from reconstructed artwork. Inspect motion through the important handoffs and listen to changed audio. Use `score_composition` only when broader critique is useful and within budget, with the payoff line as `editorialIntent`. Fix the observed acceptance failures, then export for requested final delivery.
 
 ## What good looks like
 
-Quoted from `video-craft-standards` §2 (Launch film / feature announcement) — these are format defaults:
-
-> **DEFAULT** Payoff-first hook: the OUTCOME, not the feature name ("Close the books two days
-> faster" beats "Introducing the reconciliation module"). No throat-clearing.
-
-> **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.
-
-> **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."*
+Use the relevant [craft review questions](../video-craft-standards/SKILL.md) and the [preview workflow](../cueframe-compose-loop/references/preview-workflow.md). Judge the brief's actual intent, visual relationships, timing and sound; format suggestions do not override the requested treatment. For this format's defaults read section 2 (Launch film) of the [format standards](../video-craft-standards/references/format-standards.md).
 
 ## Delivering
 
@@ -94,6 +74,6 @@ Close with the handoff, never "done":
 
 - The render link and where it lives (project + composition id).
 - Attribution for the bed and any licensed asset (provider, id, author).
-- The intentional-silence note with its reason, in the rare case silence was chosen.
+- The intentional-silence note with its reason, when relevant to the requested delivery.
 - A one-line cutdown offer: the 16:9 master can become 9:16 / 1:1 siblings for social (see
   `every-format-from-one-edit`).

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

@@ -5,13 +5,7 @@ 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).
+Use the [project and capability policy](../composing-video/references/project-policy.md) for scope, current state and metered work.
 
 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
@@ -74,29 +68,16 @@ affected window and regressions without automatically rerunning the full-film ju
    `describe_composition_ops({type:"captions.fromComposition"})`, then style via
    `setCaptionStyle` (plated, bottom, out of the mouth/eyes). Most social viewing is sound-off;
    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. 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,
+8. **Inspect and revise.** `preview_frame` at the important layout and transition landmarks;
+   describe each still in words, then inspect the intervening motion and relevant audio. Use
+   `score_composition` only when broader critique is useful and within budget, with your one-line
+   vision as `editorialIntent`, and fix the worst criterion first. Fix located acceptance failures against the brief.
+9. **Export for requested final delivery.** `create_render` → `wait_job (kind:"render")`. Iterate with previews,
    not renders.
 
 ## What good looks like
 
-Quoted from `video-craft-standards` §1 (Social reel) — these are defaults for this format, subject to the scope policy above:
-
-> **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.
-
-> **DEFAULT** Typography is poster-grade: composed plates/fields in the brand palette, considered
-> alignment and scale. **Consider:** centered white text floating on footage.
-
-> **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:
-
-> **DEFAULT** Audio is decided, never defaulted […] **Consider:** a render whose silence nobody chose.
+Use the relevant [craft review questions](../video-craft-standards/SKILL.md) and the [preview workflow](../cueframe-compose-loop/references/preview-workflow.md). Judge the brief's actual intent, visual relationships, timing and sound; format suggestions do not override the requested treatment. For this format's defaults read section 1 (Social reel) of the [format standards](../video-craft-standards/references/format-standards.md).
 
 ## Delivering
 

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

@@ -5,13 +5,7 @@ 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).
+Use the [project and capability policy](../composing-video/references/project-policy.md) for scope, current state and metered work.
 
 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
@@ -72,18 +66,7 @@ keep the final re-render separate from previews used to resolve individual styli
 
 ## What good looks like
 
-Quoted from `video-craft-standards` §3 (Brand-identity reel) — the bespoke test applies to every
-card in any class:
-
-> **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.
-
-> **DEFAULT** Footage color and brand palette agree — grade toward the palette or choose footage
-> that lives in it.
-
-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."*
+Use the relevant [craft review questions](../video-craft-standards/SKILL.md) and the [preview workflow](../cueframe-compose-loop/references/preview-workflow.md). Judge the brief's actual intent, visual relationships, timing and sound; format suggestions do not override the requested treatment. The bespoke test in section 3 of the [format standards](../video-craft-standards/references/format-standards.md) applies to every card in any class.
 
 ## Delivering
 

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

@@ -1,121 +1,38 @@
 ---
 name: video-craft-standards
-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.
+description: "Use when judging whether a CueFrame video's idea, visual form, motion, timing and sound meet its brief or reference (social reel, launch film, brand reel, talking-head clip). For tool selection and scoped revision use cueframe-compose-loop. 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
+# Video craft review
 
-## Scope and capability policy
+Use the [project and capability policy](../composing-video/references/project-policy.md). Judge the requested film, not a universal house style. Typography, gradients, logo openings, deliberate stillness, silent work and reconstructed UI artwork can all be valid choices. Factual claims and the identity of actual captures must remain truthful.
 
-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.
+[cueframe-compose-loop](../cueframe-compose-loop/SKILL.md) owns evidence, optional judge use and revision scope. Its [preview workflow](../cueframe-compose-loop/references/preview-workflow.md) distinguishes isolated previews, saved compositions and final exports. Use these questions where they matter to the brief; a small color correction does not require a new whole-film critique.
 
-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.
+## What should the viewer experience?
 
-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).
+Can the film's intended idea, transformation, mood or observation be understood? Does each major choice support it? For a story, does an action change what follows? For an identity study, are form and movement specific to that identity? A film can intentionally be non-narrative; do not invent a sales argument to justify it.
 
-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.
+## Do the visual relationships hold?
 
-## The controlling idea — the rule above every rule
+Inspect hierarchy, silhouette, spacing and legibility at the intended viewing size. Verify that essential copy has enough readable time after settling. For a reference, compare projected bounds, glyph form, angles, materials and camera path as well as subject names. Two scenes showing the same phone are not necessarily the same shot.
 
-- **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?).
-- **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
-    gets a patient, sparse bed and the nerve to hold shots; an "instant"
-    claim cuts hot). Silence and pauses are rhetoric, not absence.
-  - **Pacing** — the cut rhythm IS part of the argument; it may defy
-    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.
-- **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.
+Mounted UI should remain attached to its screen. Masks, edges and occlusion should agree with the pose. A pointer contacts the intended control before the response; an object carried through a transition retains identity and an intelligible path. Multiple simultaneous movements are useful when the viewer can follow their relationship. An attractive still does not establish any of these temporal properties.
 
-## Cross-cutting rules (every artifact)
+## Does time express the idea?
 
-These are final-artifact criteria, not a requirement to re-plan or export after every tweak.
-For scoped corrections and preview selection, use `cueframe-compose-loop`'s
-[preview workflow](../cueframe-compose-loop/references/preview-workflow.md). Inspect continuous
-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.
+Look for accidental pauses, rushed reading windows, unexplained changes in speed and transitions that lose the subject. A deliberate hold can be the strongest beat. Check actual stable time rather than a layer's nominal duration. For a revision, ensure dependent motion and sound still agree with the new event order. Inspect the complete end, including backgrounds, captions and tails.
 
-- **DEFAULT** Brand/text graphics are AUTHORED — `kind:"card"` HTML (your
-  typography, layout, palette-as-fields) animated in CSS or with `clip.setKeyframes`,
-  or a native component (`create_component`). Catalog text primitives are for utility only.
-  **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. **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.
+## Does the medium support the promise?
 
-## 1. Social reel — 9:16 · 8–30s
+- **Product evidence:** a real interaction and its result are visible and legible. Simulated UI is identified as artwork, not a capture of working software.
+- **Speech-led footage:** selected words preserve meaning; captions and framing follow actual source evidence and the saved edit. Camera movement and captions are choices governed by the brief.
+- **Type, illustration or data:** geometry and transformation carry meaning; text remains accurate, values are sourced and material behavior is coherent.
+- **Brand work:** type, palette, material and motion form an intentional system; a new logo/name should not be the only thing distinguishing a supposedly specific treatment.
+- **Sound:** heard intelligibility, balance and event synchronization are separate from loudness or waveform measurements. Silence needs no apology when it serves the piece.
 
-- **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.
-- **DEFAULT** Typography is poster-grade: composed plates/fields in the brand
-  palette, considered alignment and scale. **Consider:** centered white text
-  floating on footage.
-- **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.
-- **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.
+A useful critique names a timestamp/window, observed problem, its consequence and a plausible correction. Prioritize failures of intent, fidelity or continuity over minor polish. Do not certify unseen motion or unheard audio, and do not substitute a score for the user's acceptance criteria.
 
-## 2. Launch film / feature announcement — 16:9 · 30–90s
+## Detailed guidance
 
-- **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…").
-- **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.
-- **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:
-- **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.
-- **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.
-- **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
-
-- **DEFAULT** Hook = the strongest sentence, first. Cut TO the moment;
-  never open on wind-up.
-- **DEFAULT** Active-speaker reframe (`focus: active-speaker` / `face`) — a
-  moving camera, not a static center crop.
-- **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.
-- **DEFAULT** Dead air and false starts cut (`addExcludedRange` /
-  `cutAndRipple`).
-
-## Scoring discipline
-
-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.
+[Format standards](references/format-standards.md) has the controlling idea, the cross-cutting rules, and the checklists for social reels, launch films, brand-identity reels and talking-head clips, plus scoring discipline.

package/dist/skills/video-craft-standards/references/format-standards.md

@@ -0,0 +1,118 @@
+# Format standards
+
+Defaults, examples and detail for this topic. The [skill](../SKILL.md) and the [project and capability policy](../../composing-video/references/project-policy.md) take precedence where they differ, and the current tool schemas are authoritative.
+
+## 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).
+
+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
+
+- **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?).
+- **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
+    gets a patient, sparse bed and the nerve to hold shots; an "instant"
+    claim cuts hot). Silence and pauses are rhetoric, not absence.
+  - **Pacing** — the cut rhythm IS part of the argument; it may defy
+    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.
+- **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.
+
+## Cross-cutting rules (every artifact)
+
+These are final-artifact criteria, not a requirement to re-plan or export after every tweak.
+For scoped corrections and preview selection, use `cueframe-compose-loop`'s
+[preview workflow](../../cueframe-compose-loop/references/preview-workflow.md). Inspect continuous
+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.
+
+- **DEFAULT** Brand/text graphics are AUTHORED — `kind:"card"` HTML (your
+  typography, layout, palette-as-fields) animated in CSS or with `clip.setKeyframes`,
+  or a native component (`create_component`). Catalog text primitives are for utility only.
+  **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. **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
+
+- **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.
+- **DEFAULT** Typography is poster-grade: composed plates/fields in the brand
+  palette, considered alignment and scale. **Consider:** centered white text
+  floating on footage.
+- **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.
+- **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
+
+- **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…").
+- **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.
+- **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:
+- **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.
+- **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.
+- **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
+
+- **DEFAULT** Hook = the strongest sentence, first. Cut TO the moment;
+  never open on wind-up.
+- **DEFAULT** Active-speaker reframe (`focus: active-speaker` / `face`) — a
+  moving camera, not a static center crop.
+- **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.
+- **DEFAULT** Dead air and false starts cut (`addExcludedRange` /
+  `cutAndRipple`).
+
+## Scoring discipline
+
+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/package.json

@@ -1,6 +1,6 @@
 {
   "name": "cueframe",
-  "version": "0.11.0",
+  "version": "0.11.4",
   "description": "CueFrame video editing CLI: manage media, edit compositions and render MP4s from terminals and scripts.",
   "keywords": [
     "cueframe",
@@ -40,14 +40,14 @@
     "pino": "^10.3.1"
   },
   "devDependencies": {
-    "zod": "^4.5.4",
+    "zod": "^4.6.7",
     "@types/node": "^26.6.5",
     "tsup": "^8.5.1",
     "typescript": "npm:@typescript/typescript6@^6.0.2",
     "vitest": "^5.0.3",
     "@typescript/native": "npm:typescript@^7.0.2",
-    "@cueframe/sdk": "^0.15.0",
-    "@cueframe/skills": "0.4.1"
+    "@cueframe/sdk": "^0.17.0",
+    "@cueframe/skills": "0.4.5"
   },
   "repository": {
     "type": "git",

package/dist/analyze-5KCAIZI6.js

@@ -1,2 +0,0 @@
-#!/usr/bin/env node
-import{L as a}from"./chunk-M3NS5UR2.js";import"./chunk-3QSA3EBY.js";export{a as analyzeCommand};