cueframe 0.11.0 → 0.11.3

package/dist/skills/add-music-bed/SKILL.md

@@ -5,20 +5,14 @@ description: Retrofits a music bed (and ambience or SFX) onto an existing compos
 
 # Add a music bed
 
-## 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.
 
 > **Stock-audio limits (verified in production):** a Freesound import lands with
 > `audioRole:"sfx"` and NO beat grid — `import_resource` takes no audioRole param, and
 > `materializeGrid grid:"beat"` will 422 `grid_unavailable` on it. Set the role yourself when
 > placing the clip (`audioRole:"music"` on the composition clip), put the bed on its own AUDIO
-> track (the judge expects a dedicated music track), and until curated music-pack discovery
-> exists, prefer fades over beat-cuts for stock beds — beat-grid cutting works with pack beds.
+> track, kept dedicated to music. Discover curated music beds through `list_catalog`; use an available measured grid
+> only when it exists. A music role alone does not establish a reliable beat grid.
 
 You point at an existing composition that sounds empty; you get it back with a licensed bed that
 matches the brand's mood, sits correctly under any speech, and — where the bed drives pacing —
@@ -50,8 +44,7 @@ delivery; stills and a visual judge cannot establish the mix. Recheck visuals wh
 
 1. **Read the composition and its speech.** `list_compositions` / the composition body for
    what's on the timeline; `get_media_context` for transcripts. Speech present → the voice is
-   the rhythm authority and the bed serves it. No speech → the bed IS the rhythm authority and
-   earns beat-cuts.
+   the rhythm authority and the bed serves it. Without speech, the bed is the default rhythm authority and earns beat-cuts when it has a measured grid; let the visible action drive timing instead when the brief calls for it, and preserve approved cuts unless retiming is requested.
 2. **Find the bed, license-aware.** Beds come from the curated music packs —
    `import_resource { kind:"music-pack" }` — honoring the brand kit's `musicMood` (mood and
    energy matched to the cut rate). For ambience or loop textures, `search_resources
@@ -81,18 +74,7 @@ and its reason in the delivery note instead of forcing a bed.
 
 ## What good looks like
 
-Quoted from `video-craft-standards` (cross-cutting rules — every artifact); this skill exists to
-satisfy the second one:
-
-> **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** Every stock asset's provenance is recorded (provider, id, author).
-
-And from §1: *"**SHOULD** Cuts land on the music grid when a bed exists."*
+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. This skill exists to satisfy the audio rule in the cross-cutting section of the [format standards](../video-craft-standards/references/format-standards.md), which also covers provenance for stock assets; section 1 adds cutting to the music grid when a bed exists.
 
 ## Delivering
 

package/dist/skills/brand-reel/SKILL.md

@@ -5,13 +5,7 @@ description: Produces a 12–20 second 9:16 brand-identity reel — three-beat a
 
 # Brand 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 bring a brand (a website, a kit, or just a logo and a palette) plus footage of its world;
 you get back a 12–20 second vertical reel with a three-beat arc — wordmark moment, craft/proof
@@ -68,30 +62,13 @@ affected behavior and regressions; reserve full-film judging and export for the
    `musicMood`; place it `audioRole:"music"`, then `materializeGrid { grid:"beat" }` and land
    the three beat boundaries on the grid. A brand reel almost always wants a bed; if the brand's
    voice calls for silence, preserve that decision.
-7. **Preview each beat, then get judged.** `preview_frame` at t=0, each beat boundary, and the
-   final lockup; describe each still before scoring. `score_composition` with the brand facts as
-   `brandContext` and your arc as `editorialIntent`; fix the worst axis first, fix relevant acceptance failures.
-8. **One final render.** `create_render` → `wait_job (kind:"render")`.
+7. **Inspect the connected sequence.** `preview_frame` at t=0, each beat boundary, and the
+   final lockup; describe each still, then inspect the intervening motion and relevant sound. Use `score_composition` only for useful, budgeted broader critique, with the brand facts as `brandContext` and your arc as `editorialIntent`; fix the worst axis first, then located acceptance failures.
+8. **Export for requested final delivery.** `create_render` → `wait_job (kind:"render")`.
 
 ## What good looks like
 
-Quoted from `video-craft-standards` §3 (Brand-identity reel) — read the full section; §1's
-social-reel rules apply underneath it:
-
-> **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.
-
-And the cross-cutting card rule:
-
-> **DEFAULT** Brand/text graphics are AUTHORED — `kind:"card"` HTML […] **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. For this format's defaults read section 3 (Brand-identity reel) of the [format standards](../video-craft-standards/references/format-standards.md); section 1's social-reel defaults apply underneath it.
 
 ## Delivering
 

package/dist/skills/clip-a-talking-head/SKILL.md

@@ -5,13 +5,7 @@ description: Cuts a podcast, talk, or interview into shorts that open on the str
 
 # Clip a talking head
 
-## 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 point at long-form footage of people talking; you get back one or more 15–60 second clips
 that each open on the strongest sentence, keep a moving camera on whoever is speaking, cut the
@@ -83,19 +77,7 @@ correction, retain the approved edit and check relevant regressions without auto
 
 ## What good looks like
 
-Quoted from `video-craft-standards` §4 (Talking-head clip) — apply the relevant defaults under the scope policy:
-
-> **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 edited clip (`captions.fromComposition`); behind-speaker
-> placement where the footage allows it. **DEFAULT** Dead air and false starts cut
-> (`addExcludedRange` / `cutAndRipple`).
-
-Plus the cross-cutting audio rule: *"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 4 (Talking-head clip) of the [format standards](../video-craft-standards/references/format-standards.md).
 
 ## Delivering