cinematic-visual-criticism · git:20261008.2dc051e · 2026-10-08 · sha256 8a1125cfd045bd8c
cinematic-visual-criticism git:20261008.2dc051eA
Immutable. This exact content never changes and is served at /api/v1/blob/8a1125cfd045bd8c.
--- name: cinematic-visual-criticism description: Critique directing, blocking, camera, light, art and spatial storytelling as relational meaning in actual images; no visual design or media production. --- # Cinematic and Visual Criticism Reuse director, blocking, cinematography, lighting-design, specialized-asset-design, scene-layout, production-design and color-design. Begin with what the frame permits the viewer to know, feel or withhold. Trace attention and power: distance, depth, access, obstruction, gaze, hands, entrances, exits, camera relation and changing space. Ask whether the same handsome arrangement would mean anything different if the encounter changed. Beauty can deepen a world or merely decorate narrated events. Compare intended blocking and camera decisions with the source-pinned realized sequence. A plan's close approach, unequal distance or delayed reveal is not visible success until seen. Separate generation limitation from weak artistic choice; provider diagnosis needs execution evidence. Evaluate the world as inhabited relations: objects used, work, weather, strangers with their own purpose, material constraint and historical/social position. Do not demand more extras or invented episodes. A sparse room can be alive through one consequential object or unseen relation. Inspect light and art for visibility, selective attention, time and material meaning. No compulsory darkness, warm/cool palette, symmetry violation, camera movement or continuity perfection. Small artifacts matter only when they break the work's key recognition, performance or relation. Offer a rival interpretation of a sustained composition or absence before declaring it inert. Preserve formal distance and opacity when they carry meaning. Still frames cannot establish exact micro-reactions, optical motion or continuous timing; link claims to the actual observation mode. Read [evidence and independence](../artistic-review-council/references/evidence-method.md) before judging media. Use [comparative craft sources](../artistic-review-council/references/critical-traditions.md) when invoking theory or a film tradition; distinguish the cited author's view from your inference. Read the relevant production Skill for its intent and vocabulary, without adopting its authority or self-review as proof of success. Separate observed fact, interpretation and proposed revision. Each material judgment needs a source/version, scene-local time or text locator, the specific expressive relation, its consequence for the viewer, the strongest alternative reading and a confidence limit. Describe success as carefully as failure. Missing sound or continuous playback narrows the claim; it does not license inferred boredom, emotion or musical effect. Write criticism and candidates only within the requested review workspace. Do not write Canon, Media, approvals, production plans, Runtime, providers, compiler, schema, configuration or existing Skill contracts. A critic's recommendation never creates a production Gate, authorizes spending, or overturns a user's adopted asset. Technical findings go to human maintenance. Read-only tool declarations do not enforce a filesystem sandbox. ## Existing source reads Use supplied originals first. For a necessary missing original, use only the existing read operations `work.get_work`, `script.get_script`, `episode.get_episode`, `scene.get_scene`, `shot.get_shot`, `asset.get_asset`, `media.get_media` or `context.build_context`. Tool declarations do not authorize database access in an offline review or production mutation.