Turn Prompt Gallery into a reviewable shot contract.

Write the invariant shot intent first

For Prompt Gallery, state the subject, environment, action objective, emotional beat, and end condition in plain production language. These invariants keep general video prompts variants comparable instead of producing unrelated ideas. For this section 1, save a input manifest; have the motion designer review camera intent; record the failed case as well as the accepted one; and do not advance it beyond a source-preserving edit until the named limitation is resolved. Keep gallery evidence separate from prompt assumptions.

Turn the topic into a repeatable method

Move from definition to a small practice sequence, then review the result against explicit craft, rights, and delivery checks. Keep vendor-specific behavior outside the method unless a source verifies it. For this section 2, save a acceptance matrix; have the rights reviewer review revision control; record the failed case as well as the accepted one; and do not advance it beyond a shot approval until the named limitation is resolved. Keep gallery evidence separate from prompt assumptions.

Layer camera, timing, continuity, and sound

Add framing and camera movement only when they support the action. Mark temporal beats, preserve identity and environment anchors, describe sound as intent rather than a guaranteed feature, and name artifacts or changes to avoid. For this section 3, save a camera plan; have the legal reviewer review temporal stability; record the failed case as well as the accepted one; and do not advance it beyond a shot approval until the named limitation is resolved. Keep gallery evidence separate from prompt assumptions.

• Subject and action — record acceptance matrix, art director, input fidelity, and delivery package; keep gallery evidence separate from prompt assumptions.
• Framing and camera relationship — record input manifest, product specialist, reference integrity, and delivery package; keep gallery evidence separate from prompt assumptions.
• Beat order and end state — record delivery checklist, channel owner, motion coherence, and delivery package; keep gallery evidence separate from prompt assumptions.
• Continuity, sound intent, and exclusions — record versioned handoff, rights reviewer, temporal stability, and delivery package; keep gallery evidence separate from prompt assumptions.

Create controlled prompt variants

Change one meaningful dimension per version, such as shot size, movement, pacing, or performance intensity. Label the hypothesis for each variant so review can identify which instruction caused the difference. For this section 4, save a asset ledger; have the editor review identity consent; record the failed case as well as the accepted one; and do not advance it beyond a source-preserving edit until the named limitation is resolved. Keep gallery evidence separate from prompt assumptions.

Review the output without inventing model controls

Check whether the requested action reads clearly, the camera supports the beat, references remain coherent, and the ending is usable. A prompt template does not prove that any named model, duration, audio mode, or parameter is available. For this section 5, save a decision memo; have the rights reviewer review input fidelity; record the failed case as well as the accepted one; and do not advance it beyond a source-preserving edit until the named limitation is resolved. Keep gallery evidence separate from prompt assumptions.

Keep the evidence ledger attached to the decision

Partial evidence was supplied, but it does not establish product support or a complete capability, customer, or performance claim. Record the source, verification date, claim scope, unresolved gap, and the decision that the evidence can support. Search demand must never be reused as capability proof. For this section 6, save a rights record; have the brand reviewer review continuity; record the failed case as well as the accepted one; and do not advance it beyond a source-preserving edit until the named limitation is resolved. Keep gallery evidence separate from prompt assumptions.

Build a specific test brief for prompt gallery

Start with a bounded text brief with visible constraints and an end state. Define one observable change, protected details, a stopping rule, and the named reviewer. The intended output is a reusable prompt contract with controlled variants. Test one variable per version, preserve the source and settings, and compare results at the actual delivery size instead of choosing from an unrecorded impression. For this topic test, save a prompt brief; have the fact checker review revision control; record the failed case as well as the accepted one; and do not advance it beyond a rights-cleared draft until the named limitation is resolved. Keep gallery evidence separate from prompt assumptions.

• Primary query: prompt gallery; test record: shot contract, product specialist, camera intent, and dated decision; keep gallery evidence separate from prompt assumptions.
• Editorial owner: keyword-expansion:0322; decision record: input manifest, channel owner, input fidelity, and bounded experiment; keep gallery evidence separate from prompt assumptions.
• Source scope: a user-provided competitor-gap export dated 2026-08-05 supports topic prioritization only; source review: test worksheet, legal reviewer, editability, and versioned review; keep gallery evidence separate from prompt assumptions.

Separate topic fit from product proof

A dated, user-provided competitor-gap export supports only the decision to cover “prompt gallery.” It does not prove audience demand, SEELE capability, third-party behavior, commercial value, or a likely outcome. Verify product-specific statements against current first-party documentation and a recorded representative test. For this source review, save a prompt brief; have the creative producer review claim support; record the failed case as well as the accepted one; and do not advance it beyond a bounded experiment until the named limitation is resolved. Keep gallery evidence separate from prompt assumptions.