← falCONTENT HISTORY

Update to fal

Snapshot Nov 14, 2026 · 00:10 UTC · version 1.3.2

Collection source: downloaded plugin package. These snapshots do not have a confirmed matching collection source. Differences in file lists alone do not establish changes to the package.

WHAT CHANGED

Instructions updated for cinematography

Skill instructions — Now says: Bundled guidance is fallback craft. For inputs, recommend_model's `input_contract` and live validation at submission are authoritative. See [the shared...

Observed in instructions or declared skills. Runtime behavior has not been tested.

Save fal and check future changes in Following.

Up to 3 plugins free · no card required.

All fields and original values.

Skill instructions

Before

Sep 30, 2026 · 22:46 UTC

## Model Choices - Premium still: `openai/gpt-image-2`, `fal-ai/nano-banana-pro`. - Final video: Seedance 2.0 text/image video. - Fast video draft: Grok Imagine Video. - Multi-prompt/control-heavy shot: Kling v3.

After

Nov 14, 2026 · 00:10 UTC

Bundled guidance is fallback craft. For inputs, recommend_model's `input_contract` and live validation at submission are authoritative. See [the shared production contract](../shared/production-contract.md). ## Model selection Use `model...

Compare saved observations

Download comparison JSON

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -8,6 +8,10 @@
 
 # Cinematography
 
+Bundled guidance is fallback craft. For inputs, recommend_model's
+`input_contract` and live validation at submission are authoritative. See
+[the shared production contract](../shared/production-contract.md).
+
 Use when the user needs concrete visual direction, not generic "cinematic"
 prompting. Execution runs through fal.ai MCP tools.
 
@@ -33,12 +37,13 @@
 7. Texture: clean digital, film grain, archival, phone, broadcast.
 8. Constraints: no identity/product drift, no fake text, no extra logos.
 
-## Model Choices
+## Model selection
 
-- Premium still: `openai/gpt-image-2`, `fal-ai/nano-banana-pro`.
-- Final video: Seedance 2.0 text/image video.
-- Fast video draft: Grok Imagine Video.
-- Multi-prompt/control-heavy shot: Kling v3.
+Use `model-routing` with this brief and actual references, then submit the
+selected `next_call`. Keep a model the user named. Bundled family suggestions
+must not override the current task-specific recommendation. Inspect one result
+before dependent continuity shots; submit independent variations together with
+`submit_jobs`. Preserve originals through any permitted repair.
 
 ## Quality Bar
 
Full technical diff · 1 changed fields

changed /skill_md_contents

BEFORE
"---\nname: cinematography\ndescription: >\n  Design cinematic image and video prompts for fal.ai. Use for shot language,\n  camera movement, lighting, lens choices, color grade, scene blocking,\n  film texture, and production-ready visual direction.\n---\n\n# Cinematography\n\nUse when the user needs concrete visual direction, not generic \"cinematic\"\nprompting. Execution runs through fal.ai MCP tools.\n\n## Inputs To Collect\n\n- Subject and action.\n- Medium: still, video, image-to-video, edit, storyboard frame.\n- Genre and mood.\n- Framing: close-up, medium, wide, overhead, POV, profile, locked-off.\n- Camera motion: push-in, dolly, tracking, handheld, crane, drone.\n- Lens feel: wide, normal, telephoto, macro, shallow/deep focus.\n- Lighting: natural, practical, studio, noir, high key, low key, backlit.\n- Output: aspect ratio, duration, first frame, last frame.\n\n## Prompt Build\n\n1. Subject/action.\n2. Shot size and camera position.\n3. Camera motion over time if video.\n4. Lens/depth behavior.\n5. Lighting source and direction.\n6. Color palette and grade.\n7. Texture: clean digital, film grain, archival, phone, broadcast.\n8. Constraints: no identity/product drift, no fake text, no extra logos.\n\n## Model Choices\n\n- Premium still: `openai/gpt-image-2`, `fal-ai/nano-banana-pro`.\n- Final video: Seedance 2.0 text/image video.\n- Fast video draft: Grok Imagine Video.\n- Multi-prompt/control-heavy shot: Kling v3.\n\n## Quality Bar\n\n- Prompt describes an actual camera setup.\n- Motion is physically plausible.\n- Lighting direction matches the setting.\n- Video prompt has a beginning and ending state.\n- Any referenced first frame is treated as an anchor, not redesigned.\n"
AFTER
"---\nname: cinematography\ndescription: >\n  Design cinematic image and video prompts for fal.ai. Use for shot language,\n  camera movement, lighting, lens choices, color grade, scene blocking,\n  film texture, and production-ready visual direction.\n---\n\n# Cinematography\n\nBundled guidance is fallback craft. For inputs, recommend_model's\n`input_contract` and live validation at submission are authoritative. See\n[the shared production contract](../shared/production-contract.md).\n\nUse when the user needs concrete visual direction, not generic \"cinematic\"\nprompting. Execution runs through fal.ai MCP tools.\n\n## Inputs To Collect\n\n- Subject and action.\n- Medium: still, video, image-to-video, edit, storyboard frame.\n- Genre and mood.\n- Framing: close-up, medium, wide, overhead, POV, profile, locked-off.\n- Camera motion: push-in, dolly, tracking, handheld, crane, drone.\n- Lens feel: wide, normal, telephoto, macro, shallow/deep focus.\n- Lighting: natural, practical, studio, noir, high key, low key, backlit.\n- Output: aspect ratio, duration, first frame, last frame.\n\n## Prompt Build\n\n1. Subject/action.\n2. Shot size and camera position.\n3. Camera motion over time if video.\n4. Lens/depth behavior.\n5. Lighting source and direction.\n6. Color palette and grade.\n7. Texture: clean digital, film grain, archival, phone, broadcast.\n8. Constraints: no identity/product drift, no fake text, no extra logos.\n\n## Model selection\n\nUse `model-routing` with this brief and actual references, then submit the\nselected `next_call`. Keep a model the user named. Bundled family suggestions\nmust not override the current task-specific recommendation. Inspect one result\nbefore dependent continuity shots; submit independent variations together with\n`submit_jobs`. Preserve originals through any permitted repair.\n\n## Quality Bar\n\n- Prompt describes an actual camera setup.\n- Motion is physically plausible.\n- Lighting direction matches the setting.\n- Video prompt has a beginning and ending state.\n- Any referenced first frame is treated as an anchor, not redesigned.\n"
Full snapshot data
{
  "description": "Design cinematic image and video prompts for fal.ai. Use for shot language, camera movement, lighting, lens choices, color grade, scene blocking, film texture, and production-ready visual direction.\n",
  "included_files": [],
  "name": "cinematography",
  "skill_md_contents": "---\nname: cinematography\ndescription: >\n  Design cinematic image and video prompts for fal.ai. Use for shot language,\n  camera movement, lighting, lens choices, color grade, scene blocking,\n  film texture, and production-ready visual direction.\n---\n\n# Cinematography\n\nBundled guidance is fallback craft. For inputs, recommend_model's\n`input_contract` and live validation at submission are authoritative. See\n[the shared production contract](../shared/production-contract.md).\n\nUse when the user needs concrete visual direction, not generic \"cinematic\"\nprompting. Execution runs through fal.ai MCP tools.\n\n## Inputs To Collect\n\n- Subject and action.\n- Medium: still, video, image-to-video, edit, storyboard frame.\n- Genre and mood.\n- Framing: close-up, medium, wide, overhead, POV, profile, locked-off.\n- Camera motion: push-in, dolly, tracking, handheld, crane, drone.\n- Lens feel: wide, normal, telephoto, macro, shallow/deep focus.\n- Lighting: natural, practical, studio, noir, high key, low key, backlit.\n- Output: aspect ratio, duration, first frame, last frame.\n\n## Prompt Build\n\n1. Subject/action.\n2. Shot size and camera position.\n3. Camera motion over time if video.\n4. Lens/depth behavior.\n5. Lighting source and direction.\n6. Color palette and grade.\n7. Texture: clean digital, film grain, archival, phone, broadcast.\n8. Constraints: no identity/product drift, no fake text, no extra logos.\n\n## Model selection\n\nUse `model-routing` with this brief and actual references, then submit the\nselected `next_call`. Keep a model the user named. Bundled family suggestions\nmust not override the current task-specific recommendation. Inspect one result\nbefore dependent continuity shots; submit independent variations together with\n`submit_jobs`. Preserve originals through any permitted repair.\n\n## Quality Bar\n\n- Prompt describes an actual camera setup.\n- Motion is physically plausible.\n- Lighting direction matches the setting.\n- Video prompt has a beginning and ending state.\n- Any referenced first frame is treated as an anchor, not redesigned.\n"
}

SHA-256 of public snapshot: 84e3db74e4436880764271b846b862e7935818290676f59a5ec8ad2e7169de5c