← 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 storytelling

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

5. Keyframes: create or upload approved first frames when continuity matters. ## Model Choices - Final high-quality shots: Seedance 2.0. - Control-heavy video: Kling v3 when schema supports the needed controls. - Brief simple motion: Hap...

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). 5. Keyframes: create or uploa...

Compare saved observations

Download comparison JSON

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -8,6 +8,10 @@
 
 # Storytelling
 
+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 wants a sequence, not a single asset. Execution runs through
 fal.ai MCP tools.
 
@@ -31,7 +35,8 @@
 3. Continuity anchors: what must remain stable.
 4. Model route: text-to-video, image-to-video, reference-to-video, or
    talking-head/audio path.
-5. Keyframes: create or upload approved first frames when continuity matters.
+5. Keyframes: create or upload first frames when continuity matters; check
+   them before dependent shots.
 6. Async execution per shot.
 7. Review sequence order, duration, continuity, and artifact defects.
 
@@ -47,13 +52,13 @@
 - Ending state.
 - What must not change.
 
-## Model Choices
+## Model selection
 
-- Final high-quality shots: Seedance 2.0.
-- Control-heavy video: Kling v3 when schema supports the needed controls.
-- Brief simple motion: Happy Horse or fast video endpoints.
-- Product/character continuity: use approved stills or reference-to-video.
-- Voice/spoken story: use UGC/talking-head routes and align visuals to audio.
+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: storytelling\ndescription: >\n  Build multi-shot narrative image, video, and audio workflows with fal.ai.\n  Use for storyboards, shot lists, multi-prompt video, first-frame/last-frame\n  pipelines, social stories, brand films, and sequence continuity.\n---\n\n# Storytelling\n\nUse when the user wants a sequence, not a single asset. Execution runs through\nfal.ai MCP tools.\n\nLoad `cinematography` for shot language and `character-design` when identity\ncontinuity matters.\n\n## Inputs To Collect\n\n- Format: ad, short film, music video, documentary, tutorial, social story.\n- Duration and aspect ratio.\n- Number of shots or range.\n- Main subject, character, product, or location.\n- Continuity anchors: character, product, wardrobe, environment, color.\n- Source media: first frame, reference image, product shot, audio track.\n- Audio needs: narration, music, sound design, transcript, or no audio.\n\n## Story Build\n\n1. Beat sheet: what changes emotionally or informationally.\n2. Shot list: one visual purpose per shot.\n3. Continuity anchors: what must remain stable.\n4. Model route: text-to-video, image-to-video, reference-to-video, or\n   talking-head/audio path.\n5. Keyframes: create or upload approved first frames when continuity matters.\n6. Async execution per shot.\n7. Review sequence order, duration, continuity, and artifact defects.\n\n## Shot Prompt Pattern\n\nFor each shot:\n\n- Shot number and purpose.\n- Subject and action.\n- Framing and camera movement.\n- Lighting and environment.\n- Continuity anchors.\n- Ending state.\n- What must not change.\n\n## Model Choices\n\n- Final high-quality shots: Seedance 2.0.\n- Control-heavy video: Kling v3 when schema supports the needed controls.\n- Brief simple motion: Happy Horse or fast video endpoints.\n- Product/character continuity: use approved stills or reference-to-video.\n- Voice/spoken story: use UGC/talking-head routes and align visuals to audio.\n\n## Quality Bar\n\n- Every shot has a narrative job.\n- Continuity anchors are repeated and visible.\n- The sequence can be edited together without random style drift.\n- The final answer includes shot manifest, output URLs, endpoint IDs, and known\n  issues.\n"
AFTER
"---\nname: storytelling\ndescription: >\n  Build multi-shot narrative image, video, and audio workflows with fal.ai.\n  Use for storyboards, shot lists, multi-prompt video, first-frame/last-frame\n  pipelines, social stories, brand films, and sequence continuity.\n---\n\n# Storytelling\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 wants a sequence, not a single asset. Execution runs through\nfal.ai MCP tools.\n\nLoad `cinematography` for shot language and `character-design` when identity\ncontinuity matters.\n\n## Inputs To Collect\n\n- Format: ad, short film, music video, documentary, tutorial, social story.\n- Duration and aspect ratio.\n- Number of shots or range.\n- Main subject, character, product, or location.\n- Continuity anchors: character, product, wardrobe, environment, color.\n- Source media: first frame, reference image, product shot, audio track.\n- Audio needs: narration, music, sound design, transcript, or no audio.\n\n## Story Build\n\n1. Beat sheet: what changes emotionally or informationally.\n2. Shot list: one visual purpose per shot.\n3. Continuity anchors: what must remain stable.\n4. Model route: text-to-video, image-to-video, reference-to-video, or\n   talking-head/audio path.\n5. Keyframes: create or upload first frames when continuity matters; check\n   them before dependent shots.\n6. Async execution per shot.\n7. Review sequence order, duration, continuity, and artifact defects.\n\n## Shot Prompt Pattern\n\nFor each shot:\n\n- Shot number and purpose.\n- Subject and action.\n- Framing and camera movement.\n- Lighting and environment.\n- Continuity anchors.\n- Ending state.\n- What must not change.\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- Every shot has a narrative job.\n- Continuity anchors are repeated and visible.\n- The sequence can be edited together without random style drift.\n- The final answer includes shot manifest, output URLs, endpoint IDs, and known\n  issues.\n"
Full snapshot data
{
  "description": "Build multi-shot narrative image, video, and audio workflows with fal.ai. Use for storyboards, shot lists, multi-prompt video, first-frame/last-frame pipelines, social stories, brand films, and sequence continuity.\n",
  "included_files": [],
  "name": "storytelling",
  "skill_md_contents": "---\nname: storytelling\ndescription: >\n  Build multi-shot narrative image, video, and audio workflows with fal.ai.\n  Use for storyboards, shot lists, multi-prompt video, first-frame/last-frame\n  pipelines, social stories, brand films, and sequence continuity.\n---\n\n# Storytelling\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 wants a sequence, not a single asset. Execution runs through\nfal.ai MCP tools.\n\nLoad `cinematography` for shot language and `character-design` when identity\ncontinuity matters.\n\n## Inputs To Collect\n\n- Format: ad, short film, music video, documentary, tutorial, social story.\n- Duration and aspect ratio.\n- Number of shots or range.\n- Main subject, character, product, or location.\n- Continuity anchors: character, product, wardrobe, environment, color.\n- Source media: first frame, reference image, product shot, audio track.\n- Audio needs: narration, music, sound design, transcript, or no audio.\n\n## Story Build\n\n1. Beat sheet: what changes emotionally or informationally.\n2. Shot list: one visual purpose per shot.\n3. Continuity anchors: what must remain stable.\n4. Model route: text-to-video, image-to-video, reference-to-video, or\n   talking-head/audio path.\n5. Keyframes: create or upload first frames when continuity matters; check\n   them before dependent shots.\n6. Async execution per shot.\n7. Review sequence order, duration, continuity, and artifact defects.\n\n## Shot Prompt Pattern\n\nFor each shot:\n\n- Shot number and purpose.\n- Subject and action.\n- Framing and camera movement.\n- Lighting and environment.\n- Continuity anchors.\n- Ending state.\n- What must not change.\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- Every shot has a narrative job.\n- Continuity anchors are repeated and visible.\n- The sequence can be edited together without random style drift.\n- The final answer includes shot manifest, output URLs, endpoint IDs, and known\n  issues.\n"
}

SHA-256 of public snapshot: b9518f9f97614ec819872253e6cf9db8db4af73b21e21999e3768ee33cd4230c