← 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 ugc

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

## Production Routes - Portrait plus audio: `veed/fabric-1.0`. - Portrait plus text: `veed/fabric-1.0/text`. - Avatar with visual direction: `fal-ai/creatify/aurora`. - Existing footage with new speech: `fal-ai/sync-lipsync/v2`. - Produc...

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
@@ -9,6 +9,10 @@
 
 # UGC Production
 
+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 creator-style content instead of polished studio ads.
 Execution runs through fal.ai MCP tools.
 
@@ -35,14 +39,13 @@
 Avoid fake testimonials and unsupported medical, financial, or performance
 claims.
 
-## Production Routes
+## Model selection
 
-- Portrait plus audio: `veed/fabric-1.0`.
-- Portrait plus text: `veed/fabric-1.0/text`.
-- Avatar with visual direction: `fal-ai/creatify/aurora`.
-- Existing footage with new speech: `fal-ai/sync-lipsync/v2`.
-- Product b-roll: `bytedance/seedance-2.0/image-to-video`.
-- Hook frames/thumbnails: `openai/gpt-image-2` or `fal-ai/nano-banana-pro`.
+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: ugc\ndescription: >\n  Plan and produce UGC-style creator ads and social videos with fal.ai. Use for\n  direct-to-camera creator scripts, talking-head ads, product demos,\n  testimonials, founder clips, unboxing, reactions, before-after, faceless\n  voiceover, and short vertical social videos.\n---\n\n# UGC Production\n\nUse when the user wants creator-style content instead of polished studio ads.\nExecution runs through fal.ai MCP tools.\n\n## Inputs To Collect\n\n- Product or offer.\n- Format: direct-to-camera, demo, reaction, unboxing, founder, faceless b-roll.\n- Speaker: supplied portrait/video, generated avatar, no face, or voiceover.\n- Script source: exact script, bullets, offer copy, or ask to draft.\n- Platform: TikTok, Reels, Shorts, paid social, landing page, prototype.\n- Runtime/crop: usually 9:16; 6-15 seconds for hooks, 15-45 for ads.\n- Source media: portrait, product image/video, logo, b-roll, audio.\n- Claims: proof supplied, disclaimers, banned phrases.\n\n## Script Shape\n\n1. Hook: concrete tension, result, objection, or curiosity.\n2. Context: why the speaker cares.\n3. Product moment: visible use, demo, or comparison.\n4. Proof: supplied metric, visible result, or sensory detail.\n5. Turn: objection answered or before-after.\n6. Close: soft CTA or final product frame.\n\nAvoid fake testimonials and unsupported medical, financial, or performance\nclaims.\n\n## Production Routes\n\n- Portrait plus audio: `veed/fabric-1.0`.\n- Portrait plus text: `veed/fabric-1.0/text`.\n- Avatar with visual direction: `fal-ai/creatify/aurora`.\n- Existing footage with new speech: `fal-ai/sync-lipsync/v2`.\n- Product b-roll: `bytedance/seedance-2.0/image-to-video`.\n- Hook frames/thumbnails: `openai/gpt-image-2` or `fal-ai/nano-banana-pro`.\n\n## Quality Bar\n\n- First 1-2 seconds have a clear hook.\n- Spoken script fits runtime.\n- Mouth motion is synced for speaking faces.\n- Product/logo/packaging stay stable.\n- Captions/text are not hallucinated inside the video.\n- Claims are user-supplied or phrased as visible observations.\n"
AFTER
"---\nname: ugc\ndescription: >\n  Plan and produce UGC-style creator ads and social videos with fal.ai. Use for\n  direct-to-camera creator scripts, talking-head ads, product demos,\n  testimonials, founder clips, unboxing, reactions, before-after, faceless\n  voiceover, and short vertical social videos.\n---\n\n# UGC Production\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 creator-style content instead of polished studio ads.\nExecution runs through fal.ai MCP tools.\n\n## Inputs To Collect\n\n- Product or offer.\n- Format: direct-to-camera, demo, reaction, unboxing, founder, faceless b-roll.\n- Speaker: supplied portrait/video, generated avatar, no face, or voiceover.\n- Script source: exact script, bullets, offer copy, or ask to draft.\n- Platform: TikTok, Reels, Shorts, paid social, landing page, prototype.\n- Runtime/crop: usually 9:16; 6-15 seconds for hooks, 15-45 for ads.\n- Source media: portrait, product image/video, logo, b-roll, audio.\n- Claims: proof supplied, disclaimers, banned phrases.\n\n## Script Shape\n\n1. Hook: concrete tension, result, objection, or curiosity.\n2. Context: why the speaker cares.\n3. Product moment: visible use, demo, or comparison.\n4. Proof: supplied metric, visible result, or sensory detail.\n5. Turn: objection answered or before-after.\n6. Close: soft CTA or final product frame.\n\nAvoid fake testimonials and unsupported medical, financial, or performance\nclaims.\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- First 1-2 seconds have a clear hook.\n- Spoken script fits runtime.\n- Mouth motion is synced for speaking faces.\n- Product/logo/packaging stay stable.\n- Captions/text are not hallucinated inside the video.\n- Claims are user-supplied or phrased as visible observations.\n"
Full snapshot data
{
  "description": "Plan and produce UGC-style creator ads and social videos with fal.ai. Use for direct-to-camera creator scripts, talking-head ads, product demos, testimonials, founder clips, unboxing, reactions, before-after, faceless voiceover, and short vertical social videos.\n",
  "included_files": [],
  "name": "ugc",
  "skill_md_contents": "---\nname: ugc\ndescription: >\n  Plan and produce UGC-style creator ads and social videos with fal.ai. Use for\n  direct-to-camera creator scripts, talking-head ads, product demos,\n  testimonials, founder clips, unboxing, reactions, before-after, faceless\n  voiceover, and short vertical social videos.\n---\n\n# UGC Production\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 creator-style content instead of polished studio ads.\nExecution runs through fal.ai MCP tools.\n\n## Inputs To Collect\n\n- Product or offer.\n- Format: direct-to-camera, demo, reaction, unboxing, founder, faceless b-roll.\n- Speaker: supplied portrait/video, generated avatar, no face, or voiceover.\n- Script source: exact script, bullets, offer copy, or ask to draft.\n- Platform: TikTok, Reels, Shorts, paid social, landing page, prototype.\n- Runtime/crop: usually 9:16; 6-15 seconds for hooks, 15-45 for ads.\n- Source media: portrait, product image/video, logo, b-roll, audio.\n- Claims: proof supplied, disclaimers, banned phrases.\n\n## Script Shape\n\n1. Hook: concrete tension, result, objection, or curiosity.\n2. Context: why the speaker cares.\n3. Product moment: visible use, demo, or comparison.\n4. Proof: supplied metric, visible result, or sensory detail.\n5. Turn: objection answered or before-after.\n6. Close: soft CTA or final product frame.\n\nAvoid fake testimonials and unsupported medical, financial, or performance\nclaims.\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- First 1-2 seconds have a clear hook.\n- Spoken script fits runtime.\n- Mouth motion is synced for speaking faces.\n- Product/logo/packaging stay stable.\n- Captions/text are not hallucinated inside the video.\n- Claims are user-supplied or phrased as visible observations.\n"
}

SHA-256 of public snapshot: f88e1adb5fe0837380be2272b7051165f804d2814751744c43feda568d2d95d5