← 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 marketing

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 - Exact copy/key art: `openai/gpt-image-2`. - Premium stills: `openai/gpt-image-2`, `fal-ai/nano-banana-pro`, `fal-ai/nano-banana-2`. - Edits from product/logo/UI: `fal-ai/nano-banana-pro/edit`, `openai/gpt-image-2/e...

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 @@
 
 # Marketing 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 a campaign system rather than one isolated asset.
 Execution runs through fal.ai MCP tools.
 
@@ -46,16 +50,13 @@
 6. Variation axis.
 7. Guardrails: no fake claims, extra logos, distorted UI, or fake proof.
 
-## Model Choices
+## Model selection
 
-- Exact copy/key art: `openai/gpt-image-2`.
-- Premium stills: `openai/gpt-image-2`, `fal-ai/nano-banana-pro`,
-  `fal-ai/nano-banana-2`.
-- Edits from product/logo/UI: `fal-ai/nano-banana-pro/edit`,
-  `openai/gpt-image-2/edit`.
-- Product/social video: Seedance 2.0 image-to-video or text-to-video.
-- Creator ad: `veed/fabric-1.0`, `veed/fabric-1.0/text`, or
-  `fal-ai/creatify/aurora`.
+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: marketing\ndescription: >\n  Plan campaign-level marketing asset production with fal.ai. Use for launch\n  kits, campaign matrices, paid social variants, landing-page visuals, email\n  and banner imagery, hook/proof/conversion assets, and creator ad packages.\n---\n\n# Marketing Production\n\nUse when the user wants a campaign system rather than one isolated asset.\nExecution runs through fal.ai MCP tools.\n\nLoad `commercial` for product-specific assets and `ugc` for creator-style ads.\n\n## Inputs To Collect\n\n- Objective: launch, acquisition, retargeting, education, event, activation.\n- Audience: persona, market, use case, awareness level, objections.\n- Offer: product, feature, bundle, trial, waitlist, event, promotion.\n- Channels: paid social, organic, landing page, email, display, app.\n- Required assets: stills, videos, thumbnails, hero image, carousel, banner.\n- Brand rules: colors, logo, typography, tone, taboo visuals, competitors.\n- Claims: exact approved copy, proof points, disclaimers, compliance limits.\n\n## Campaign Matrix\n\nCreate a compact matrix before generation:\n\n- Hook asset: first-frame attention.\n- Proof asset: product, process, visible result, or supplied evidence.\n- Context asset: audience use case.\n- Conversion asset: clean end frame or layout-safe visual.\n- Retention/reminder asset: variation for later touchpoints.\n\nEach asset needs role, channel, crop, format, model route, prompt summary, and\nguardrails.\n\n## Prompt Order\n\n1. Asset role and channel.\n2. Product or subject invariant.\n3. Audience context and use case.\n4. Visual system: camera, lighting, composition, color, motion.\n5. Copy handling: no generated text, safe space, or exact provided wording.\n6. Variation axis.\n7. Guardrails: no fake claims, extra logos, distorted UI, or fake proof.\n\n## Model Choices\n\n- Exact copy/key art: `openai/gpt-image-2`.\n- Premium stills: `openai/gpt-image-2`, `fal-ai/nano-banana-pro`,\n  `fal-ai/nano-banana-2`.\n- Edits from product/logo/UI: `fal-ai/nano-banana-pro/edit`,\n  `openai/gpt-image-2/edit`.\n- Product/social video: Seedance 2.0 image-to-video or text-to-video.\n- Creator ad: `veed/fabric-1.0`, `veed/fabric-1.0/text`, or\n  `fal-ai/creatify/aurora`.\n\n## Quality Bar\n\n- Every asset maps to a campaign role and channel.\n- Claims are supplied, observable, or removed.\n- Variants differ by one clear axis.\n- Safe zones work for platform UI and external overlays.\n- Final answer includes a campaign manifest and defects.\n"
AFTER
"---\nname: marketing\ndescription: >\n  Plan campaign-level marketing asset production with fal.ai. Use for launch\n  kits, campaign matrices, paid social variants, landing-page visuals, email\n  and banner imagery, hook/proof/conversion assets, and creator ad packages.\n---\n\n# Marketing 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 a campaign system rather than one isolated asset.\nExecution runs through fal.ai MCP tools.\n\nLoad `commercial` for product-specific assets and `ugc` for creator-style ads.\n\n## Inputs To Collect\n\n- Objective: launch, acquisition, retargeting, education, event, activation.\n- Audience: persona, market, use case, awareness level, objections.\n- Offer: product, feature, bundle, trial, waitlist, event, promotion.\n- Channels: paid social, organic, landing page, email, display, app.\n- Required assets: stills, videos, thumbnails, hero image, carousel, banner.\n- Brand rules: colors, logo, typography, tone, taboo visuals, competitors.\n- Claims: exact approved copy, proof points, disclaimers, compliance limits.\n\n## Campaign Matrix\n\nCreate a compact matrix before generation:\n\n- Hook asset: first-frame attention.\n- Proof asset: product, process, visible result, or supplied evidence.\n- Context asset: audience use case.\n- Conversion asset: clean end frame or layout-safe visual.\n- Retention/reminder asset: variation for later touchpoints.\n\nEach asset needs role, channel, crop, format, model route, prompt summary, and\nguardrails.\n\n## Prompt Order\n\n1. Asset role and channel.\n2. Product or subject invariant.\n3. Audience context and use case.\n4. Visual system: camera, lighting, composition, color, motion.\n5. Copy handling: no generated text, safe space, or exact provided wording.\n6. Variation axis.\n7. Guardrails: no fake claims, extra logos, distorted UI, or fake proof.\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 asset maps to a campaign role and channel.\n- Claims are supplied, observable, or removed.\n- Variants differ by one clear axis.\n- Safe zones work for platform UI and external overlays.\n- Final answer includes a campaign manifest and defects.\n"
Full snapshot data
{
  "description": "Plan campaign-level marketing asset production with fal.ai. Use for launch kits, campaign matrices, paid social variants, landing-page visuals, email and banner imagery, hook/proof/conversion assets, and creator ad packages.\n",
  "included_files": [],
  "name": "marketing",
  "skill_md_contents": "---\nname: marketing\ndescription: >\n  Plan campaign-level marketing asset production with fal.ai. Use for launch\n  kits, campaign matrices, paid social variants, landing-page visuals, email\n  and banner imagery, hook/proof/conversion assets, and creator ad packages.\n---\n\n# Marketing 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 a campaign system rather than one isolated asset.\nExecution runs through fal.ai MCP tools.\n\nLoad `commercial` for product-specific assets and `ugc` for creator-style ads.\n\n## Inputs To Collect\n\n- Objective: launch, acquisition, retargeting, education, event, activation.\n- Audience: persona, market, use case, awareness level, objections.\n- Offer: product, feature, bundle, trial, waitlist, event, promotion.\n- Channels: paid social, organic, landing page, email, display, app.\n- Required assets: stills, videos, thumbnails, hero image, carousel, banner.\n- Brand rules: colors, logo, typography, tone, taboo visuals, competitors.\n- Claims: exact approved copy, proof points, disclaimers, compliance limits.\n\n## Campaign Matrix\n\nCreate a compact matrix before generation:\n\n- Hook asset: first-frame attention.\n- Proof asset: product, process, visible result, or supplied evidence.\n- Context asset: audience use case.\n- Conversion asset: clean end frame or layout-safe visual.\n- Retention/reminder asset: variation for later touchpoints.\n\nEach asset needs role, channel, crop, format, model route, prompt summary, and\nguardrails.\n\n## Prompt Order\n\n1. Asset role and channel.\n2. Product or subject invariant.\n3. Audience context and use case.\n4. Visual system: camera, lighting, composition, color, motion.\n5. Copy handling: no generated text, safe space, or exact provided wording.\n6. Variation axis.\n7. Guardrails: no fake claims, extra logos, distorted UI, or fake proof.\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 asset maps to a campaign role and channel.\n- Claims are supplied, observable, or removed.\n- Variants differ by one clear axis.\n- Safe zones work for platform UI and external overlays.\n- Final answer includes a campaign manifest and defects.\n"
}

SHA-256 of public snapshot: 137f470bf975eaec897616a952b0b20ef628614efa8612615a36cdcc2beeab6c