create-video-seedance-2-fal

Generate a single 4-15s vertical video clip with ByteDance Seedance 2.0 reference-to-video via fal.ai. Multi-image reference (avatar + product + setting), native lip-synced VO + ambient audio (generate-audio on by default), internal multi-cut handling within one render. Routes through the GooseWorks FAL proxy (bills the Ads agent). The default clip atom for AI-creator UGC ads built on the NB2 + Seedance architecture. Validated on beauty-by-earth/video-01.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/ads/packs/ugc-video-formats/create-video-seedance-2-fal/SKILL.md

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with strong workflow sequencing, validation checkpoints, and recovery loops appropriate to a paid batch operation. The main weakness is conciseness — repeated memory pointers and inlined date stamps add tokens that could be consolidated.

Suggestions

Consolidate the repeated per-rule 'Memory: feedback_*.md' citations into a single References subsection to cut repeated tokens.

Collect the scattered 'Validated YYYY-MM-DD' stamps into a dedicated changelog/validation-notes block (or a referenced file) rather than inlining them inline.

Move the full prompt template and/or the failure-modes table into a referenced file (e.g. prompt-example.md already cited) to tighten the SKILL.md overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and dense with genuinely non-obvious operational gotchas, but repeated 'Memory: feedback_*.md' pointers, scattered 'Validated 2026-05-23' date stamps, and a few restated rules could be tightened; time-sensitive dates are inlined rather than isolated in a deprecated section.	3 / 5
Actionability	Provides a copy-paste-ready bash invocation, the exact JSON payload the proxy submits, a full proven prompt template, and concrete per-flag guidance — fully executable across the common cases.	5 / 5
Workflow Clarity	Numbered script-behavior steps, an explicit Quality Checks checklist, a Failure Modes recovery table, and a Recovery Workflow with feedback loops (NSFW → stop and surface, never retry; timeout → recover via FAL share URL) give clear sequencing with validation checkpoints.	5 / 5
Progressive Disclosure	Well-sectioned overview that signals one-level-deep references to real bundle scripts (scripts/generate.py, scripts/media_proxy.py verified present) and to prompt-example.md plus reference runs; the full inline prompt template and large failure-mode table are content that could arguably live in separate reference files.	4 / 5
	Total	17 / 20 Passed

Description

75%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, concrete, and clearly distinct, but it omits an explicit 'Use when...' trigger clause, which the rubric caps at completeness 3. Adding a concise trigger sentence would lift the weakest dimension.

Suggestions

Append an explicit 'Use when...' clause naming the natural trigger phrases (e.g. 'Use when generating a 4-15s vertical UGC ad clip with a talking-head avatar and native lip-synced VO').

Soften model-specific jargon ('reference-to-video', 'generate-audio') with one or two plain-language synonyms a non-specialist user would actually say.

Trim internal-only context ('bills the Ads agent', 'NB2 + Seedance architecture') from the description to keep the trigger signal high.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Generate a single 4-15s vertical video clip', 'Multi-image reference (avatar + product + setting)', 'native lip-synced VO + ambient audio', 'internal multi-cut handling within one render', 'Routes through the GooseWorks FAL proxy' — with comprehensive coverage of the capability surface.	5 / 5
Completeness	The 'what' is clearly and concretely stated, but there is no explicit 'Use when...' trigger clause in the description itself — per the rubric a missing explicit trigger guidance caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural user-facing terms ('vertical video clip', 'UGC ads', 'lip-synced VO') alongside model-specific jargon ('reference-to-video', 'generate-audio'); a few common synonyms a less-technical user might say are absent.	4 / 5
Distinctiveness Conflict Risk	Names a narrow niche — ByteDance Seedance 2.0 reference-to-video via the GooseWorks FAL proxy for AI-creator UGC ads — with distinct triggers and minimal overlap risk against sibling video atoms.	5 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: gooseworks-ai/goose-skills
Path: skills/ads/packs/ugc-video-formats/create-video-seedance-2-fal/SKILL.md
Commit: 2523432

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.