Skip to content
cccskills
FreePublished on GitHub

ugc-fixloop

Repair a specific beat or time window in a single-take UGC video while keeping its original audio continuous, and request a second-model review of a Seedance prompt before rendering. It provides deterministic FFmpeg stitching and a structured prompt review.

OriginalShow the original description

the UGC fix-loop toolkit — surgically re-render a bad window/beat of a single-take UGC master (stitch_replacement.py, pure FFmpeg) and GPT cross-model review a Seedance prompt before render (vet_seedance_prompt.py, routed through the openai-proxy). Fetch it into a one-shot UGC recipe so both scripts resolve on any machine and the vet call charged to your GooseWorks credits.

gooseworks-ai/goose-skills1,272 stars(GitHub 1,272 + cccskills 0)

Run score Not tested

See how to install

Good for

  • Replacing a flawed scene in a UGC master video
  • Reviewing a Seedance prompt before spending on a render
  • Preserving voice-over and ambience while changing video

Files included (5)

  • SKILL.md3.4 KB
  • scripts/stitch_replacement.py6.4 KB
  • scripts/vet_seedance_prompt.py5.9 KB
  • skill.meta.json221 B
  • tests/smoke-test.md1.7 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

ugc-fixloop

The UGC fix-loop toolkit. The one-shot UGC video recipes (create-ugc-*-video-from-refs) render a single continuous Seedance 2.0 reference-to-video master with native lip-synced audio. This capability ships the two scripts those recipes run, so they exist on the remote machine (fetched into /tmp/gooseworks-scripts/ugc-fixloop/).

Any re-render of a replacement clip goes through the same proxy path the recipe uses for the take (create-video-fal / fal-proxy), NEVER a direct fal.run call.

Env / deps

  • stitch_replacement.py — no API key, no network. Needs ffmpeg + ffprobe on PATH (all local FFmpeg).
  • vet_seedance_prompt.py — routes through the GooseWorks openai-proxy (<api_base>/api/internal/openai-proxy/v1/chat/completions), reading creds from ~/.gooseworks/credentials.json — no direct OpenAI call, no local key; the call charged to your GooseWorks credits. Exits 3 if the proxy/creds are unavailable so the recipe can fall back to an inline self-review (the vet is advisory, not a gate).

Run — vet_seedance_prompt.py (GPT cross-model prompt review)

A second opinion from a different model family on the Seedance prompt before you spend the render (a model reviewing its own prompt is a weaker signal). Takes the prompt as an argument:

vet_seedance_prompt.py --prompt-file working/seedance-prompt.txt \
    [--brief "one-line intent"] [--refs "@Image1=avatar; @Image2=product; @Image3=env"] \
    [--words 28] [--out working/seedance-review.md]

Prints + saves the structured review (verdict, line edits, word budget, consistency risk).

Run — stitch_replacement.py (surgical beat/window swap, deterministic)

Replaces one segment of the master on the VIDEO track only; the master's audio (VO + ambience) plays straight through, so lip-sync on talking beats is never touched. Output is re-encoded H.264 / yuv420p at the master's fps + resolution.

Required: --master M.mp4 --replacement R.mp4 --output O.mp4. Pick the window ONE of two ways:

# By beat (1-indexed segment between auto-detected scene cuts):
stitch_replacement.py --master M.mp4 --replacement R.mp4 --output O.mp4 --replace-beat 2

# By explicit window (seconds):
stitch_replacement.py --master M.mp4 --replacement R.mp4 --output O.mp4 \
    --window-start 4.21 --window-end 8.75 --fit stretch

All args:

  • --master (required) — the single-take master mp4.
  • --replacement (required) — the re-rendered silent replacement clip (generated via create-video-fal).
  • --output (required) — output mp4 path.
  • --window-start / --window-end (float seconds) — explicit hole to replace.
  • --replace-beat (int, 1-indexed) — pick the segment between detected scene cuts.
  • --scene-threshold (float, default 0.3) — scene-cut sensitivity for --replace-beat.
  • --fit {stretch,trim,freeze} (default stretch) — reconcile replacement length to the hole.
  • --dry-run — print the ffmpeg command without running.

Warns if output duration drifts >0.15s from the master (audio-sync check).

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

<slug>

FreeSummary

The supplied material contains only placeholder text for the skill’s purpose, inputs, steps, and completion criteria. It does not provide enough information to describe a task or result reliably.

  • No use case can be identified from the supplied material
  • Purpose is unspecified
  • Inputs and expected results are unspecified
gooseworks-ai/goose-skills1.3KUpdated Oct 27, 2026

ad-angle-miner

FreeSummary

Research supported advertising angles using buyer context, current product facts, customer language, and observed ads. Turn the evidence into static ad, video, or copy ideas, matching video concepts to available recipes. Scores rank ideas for testing; they do not predict results.

  • Finding evidence-backed angles for a product campaign
  • Developing static ad or video concepts from customer research
  • Writing headline and primary-text options for ads
gooseworks-ai/goose-skills1.3KUpdated Oct 27, 2026

Analyze campaign data from Google, Meta, and LinkedIn to find strong and wasteful spend. The skill checks funnel performance and test results, then recommends which campaigns to pause, scale, or test and how to shift budget across channels.

  • Finding campaigns and ads that waste budget
  • Comparing performance across Google, Meta, and LinkedIn
  • Planning specific budget shifts and follow-up tests
gooseworks-ai/goose-skills1.3KUpdated Oct 27, 2026

Compare ad spend and signups with downstream outcomes to calculate the cost of each qualified lead. The skill checks tracking coverage, accounts for how long leads need to mature, and groups creatives into actionable categories with confidence notes.

  • Compare true qualified-lead costs across creatives
  • Find low-CPA ads that bring poor-quality leads
  • Check whether signups can be linked to downstream outcomes
gooseworks-ai/goose-skills1.3KUpdated Oct 27, 2026

Prepare the intake for a Meta ad campaign by reviewing available brand information first, stating reasonable assumptions, and asking only questions whose answers could affect budget, claims, or legal exposure. It records stable brand facts, a campaign brief, and what was asked versus assumed.

  • Prepare a Meta ad campaign when brand facts are missing
  • Clarify budget and timing before campaign planning
  • Record approved claims and audience restrictions
gooseworks-ai/goose-skills1.3KUpdated Oct 27, 2026

ad-policy-check

FreeSummary

Review ad copy, image text, visuals, and people against platform and brand category rules. It suggests honest fixes and needed disclosures, then flags issues requiring human or legal review, with a separate result for each ad and platform.

  • Checking ad copy and visuals before launch
  • Reviewing creator ads for required disclosures
  • Fixing a platform disapproval and recording the issue
gooseworks-ai/goose-skills1.3KUpdated Oct 27, 2026

See all skills by gooseworks-ai

Report a problem with this skill