Goose Skills is a library of workflows and data APIs that lets coding agents handle growth and go-to-market work such as advertising, social media, content, SEO, lead generation, and customer research. It is intended for teams using Claude Code, Cursor, Codex, and similar agents. The catalogue entries are its reusable skills.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add gooseworks-ai/goose-skills --skill review-ugc-rendergit clone --depth 1 https://github.com/gooseworks-ai/goose-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/gooseworks-ai/goose-skills/review-ugc-render)<a href="https://agentmods.dev/skills/gooseworks-ai/goose-skills/review-ugc-render"><img src="https://agentmods.dev/badge/skills/gooseworks-ai/goose-skills/review-ugc-render/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gooseworks-ai/goose-skills/review-ugc-render"><img src="https://agentmods.dev/badge/skills/gooseworks-ai/goose-skills/review-ugc-render.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00116 | $0.01179 |
| Opus 5 | $0.00058 | $0.00589 |
| Sonnet 5 | $0.00023 | $0.00236 |
| Haiku 4.5 | $0.00012 | $0.00118 |
Grade A, and why
review-ugc-render scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
review-ugc-render
The QC gate every UGC video recipe MUST clear before it publishes. Not an eyeball
/watch— a deterministic transcript-vs-script diff that exits non-zero on a defect so the recipe can hard-stopset_final_render.
Why this exists
Seedance generates the audio natively. It sometimes mis-voices a word — the
approved line human-vetted comes back spoken as human witted; documented
siblings: Hume→Hune, Alitu→al-too. The defect lives in the render's
audio, so an eyeball /watch ("dialogue matches the script") slips it through,
and a downstream caption pass then bakes the wrong word in verbatim. Nothing was
comparing the actual spoken audio against the script the user approved.
This gate does exactly that, deterministically, and refuses to publish on a miss.
When to run
- MANDATORY in every
remix-ugc-*-from-sampleandcreate-ugc-*-video-from-refsrecipe, in the QC phase, after the master render exists and beforeset_final_render. - Re-run after every fix / re-roll until it PASSES.
Contract
Before rendering, persist the exact approved spoken lines (the verbatim utterance,
no beat notes) to working/approved-script.txt. Then, after render:
python3 <pack>/review-ugc-render/scripts/review_render.py \
--video working/final.mp4 \
--script-file working/approved-script.txt \
--json working/review-verdict.json
- exit 0 → PASS — proceed to publish (
set_final_render). - exit 2 → FAIL — do NOT publish. Read the report, fix, re-run.
- exit 3 → ERROR — the check could not run (see below); fix the environment, do not publish blind.
Transcription backend (in priority order): OPENAI_API_KEY (honors
OPENAI_BASE_URL, so it routes through the gooseworks Whisper proxy when set) →
local whisper CLI. ffmpeg must be on PATH.
What FAIL means and how to fix
| Report line | Root cause | Fix |
|---|---|---|
[high] said [witted] where script has [vetted] |
Seedance mis-voiced the word in the generated audio | Re-roll a new seed. If it is a brand/coined token, spell it phonetically in the SPOKEN LINE (e.g. Ali-too, never a (pronounced …) parenthetical — Seedance reads parentheticals aloud). See create-video-seedance-2-fal Failure Modes. |
[medium] dropped [...] / low similarity |
Seedance dropped an approved phrase | Re-roll; if only a tail word, a surgical stitch_replacement.py window fix may recover it. |
⚠ audio is effectively silent |
Wrong render / audio track lost in post | Re-render / re-check the mux; never publish a silent take. |
ERROR: no transcription backend |
No OPENAI_API_KEY and no local whisper |
Set the key (proxy OPENAI_BASE_URL) or install whisper, then re-run. |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 93 lines · 116 tokens per session scan A b5f5b014adfe
review-ugc-render is a skill published in the GitHub repository gooseworks-ai/goose-skills (1,202 stars, last pushed 11d ago), licensed MIT. It adds 116 tokens to every session and 1,179 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
laravel-testing
Use when testing controllers, services, or models, or implementing TDD on Laravel 13 with Pest 4 / PHPUnit 12.
react-testing
Testing Library for React 19 - render, screen, userEvent, waitFor, Suspense. Use when writing tests for React components with Vitest.
php-testing
Use when writing/configuring tests on a non-Laravel PHP project — PHPUnit vs Pest. Do NOT use for Laravel test helpers or quality tooling (php-quality-tooling).
rust-testing-quality
Use when writing, organizing, or running Rust tests — unit, integration, doc-tests, proptest, criterion benchmarks, or cargo-mutants. Not for CI pipeline wiring (rust-tooling-cicd).
go-testing-quality
Use when writing or reviewing Go tests, adding coverage, benchmarking, or profiling a Go program. Not for CI/lint wiring (go-tooling-security) or non-Go tests.
Unit Test Improver
Reviews existing unit tests for gaps, weak assertions, and missing edge cases, then rewrites them to be more robust.