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 render-cartoon-music-videogit 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/render-cartoon-music-video)<a href="https://agentmods.dev/skills/gooseworks-ai/goose-skills/render-cartoon-music-video"><img src="https://agentmods.dev/badge/skills/gooseworks-ai/goose-skills/render-cartoon-music-video/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/render-cartoon-music-video"><img src="https://agentmods.dev/badge/skills/gooseworks-ai/goose-skills/render-cartoon-music-video.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 | $0.00218 | $0.01401 |
| Opus 5 | $0.00109 | $0.00700 |
| Sonnet 5 | $0.00044 | $0.00280 |
| Haiku 4.5 | $0.00022 | $0.00140 |
Grade A, and why
render-cartoon-music-video 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 13d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
render-cartoon-music-video
Assemble a cartoon music-video ad from a config: an animated / illustrated / hand-crafted story (stop-motion felt-and-foam, claymation, 2D toon, cut-out) where a sung song is the entire script and one recurring animated character carries every shot, cut to the bar with the climax line on the drop. This capability is the FREE, deterministic assembly — cut-to-bar, hard-concat, the logo bug + captions burn, and the solid-color end card.
scripts/config.example.json is the worked example (Coinbase "Bet on anything", ~55s 1080×1920
9:16, 16 body bars + a 3s end card); scripts/PIPELINE.md maps every config block to its source
step and scripts/README.md documents the free assembly.
Run
This is the FREE, deterministic assembly stage — it spends nothing. The paid inputs are
separate capabilities: the sung song (create-music-elevenlabs, or a user-supplied mp3 + Whisper
word timings) beat-tracked with librosa so the BAR GRID sets the timeline; one locked recurring
character + one keyframe per bar in one look pack (create-image-fal, Nano Banana); and one
Seedance i2v clip per bar (create-video-fal). Given the song + word-timestamps.json +
bars.json + one clip per bar + the brand wordmark SVG, render-cartoon-music-video cuts each
clip to its bar window, hard-concats on the bar, burns the logo bug + captions, appends the
solid-color end card, and muxes the song under it → the master. Re-cuts reuse the existing song /
keyframes / clips and cost $0.
Contract (the free assembly)
- The sung song carries the narrative — no separate VO. The generated/supplied track IS the bed (no VO to duck under); do not add a spoken voiceover or a second bed.
- Plan the timeline AROUND the delivered song's BAR GRID. Beat-track the song with librosa (assume 4/4); one bar = one shot (default). Snap every tableau window to the bar boundaries — never trim the song to a pre-planned grid.
- Captions from the song's word timings, re-spelled against the locked lyrics. Whisper
mishears shouted accents ("BETS" → "Hearts"); re-spell the timed tokens against the locked
lyric file (never edit lyrics to match Whisper). VEED-whisper white bold sans in the
BOTTOM third (Alignment 2,
margin_vabove the bottom-left logo bug), ~4–5 words per cue, NO background pill; captions STOP at the end-card boundary. Never mid-frame — it covers the character (fixed 2026-07). If the host ffmpeg lacks libass, render the cues as timed PIL PNG overlays (ffmpegoverlay=…:enable='between(t,st,en)') at the same bottom placement. - Land the climax line on the drop. The climax tableau is timed so the payoff line sits on the sub-bass drop; accent that line.
- Persistent logo bug, suppressed on the end card. Burn a white brand wordmark bottom-left over the body bars (cairosvg → PIL from the real SVG), suppressed on the end card where the big wordmark dominates.
- End card via cairosvg + PIL from the real wordmark — never AI-render brand text. Solid brand-color card + white wordmark + subhead, holding ~3s WITH the song still playing under it (afade-out over the tail — no silent tail). A diffusion model garbles a wordmark.
- FFmpeg composite, deterministic, FREE. Cut each clip to its bar window, hard-concat, burn
the logo bug + captions, append the end card, mux the song over the whole video with a 0.5s
afade tail,
loudnorm I=-14→ a 1080×1920 h264+aac master. No paid calls, no keys. When the host ffmpeg lacks libass/drawtext, BOTH the captions and the logo bug are timed PIL PNG overlays (overlay=x:y:enable='between(t,st,en)'), not an ASS burn. - QC PER SCENE, never just the master — the two failure modes are content, not assembly. The upstream keyframe/i2v steps can (a) drift the character felt → smooth-3D "man" partway through and (b) hallucinate hands — realistic fingers in a hand macro, a pointing finger on a "tap the phone" shot, or a disembodied hand sliding in from the frame edge. Both hide at thumbnail size. Extract a 2 fps contact sheet + a per-bar FACE crop and HAND crop (across each clip's full duration), confirm every bar is matte felt with the ONE character and no human/floating hands, and re-check the served bytes after publish. A drifted bar means regenerating that bar's KEYFRAME (not re-cutting) — see the recipe STEP 3/6.
What ships with it
5 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.
- 13d ago First seen · 66 lines · 218 tokens per session scan A 8f63a0a40329
render-cartoon-music-video is a skill published in the GitHub repository gooseworks-ai/goose-skills (1,202 stars, last pushed 11d ago), licensed MIT. It adds 218 tokens to every session and 1,401 once invoked, about $0.0011 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 2026-08-30.
Other skills, from other repositories
excalidraw-ai
Create professional Excalidraw diagrams by generating JSON directly. This skill provides the Excalidraw JSON schema reference and professional icon libraries for AI agents to autonomously create diagrams without templates.
error-handling
Python error handling patterns for FastAPI, Pydantic, and asyncio. Follows "Let it crash" philosophy - raise exceptions, catch at boundaries. Covers HTTPException, global exception handlers, validation errors, background task failures. Use when: (1) Designing API error responses, (2) Handling RequestValidationError…
linting
Python linting with Ruff - an extremely fast linter written in Rust. Use when: (1) Standardizing code quality, (2) Fixing style warnings, (3) Enforcing rules in CI, (4) Replacing flake8/isort/pyupgrade/autoflake, (5) Configuring lint rules and suppressions.
logfire
Structured observability with Pydantic Logfire and OpenTelemetry. Use when: (1) Adding traces/logs to Python APIs, (2) Instrumenting FastAPI, HTTPX, SQLAlchemy, or LLMs, (3) Setting up service metadata, (4) Configuring sampling or scrubbing sensitive data, (5) Testing observability code.
commit-message
Analyze git changes and generate conventional commit messages. Supports batch commits for multiple unrelated changes. Use when: (1) Creating git commits, (2) Reviewing staged changes, (3) Splitting large changesets into logical commits.
python-backend
Python backend development expertise for FastAPI, security patterns, database operations, Upstash integrations, and code quality. Use when: (1) Building REST APIs with FastAPI, (2) Implementing JWT/OAuth2 authentication, (3) Setting up SQLAlchemy/async databases, (4) Integrating Redis/Upstash caching, (5) Refactoring…