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-finished-adgit 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-finished-ad)<a href="https://agentmods.dev/skills/gooseworks-ai/goose-skills/review-finished-ad"><img src="https://agentmods.dev/badge/skills/gooseworks-ai/goose-skills/review-finished-ad/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-finished-ad"><img src="https://agentmods.dev/badge/skills/gooseworks-ai/goose-skills/review-finished-ad.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00200 | $0.03231 |
| Opus 5.5 | $0.00080 | $0.01292 |
| Sonnet 5.5 | $0.00040 | $0.00646 |
| Haiku 4.5 | $0.00020 | $0.00323 |
Grade A, and why
review-finished-ad 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 4d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Superseded: the video kit now does this with the check-layer part, version 1.2.0, in the parts folder of this repository. It runs the machine checks every finished video gets: it plays, length, size, sound level, captions, black and frozen frames and the end card. This atom stays, unchanged in behaviour, for skills outside the kit until they move; its scripts still run.
review-finished-ad
The gate between a rendered master and the user. A finished ad has to look like the brand's ad and play like an ad, not like a pile of clips. This skill checks both, fixes are made by the caller, and the gate is re-run until it passes.
Run it
Needs ffmpeg + ffprobe on PATH and pip install --quiet numpy pillow.
python3 scripts/review_finished_ad.py \
--video working/final.mp4 \
--json working/review/finished-ad.json \
--sheet working/review/finished-ad-sheet.png \
--logo working/brand/logo.png \
--palette "#0b3d2e,#f4efe6" \
--product-images working/brand/product-1.png,working/brand/product-2.png \
--font working/brand/font.ttf --brand-name "Acme"
--logois the logo file the video actually composites: the kit'slogoUrl/logos[0], or the wordmark file the recipe's end card uses. PNG, JPEG or SVG (an SVG is rasterised withcairosvgorrsvg-convert). Never a generated logo.- No logo image in the video (the brand name set as text in the brand font, because the
kit only has a favicon or no logo): omit
--logo, and judge the text wordmark on the sheet. --endcard-sis the end card's length (default 3.0). Set it to the real length: a longer silent or static end card would otherwise read as dead air or a freeze.--logo-at 3.2(repeatable) adds a timestamp where the logo also appears mid-video; the end card (last ~1.6s) is always checked.--no-speechfor formats with no voiceover or dialogue (music-only), so silence is not judged.--format-profile silent-textfor a declared silent, text-led format (kinetic text). Use it only when the recipe names it. It implies--no-speechand changes three checks (see "Silent-text profile" below); every other check stays the same.--expect-sizedefaults to1080x1920. Video ads are always 9:16.
What ships with it
6 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.
- 4d ago Changed · +37 lines 601fd742ad31
- 6d ago Changed e78075d78279
- 8d ago Changed · +4 lines add4912ce985
- 9d ago Changed · +24 lines · +32 tokens per session e2bf78eb24a1
- 10d ago Changed · +6 lines e67f8f1f3711
- 15d ago Changed · +168 tokens per session 1f84e7f52426
- 16d ago First seen · 99 lines · 0 tokens per session scan A a898745f1e17
review-finished-ad is a skill published in the GitHub repository gooseworks-ai/goose-skills (1,254 stars, last pushed today), licensed MIT. It adds 200 tokens to every session and 3,231 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-10-01.
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.
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.
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…
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…