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 meta-ad-policy-checkergit 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/meta-ad-policy-checker)<a href="https://agentmods.dev/skills/gooseworks-ai/goose-skills/meta-ad-policy-checker"><img src="https://agentmods.dev/badge/skills/gooseworks-ai/goose-skills/meta-ad-policy-checker/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/meta-ad-policy-checker"><img src="https://agentmods.dev/badge/skills/gooseworks-ai/goose-skills/meta-ad-policy-checker.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 | $0.00052 | $0.02794 |
| Opus 5.5 | $0.00021 | $0.01118 |
| Sonnet 5.5 | $0.00010 | $0.00559 |
| Haiku 4.5 | $0.00005 | $0.00279 |
Grade A, and why
meta-ad-policy-checker 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 2d 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta Ad Policy Checker
Meta disapproves ads for policy reasons constantly, and most disapprovals are preventable. The pattern is almost always the same: an advertiser (or an AI agent generating variants) writes copy that uses a phrase or implies a claim that violates Meta's published advertising standards. The fix is cheap if you catch it before submission, expensive if you don't — repeated disapprovals on the same account can throttle delivery or trigger account-level restrictions.
This skill is a pre-flight check. It reads ad copy, figures out which Meta policies apply, fetches the live policy text from Meta's transparency center, and returns a clear verdict with specific findings, citations, and rewrites. It does not hardcode policy rules — Meta updates those, and a static rule list goes stale. Instead, the skill uses Meta's own canonical policy pages as ground truth on every run.
Core principle: The skill provides the methodology — what to check, how to reason, what severity to assign. Meta provides the source of truth — the actual policy text. This separation is what keeps the skill correct as Meta's standards evolve.
When to Use
- Before launching any new Meta ad
- After generating ad copy variants (call this on each variant before showing or submitting)
- When auditing an existing live ad for policy risk
- When troubleshooting a recently disapproved ad
- Before pushing copy through any Meta MCP / API write tool
Phase 0: Intake
- Advertiser context (1–2 sentences)
- What the business does
- What product / service / offer is being advertised
- Primary conversion goal
- Ad asset(s)
- Headline(s)
- Primary text / body
- Description (if applicable)
- CTA button text
- Destination URL (optional — enables a landing-page cross-check)
- Special Ad Category — declared by user:
None/Employment/Credit/Housing/Social Issues, Elections or Politics(this changes the applicable rules significantly) - Targeting summary (optional) — useful for discrimination checks (age, gender, location exclusions)
- Visual description (optional) — text-in-image is policy-relevant
- Mode —
pre-flight(block until clean) oraudit(flag-only, used for already-live ads)
What ships with it
1 file 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.
- 2d ago Changed · -1 lines b4628f6544e6
- 1mo ago Changed 3612ade71c8a
- 1mo ago First seen · 205 lines · 52 tokens per session scan A 2777e69baa43
meta-ad-policy-checker is a skill published in the GitHub repository gooseworks-ai/goose-skills (1,271 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 2,794 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…