AI Marketing Skills is a collection of open-source workflows that help AI coding agents handle marketing and sales work, including growth experiments, pipeline management, content operations, outbound outreach, SEO, and finance analysis. It is intended for marketing and sales teams that want reusable agent-driven processes. The catalogue entries package these workflows as skills for compatible coding agents.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ericosiu/ai-marketing-skillsnpx agentmods add skills/ericosiu/ai-marketing-skills/packaging-youtube-thumbnailsWrote 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/ericosiu/ai-marketing-skills/packaging-youtube-thumbnails)<a href="https://agentmods.dev/skills/ericosiu/ai-marketing-skills/packaging-youtube-thumbnails"><img src="https://agentmods.dev/badge/skills/ericosiu/ai-marketing-skills/packaging-youtube-thumbnails/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/ericosiu/ai-marketing-skills/packaging-youtube-thumbnails"><img src="https://agentmods.dev/badge/skills/ericosiu/ai-marketing-skills/packaging-youtube-thumbnails.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 | $0.00054 | $0.02953 |
| Opus 5 | $0.00027 | $0.01477 |
| Sonnet 5 | $0.00011 | $0.00591 |
| Haiku 4.5 | $0.00005 | $0.00295 |
Grade A, and why
packaging-youtube-thumbnails 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 7d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Packaging YouTube Thumbnails
Overview
Turn new content into differentiated packages using a saved channel profile and evidence-backed performance memory. Keep identity, episode packaging, and performance learning separate.
REQUIRED SUB-SKILL: Use imagegen for raster generation or editing when available. Otherwise return production-ready briefs and state the rendering blocker.
Preamble
From the repository root, run the privacy-preserving version check and telemetry initializer when available:
python3 telemetry/version_check.py 2>/dev/null || true
python3 telemetry/telemetry_init.py 2>/dev/null || true
Remote telemetry is opt-in. Never log content, URLs, paths, credentials, names, business data, channel analytics, or source assets.
Resolve <skill-root> as the installed directory that contains this SKILL.md. Use that absolute directory for every bundled helper and reference. Never assume the current working directory is the skill directory.
Mode Gate
Default mode: production
Resolve the profile in order:
- a user-supplied path;
- the current project's channel profile.
If neither profile exists, switch to identity bootstrap. This public package does not bundle a creator profile, likeness, channel analytics, or approved brand assets.
When a usable profile resolves:
- Validate it with
python3 <skill-root>/scripts/thumbnail_guard.py profile --profile <profile-path>. Missing output roots or approved reference paths make the profile unusable; repair or bootstrap it instead of improvising. - Load it before developing hooks.
- Load any user-reviewed co-design calibration and approved winning references before proposing titles or visual directions.
- Do not re-audit the channel, browse its Videos grid, or rewrite the profile.
- Use its identity rules, approved references, output root, and avoid list.
- Treat the new transcript, recording, notes, brief, links, and user additions as one source pack. Latest explicit user instructions win.
- Read references/performance-learning.md. If the profile output root contains performance state, generate its preflight brief; missing state never blocks a first run.
What ships with it
12 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.
- agents/openai.yaml 391 B
- README.md 4.3 KB
- references/channel-profile-template.md 1.4 KB
- references/image-contracts.md 7.4 KB
- references/packaging-rubric.md 4.9 KB
- references/performance-learning.md 5.4 KB
- requirements.txt 17 B
- scripts/thumbnail_guard.py 11 KB runs code
- scripts/thumbnail_learning.py 24 KB runs code
- tests/test_public_package.py 678 B runs code
- tests/test_thumbnail_guard.py 9.9 KB runs code
- tests/test_thumbnail_learning.py 26 KB runs code
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.
- 7d ago First seen · 175 lines · 54 tokens per session scan A 94149b61f868
packaging-youtube-thumbnails is a skill published in the GitHub repository ericosiu/ai-marketing-skills (3,521 stars, last pushed 5d ago), licensed MIT. It adds 54 tokens to every session and 2,953 once invoked, about $0.0003 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 2026-09-05.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…