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 AIDotNet/OpenCowork --skill creative-production-ads-explorergit clone --depth 1 https://github.com/AIDotNet/OpenCoworkWrote 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/aidotnet/opencowork/creative-production-ads-explorer)<a href="https://agentmods.dev/skills/aidotnet/opencowork/creative-production-ads-explorer"><img src="https://agentmods.dev/badge/skills/aidotnet/opencowork/creative-production-ads-explorer/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/aidotnet/opencowork/creative-production-ads-explorer"><img src="https://agentmods.dev/badge/skills/aidotnet/opencowork/creative-production-ads-explorer.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 | $0.00061 | $0.01421 |
| Opus 5 | $0.00030 | $0.00711 |
| Sonnet 5 | $0.00012 | $0.00284 |
| Haiku 4.5 | $0.00006 | $0.00142 |
Grade A, and why
creative-production-ads-explorer 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 10d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ads Explorer
Use this skill when the user wants to see many different image-ad directions from one subject anchor: product reference image, packaging, service, venue, app, campaign offer, or business asset.
This is the Explore-stage owner for ad-format diversity. It is intentionally broader than scene-explorer and more ad-specific than offer-explorer.
Read references/experience-contract.md before writing the user-facing handoff.
Read references/artifact-contracts.md before creating, repairing, or reporting artifacts.
Read references/codex-exec-image-generation.md before running image generation.
Read references/image-building-strategy.md alongside the Codex exec contract for first-pass imagery rules.
Pipeline Role
Use ads-explorer when the request is about ad formats, campaign images, paid social ideas, launch ads, proof-led ads, ecommerce ads, OOH mockups, UGC thumbnails, surreal product posters, or a visual wall of ad directions.
Use scene-explorer first when the main question is where the product should appear in the real world.
After the review wall, keep more versions in the same mood-board surface. Use tile-level Remix controls, item remixSuggestions, or follow-up generation for controlled changes such as different character, scene, copy, format, crop, style, palette, camera, props, or product placement, then append new results to the saved board.
Default Library
Use the checked-in packs under assets/image-ad-library/packs/.
The default diverse-image-ad-archetypes pack contains 25 reusable starter ad families. The number describes starter directions in the pack, not a required mood-board tile count. It declares:
- per-family prompt structure;
- per-family image size where a non-square crop is better;
- review-wall behavior with captions suppressed;
- copy safety rules for exact headline, CTA, claims, proof, and placeholder text.
Use --pack digital-product-core-ad-prompts for app, SaaS, AI product, marketplace, commerce, developer-tool, or other software-product ads where the interface should be the product proof.
What ships with it
10 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.
- assets/image-ad-library/packs/digital-product-core-ad-prompts.json 28 KB
- assets/image-ad-library/packs/diverse-image-ad-archetypes.json 63 KB
- assets/image-ad-library/README.md 2.5 KB
- assets/image-ad-library/registry-index.json 841 B
- references/artifact-contracts.md 9.6 KB
- references/codex-exec-image-generation.md 6.0 KB
- references/experience-contract.md 8.5 KB
- references/image-building-strategy.md 2.3 KB
- references/review-renderer.md 2.9 KB
- scripts/build_ads_explorer.py 4.2 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.
- 10d ago First seen · 115 lines · 61 tokens per session scan A ed274aa7bbce
creative-production-ads-explorer is a skill published in the GitHub repository AIDotNet/OpenCowork (635 stars, last pushed 7d ago), licensed Apache-2.0. It adds 61 tokens to every session and 1,421 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.