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-exploregit 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-explore)<a href="https://agentmods.dev/skills/aidotnet/opencowork/creative-production-explore"><img src="https://agentmods.dev/badge/skills/aidotnet/opencowork/creative-production-explore.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 70 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00045 | $0.02723 |
| Opus 5 | $0.00023 | $0.01362 |
| Sonnet 5 | $0.00009 | $0.00545 |
| Haiku 4.5 | $0.00005 | $0.00272 |
Grade A, and why
creative-production-explore 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 8d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explore
Render the main Explore-stage decision surface for open-ended Creative Production requests.
This skill does not generate the board, assets, or final creative itself. It turns a broad business visual intent into a small set of concrete paths the user can choose from.
Read references/experience-contract.md when writing the chat handoff around Explore.
Read references/artifact-contracts.md before routing into artifact-producing paths or reporting existing artifacts.
Read references/codex-exec-image-generation.md before routing the user into any path that may generate images.
Role In The Journey
Use this as the front door when the user has supplied a business context and wants to explore what to do next.
The visible surface is named Explore.
It should feel like a compact creative path chooser, not a library, review queue, dashboard, or quality-control surface.
Treat the choices as a scale of creative commitment:
- audience and positioning;
- broad visual feeling;
- product or service in context;
- offers;
- ad directions;
- camera shots;
- logos;
- assets.
The conversation should carry that scale in plain creative language. The mood-board empty-state surface stays compact and clickable.
Generation Setup
Image generation uses Codex exec fanout through references/codex-exec-image-generation.md. The Explore chooser should still be usable before generation; generation-heavy paths should hand off to their focused skill, which owns the worker batch and review surface.
Required Paths
Use these candidate paths as the complete Explore vocabulary:
- Positioning: opens
positioning-explorerto clarify audience, occasion, growth goal, proof, and exclusions before visual generation. - Mood boards: opens
moodboard-explorerfor image-first mood, visual territories, audience feel, and creative references. - Scenes: opens
scene-explorerwhen the user wants to see the offer, venue, service, or product in realistic contexts. Use the scene library for point-of-sale, customer, retail, venue, consultation, demo, and handoff environments. - Offers: opens
offer-explorerwhen the user wants to test a product, service, venue, or experience across structured prompt families and review galleries. - Ads: opens
ads-explorerwhen the user wants ad directions, paid social ideas, display formats, ecommerce product ads, OOH mockups, UGC thumbnails, or an image-led creative review. - Shots: opens
shot-explorerwhen the user has a visual anchor and wants alternate camera angles, crops, pans, zooms, macro details, or product-view options before polish. - Logos: opens
logo-explorerwhen the user wants brand marks, wordmarks, lockups, or identity-system concepts. - Assets: opens the Build stage only when the user has enough context to produce real outputs or choose a known asset family. Prefer a strong focused skill when one applies:
ads-explorerfor ad directions,moodboard-explorerfor visual territories and board-level remixing,logo-explorerfor identity,offer-explorerfor landing-page hero or web-module variation exploration, andgenerative-polishfor selected fixed-size publishable image assets. Do not use Assets as a catch-all planning board when a focused skill can create the next visible result.
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.
- 8d ago First seen · 183 lines · 45 tokens per session scan A a91914424cb1
creative-production-explore is a skill published in the GitHub repository AIDotNet/OpenCowork (634 stars, last pushed 5d ago), licensed Apache-2.0. It adds 45 tokens to every session and 2,723 once invoked, about $0.0002 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.