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 62656456/ai-film-skills --skill web-design-directorgit clone --depth 1 https://github.com/62656456/ai-film-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/62656456/ai-film-skills/web-design-director)<a href="https://agentmods.dev/skills/62656456/ai-film-skills/web-design-director"><img src="https://agentmods.dev/badge/skills/62656456/ai-film-skills/web-design-director/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/62656456/ai-film-skills/web-design-director"><img src="https://agentmods.dev/badge/skills/62656456/ai-film-skills/web-design-director.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 | $0.00118 | $0.02579 |
| Opus 5.5 | $0.00047 | $0.01032 |
| Sonnet 5.5 | $0.00024 | $0.00516 |
| Haiku 4.5 | $0.00012 | $0.00258 |
Grade A, and why
web-design-director 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 28d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Design Director
Make the product understandable, useful, and visually specific in the actual interface. Usability means the end user can accomplish the real task with understandable, manageable effort while the interface retains its intended aesthetic quality. Direct the design and carry authorized implementation through verification. The user's taste and product priorities remain decisive; a self-review is not user acceptance.
Match the requested result
Identify the surface, deliverable, stage, and allowed changes from the user's actual intent. A GitHub repository homepage normally means its README and repository content. An existing website does not authorize a Pages redesign, a new site, or deployment. File organization, asset production, workbench status checks, and skill maintenance alone are outside this workflow. Negative mentions such as “整理资产库文件，不设计网页” must not become UI work.
Choose the appropriate mode:
- Direction: a concept, rough sketch, scheme, or comparison. Deliver at the requested fidelity; do not start production code merely to illustrate a suggestion. A rough sketch should let the user judge hierarchy before polish.
- Review: inspect the supplied page, screenshot, or code and return ranked, actionable findings. A screenshot supports visual observations; it cannot establish keyboard behavior, API results, or hidden states. Cite exact file lines when code is available; otherwise identify the visible region without inventing code locations.
- Build: create or change the requested interface, verify it, and show the result. “Help me improve this page” normally authorizes relevant, reversible changes when the target is clear. Do not repeatedly request approval for that work.
For a local correction, retain the established direction and verify the changed behavior and likely regressions. For a new product or substantial redesign, establish a compact design contract. Ask only when an unknown changes the product, deliverable, cost, or an irreversible action. Otherwise state a reasonable assumption and continue.
What ships with it
7 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.
- 28d ago Changed · +2 lines 752fbacb4e4b
- 1mo ago Changed · -22 lines · +2 tokens per session d78f9f8b00b9
- 1mo ago Changed · +4 lines · -49 tokens per session b46720444481
- 1mo ago First seen · 122 lines · 165 tokens per session scan A 229fe373fb9c
web-design-director is a skill published in the GitHub repository 62656456/ai-film-skills (92 stars, last pushed 9d ago), licensed Apache-2.0. It adds 118 tokens to every session and 2,579 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
seedance-20
This skill should be used when creating, improving, or troubleshooting Seedance 2.0 video on any surface — Dreamina, Jimeng, CapCut, Doubao, Volcengine/Ark, BytePlus, Runway's Seedance route, fal, or third-party provider/router surfaces such as EvoLink, OpenRouter, Kie.ai, PiAPI, LaoZhang, Runware, ModelsLab, AI/ML…
character-design
A design aid for creating and revising characters used in AI-generated images or video.
genhasamu-perspective
A creative design framework based on Kenya Hara's minimalist approach. It helps an agent examine visual ideas through simplicity, everyday objects, materials, and the use of empty space.
helmut-lang-perspective
A visual-design framework based on Helmut Lang’s minimalist fashion. It focuses on structure, technical materials, precise details, architecture, and the idea that design can be expressive without being obvious.
kawakubo-perspective
A fashion and visual-design framework based on Rei Kawakubo and Comme des Garçons. It examines deconstruction, unusual shapes, black clothing, unfinished forms, and questions about the relationship between the body and clothing.
tadao-ando-perspective
An architecture and design-thinking framework based on Tadao Ando’s work, focusing on simple geometry, concrete, light, shadow, nature, and empty space.