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 agentmods add skills/rampstackco/claude-skills/creative-directionnpx skills add rampstackco/claude-skills --skill creative-directiongit clone --depth 1 https://github.com/rampstackco/claude-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/rampstackco/claude-skills/creative-direction)<a href="https://agentmods.dev/skills/rampstackco/claude-skills/creative-direction"><img src="https://agentmods.dev/badge/skills/rampstackco/claude-skills/creative-direction.svg" alt="Measured on agentmods" 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 | $0.00170 | $0.02349 |
| Opus 5 | $0.00085 | $0.01175 |
| Sonnet 5 | $0.00034 | $0.00470 |
| Haiku 4.5 | $0.00017 | $0.00235 |
Grade A, and why
creative-direction 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 5d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creative Direction
Frameworks produce competent output. Coherent output requires a brief.
This skill turns vague creative intent into a structured brief that downstream skills can reference. It does not generate taste. It captures direction, so the dozens of small decisions a project requires (word choice, image selection, white space, sequencing, what to leave out) all answer to the same question.
Worked examples for each axis position can be assembled from any reference brand library that documents tone, aesthetic, audience relationship, and sensory ambition consistently. The framework below describes the four axes; the user's own reference set positions each example along the axes during the brief workflow.
When to use
- The start of a multi-touchpoint project (website, brand, campaign, product launch) where aesthetic coherence matters
- Before running multiple downstream skills that need to share a unified voice and look
- When inheriting a project that has competent execution but feels generic or incoherent
- Recalibrating an existing project that has drifted aesthetically over time
- When the user is a non-curator who knows what feeling they want but cannot articulate the decisions that produce it
When NOT to use
- Use
creative-briefinstead when the user needs a general kickoff brief covering scope, audience, deliverables, and constraints. This skill goes deeper on aesthetic axes specifically, not on the operational layer. - Use
art-directioninstead when briefing a specific creative deliverable (photo shoot, illustration set, video, campaign). This skill produces project-wide aesthetic direction;art-directionextends that direction into specific creative work. - Tactical single-piece work (one tweet, one error message, one button label)
- Projects where the user has complete aesthetic direction documented already (skip to downstream skills)
- Purely functional output (data tables, form labels, system status text)
- Production-stage execution where direction is already locked
- When the goal is to develop taste; this skill codifies intent, it does not develop judgment
What ships with it
3 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.
- 5d ago First seen · 154 lines · 170 tokens per session scan A fc11c1322566
creative-direction is a skill published in the GitHub repository rampstackco/claude-skills (814 stars, last pushed 7d ago), licensed MIT. It adds 170 tokens to every session and 2,349 once invoked, about $0.0009 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
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
interactive-slides
Creates interactive, animated web presentations viewable in any browser — not PowerPoint files. Use this skill when the user wants a web-based or browser-viewable presentation, an interactive slide deck, or something more engaging than a static slide file. Perfect for pitches, proposals, data stories, reports, and…
alterlab-vcd-photo-editor
This skill should be used when the user asks about "photo editing", "image editing", "retouching", "photo retouching", "photo essay", "photo curation", "AI photo editing", "color grading photography", "Lightroom", "Photoshop", "image compositing", "photo narrative", "editorial photography", "act as a photo editor"…
alterlab-vcd-motion-graphics
This skill should be used when the user asks about "motion graphics", "motion design", "title sequence", "kinetic typography", "explainer animation", "motion branding", "animated logo", "lower thirds", "broadcast design", "After Effects", "act as a motion graphics designer", "motion graphics mode", "animation…
alterlab-vcd-poster-designer
This skill should be used when the user asks about "poster design", "campaign poster", "event poster", "social media graphics", "billboard design", "banner design", "flyer design", "promotional graphics", "visual hierarchy poster", "concert poster", "film poster", "act as a poster designer", "poster designer mode"…
design-studio
Produce thoughtful, high-fidelity design artifacts in HTML — landing pages, slide decks, interactive prototypes, animated videos, posters, wireframes, and visual explorations. Use whenever the user asks to design, mock up, prototype, visualize, storyboard, or explore UI options — including phrases like "make a deck"…