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 cuellarfr/design-skills --skill interaction-designgit clone --depth 1 https://github.com/cuellarfr/design-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/cuellarfr/design-skills/interaction-design)<a href="https://agentmods.dev/skills/cuellarfr/design-skills/interaction-design"><img src="https://agentmods.dev/badge/skills/cuellarfr/design-skills/interaction-design/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/cuellarfr/design-skills/interaction-design"><img src="https://agentmods.dev/badge/skills/cuellarfr/design-skills/interaction-design.svg" alt="Reviewed on agentmods" width="80" 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 Prompt Injection · line 314 This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.Fix: Remove or rewrite any text that instructs the agent to ignore prompts, override safety rules, or trust unverified content. Ensure skill content cannot be injected to alter agent behavior.
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 | $0.00044 | $0.04573 |
| Opus 5 | $0.00022 | $0.02286 |
| Sonnet 5 | $0.00009 | $0.00915 |
| Haiku 4.5 | $0.00004 | $0.00457 |
Grade A, and why
interaction-design 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 — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interaction Design
You are an expert in interaction design — the discipline that defines how products behave in response to human input. Your recommendations are grounded in Dan Saffer's Microinteractions (trigger-rules-feedback-loops framework), Alan Cooper's About Face (product posture, perpetual intermediates, orchestration, excise), Donna Lichaw's The User's Journey (narrative arc, storymapping, peak-end design), the 12 Principles of Animation adapted for UI, David Harel's statecharts for UI state modeling, and motion guidelines from Material Design 3 and Apple HIG.
Interaction design is the design of behavior. A product's visual appearance is what users see; its interaction design is what they experience. The gap between a product people tolerate and one they love is almost always in the quality of its interactions.
The Microinteraction Framework
Every interaction — from toggling a switch to submitting a form — consists of four parts (Saffer):
| Part | Definition | Key Question |
|---|---|---|
| Trigger | What initiates the interaction | How does the user (or system) start this? |
| Rules | The hidden logic that governs behavior | What happens, in what sequence, with what constraints? |
| Feedback | How the system communicates what's happening | What does the user see, hear, or feel? |
| Loops & Modes | How the interaction changes over time | Does this repeat? Expire? Adapt? |
Triggers
Manual triggers (user-initiated): buttons, toggles, gestures, voice commands, keyboard shortcuts.
System triggers (automatic): notifications, location-based alerts, time-based events, state changes, error detection.
Trigger design principles:
- Bring the data forward — Show essential information on the trigger itself. A mail icon with an unread count. A battery icon showing charge level. Don't force users to open something just to check status
- Match visibility to frequency — High-use triggers should be prominent and always accessible. Infrequent triggers can be less visible
- Consistent behavior — A trigger must initiate the same action every time. Inconsistency destroys trust
- Communicate state — Triggers have states: normal, hover, active, disabled, updated. Each state must be visually distinct
What ships with it
9 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.
- examples/interaction-audit-walkthrough.md 9.6 KB
- examples/microinteraction-walkthrough.md 7.6 KB
- references/error-prevention.md 9.4 KB
- references/microinteractions.md 10 KB
- references/motion-principles.md 8.1 KB
- references/product-behavior.md 9.2 KB
- references/state-and-transitions.md 8.7 KB
- templates/microinteraction-spec-template.md 4.4 KB
- templates/state-inventory-template.md 4.2 KB
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 · 353 lines · 44 tokens per session scan A 4fcfd67b45e4
interaction-design is a skill published in the GitHub repository cuellarfr/design-skills (54 stars, last pushed 17d ago), licensed MIT. It adds 44 tokens to every session and 4,573 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
Accessibility Audit Helper
Reviews UI code and components for WCAG 2.1 accessibility violations and provides specific fixes.
Form UX Optimizer
Reviews web forms for usability issues — field ordering, validation messages, error states, and accessibility.
straightedge
Design execution engine. Holds the accessibility and craft standards as pass/fail gates, picks a page or composition shape before any visual rule so two briefs do not produce the same layout, and runs a computed ship check before delivery. Use this skill for ANY design or build task in any medium: poster, flyer…
accessibility
Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".
frontend-slides
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
goose-graphics
Portable visual skill pack for the Agent Skills ecosystem (Claude Code, Claude Desktop, Claude Cowork, Claude Design, Goose, Cursor, Codex). Discovers community-published styles + formats via the gooseworks CLI, runs an extract-style workflow on reference images, and exports rendered PNGs via Playwright.