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 Owl-Listener/inclusive-design-skills --skill voice-interactiongit clone --depth 1 https://github.com/Owl-Listener/inclusive-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/owl-listener/inclusive-design-skills/voice-interaction)<a href="https://agentmods.dev/skills/owl-listener/inclusive-design-skills/voice-interaction"><img src="https://agentmods.dev/badge/skills/owl-listener/inclusive-design-skills/voice-interaction/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/owl-listener/inclusive-design-skills/voice-interaction"><img src="https://agentmods.dev/badge/skills/owl-listener/inclusive-design-skills/voice-interaction.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 | $0.00089 | $0.00591 |
| Opus 5 | $0.00044 | $0.00296 |
| Sonnet 5 | $0.00018 | $0.00118 |
| Haiku 4.5 | $0.00009 | $0.00059 |
Grade A, and why
voice-interaction 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 12d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voice Interaction Design
Design voice interfaces that work for the full range of human speech — including accents, speech disabilities, non-native speakers, and people in noisy or quiet environments.
Who This Is For
- People with motor disabilities who use voice as primary input
- People who stutter, have dysarthria, or other speech differences
- Non-native speakers with varied accents
- People in environments where typing is impractical
- Anyone who prefers voice to typing for certain tasks
Core Principles
Voice Should Never Be the Only Option
- Every voice interaction must have a text/touch/keyboard alternative
- Voice is an accelerator, not a gatekeeper
- Don't require voice for identity verification or critical actions unless an alternative exists
Design for Speech Variation
- Support varied pacing — don't cut off slow speakers
- Allow generous silence before timing out
- Don't penalise repetition, filler words, or self-correction
- Support multiple phrasings for the same intent ("go back", "previous page", "take me back", "undo")
Feedback Must Be Clear
- Confirm what the system heard (visual transcript)
- Make it easy to correct misrecognition
- Show when the system is listening vs. processing vs. waiting
- Never execute a destructive action on voice alone without confirmation
Design Patterns
Flexible Recognition
- Accept multiple ways to say the same command
- Don't require exact phrasing — intent matters more than syntax
- Support "did you mean?" clarification for ambiguous input
- Allow users to spell out words the system doesn't recognise
Graceful Failure
- When recognition fails: show what was heard and offer correction
- Never respond with just "I didn't understand" — offer alternatives
- Provide a "type instead" option at every failure point
- After repeated failures: proactively suggest switching to text input
Privacy and Control
- Clear visual/audio indicator when microphone is active
- Easy one-action mute/stop listening
- Don't record or transmit audio without explicit consent
- Allow users to review and delete voice data
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.
- 12d ago First seen · 69 lines · 89 tokens per session scan A 091bbbaed8dd
voice-interaction is a skill published in the GitHub repository Owl-Listener/inclusive-design-skills (98 stars, last pushed 3mo ago), licensed MIT. It adds 89 tokens to every session and 591 once invoked, about $0.0004 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.
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).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.