Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Voice Command Consulting

ASecurity

Interview-driven consulting for custom voice command sets. Discover workflows, translate to noun-verb commands (or verb-first for developers), iterate, and emit JSON config.

3 stars
0 votes
0 copies
0 views
Added 9/20/2026
developmentgo

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add trillium/parlay --skill voice-command-consulting --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Voice Command Consulting?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Voice Command Consulting
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/trillium-voice-command-consulting/badge)](https://www.skillsdirectory.com/skills/trillium-voice-command-consulting)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: voice-command-consulting
description: Interview-driven consulting for custom voice command sets. Discover workflows, translate to noun-verb commands (or verb-first for developers), iterate, and emit JSON config.
argument-hint: "What's the user's primary workflow or use case (e.g., 'private chef managing orders')?"
disable-model-invocation: false
---

# Voice Command Consulting

**INVOKE THIS**: `/voice-command-consulting "describe your workflow"`

When invoked, this skill spawns a consulting agent who will:
1. Interview you about your workflow
2. Suggest command patterns (noun-verb or verb-first based on your domain)
3. Iterate on commands with you
4. Output a JSON command definition ready to import

See `consulting-agent.md` in this skill directory for the full agent prompt.

## Workflow Discovery → Command Design → JSON Config

The consulting process flows: **interview** → **suggest** → **refine** → **export**.

### 1. Discover Workflows

Ask the user:
- **What visuals must you see?** (screens, panels, data views they reference)
- **What actions do you take?** (what changes state? what triggers notifications?)
- **When do you use voice?** (hands busy? eyes elsewhere? both?)
- **How many times daily?** (frequent = optimize for speed, rare = okay to be verbose)

Examples:
- Chef: "I need to see incoming orders and mark them ready."
- Developer: "I need to switch between open PRs and file a status update."

### 2. Design Commands (Noun-Verb Pattern)

Based on Talon Hub conventions, suggest **noun-verb** or **verb-noun** commands:
- `orders show` — reveal incoming orders
- `order <name> select` — pick an order (name is disambiguator)
- `order ready submit` — mark order as ready
- `pr list show` — show open PRs
- `pr <number> comment` — add a comment

**Key principle**: each command should advance the user toward their next action.

### 3. Build Aliases (STT Tolerance)

For each command, suggest phonetically similar variants to handle STT misrecognition:
- `bravely / gravely / briefly / beverly` (four homophones for reliability)
- `frame / brake / shame` (pick one, alias the others)

Aliases are learned via 3-utterance calibration sessions when the user trains.

### 4. Define Trigger Words

Identify a **submit trigger** word(s) to distinguish intent from action:
- User says: `order three ready` → system transitions to confirmation view
- System shows: "Ready to submit: order three marked ready"
- User says: `bravely` → system submits

This two-step flow prevents accidental submission and allows visual review.

### 5. Output JSON Config

Produce a command definition that the system can load:

```json
{
  "commands": [
    {
      "id": "order_show",
      "triggers": ["orders show", "order list show"],
      "aliases": ["or- show", "orderlist show"],
      "action": "transition",
      "target_view": "incoming_orders",
      "description": "Display incoming orders"
    },
    {
      "id": "order_select",
      "triggers": ["order {name} select", "select {name}"],
      "aliases": ["oder {name} select"],
      "action": "transition",
      "target_view": "compose",
      "context": { "selected_order": "{name}" },
      "description": "Select an order and move to compose view"
    }
  ],
  "submit_triggers": ["bravely", "gravely", "briefly", "beverly"],
  "reset_trigger": "never mind",
  "protocol": "noun-verb",
  "visual_feedback": "instant_state_update",
  "training_utterances_per_command": 3
}
```

## Refinement Loop

After initial suggestions:
- Ask: "Does this feel right? Too many commands? Missing something?"
- Test: "Say this command out loud — does it feel natural?"
- Refine: Update aliases, adjust grouping, remove low-value commands
- Validate: "Can you imagine using this 5 times per day?"

## Key Constraints

1. **STT reliability** — Good acoustic environment required (quiet workspace, good mic placement)
2. **Cognitive load** — Start with 5–8 commands max; add more via organic learning over time
3. **Muscle memory** — Commands should follow consistent patterns (noun-verb, not verb-noun)
4. **Recoverability** — Every action can be undone or corrected visually

## Anti-Patterns to Avoid

- ❌ Too many homophones that collide (e.g., "frame" + "frame" as both command and submit)
- ❌ Inconsistent structure ("orders show" + "get status" — mixing patterns)
- ❌ Chaining commands that require 5+ steps without progress
- ❌ Voice-only mode without visual feedback (chef cooking can't hear confirmations)

## Tips

- **Observe first**: Ask the user to narrate what they do, then build commands from their own language
- **Start narrow**: 3 commands for the top workflow beats 20 scattered ones
- **Test early**: Have them say the commands out loud before finalizing
- **Monitor real use**: Log misrecognitions and iterate quarterly

---

**Next step**: Invoke this skill with the user's primary workflow, and the consulting agent will guide you through the full interview → design → export cycle.

Attribution

trilliumtrillium
View sourceMore from trillium →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Browser Extension Developer

Use this skill when developing or maintaining browser extension code in the `browser/` directory, including Chrome/Firefox/Edge compatibility, content scripts, background scripts, or i18n updates.

281612 votes

Seo Optimizer

SEO optimization with keyword analysis, readability assessment, technical validation, content quality. Use for search rankings, blog posts, content audits, or encountering keyword density, readability scores, meta tags, schema markup errors.

2132 votes

Google Official Seo Guide

Official Google SEO guide covering search optimization, best practices, Search Console, crawling, indexing, and improving website search visibility based on official Google documentation

1862 votes

Tanstack Start

Build a full-stack TanStack Start app on Cloudflare Workers from scratch — SSR, file-based routing, server functions, D1+Drizzle, better-auth, Tailwind v4+shadcn/ui. Use whenever the user mentions TanStack Start, asks to scaffold a full-stack Cloudflare app with SSR, wants an SSR dashboard, or asks for a React 19 + Cloudflare Workers app with file-based routing and server functions — even if they don't name TanStack Start specifically. No template repo — Claude generates every file fresh per ...

9881 votes

Pentest

PTES-aligned adversarial security audit for backend, frontend, and mobile applications. Produces a CVSS-scored Hacker Report with verified PoCs and phased remediation.

5491 votes
View all in development →