Voice Apply Skill

Local writing and participating consumer recipes

Use author-controlled writing workflows for the actual aiwg writing plan and aiwg writing proofread commands, channel APIs, bounded revision, explicit learning, scoped MCP resources and separate receipts. Planning creates a structured artifact; proofreading applies exact listed author-authorized corrections without a model or voice rewrite. A selected mode is not an applied transformation. Unsupported consumers use explicit instruction exports; never claim every provider response is intercepted. Keep original text and unresolved review decisions recoverable. Publication controls remain with the user's existing workflow.

Reviewed voice application

For model-driven voice transformation, use the packaged criticism/correction flow and output impact guide. The selected development lane uses one Astra draw and at most one correction with the primary session as reviewer. Neutral analytical packets are required; private author provenance stays outside generator and corrector context. Preserve the original unless a hash-bound review accepts both fidelity and cadence. This does not change deterministic proofread-only behavior or qualify all channels.

Brief and fidelity contract

For author-controlled writing, prepare a structured writing brief before generating prose. Record reader task, supported propositions, limitations, intended action and approved author notes. Missing first-person experiences or design rationale are editorial gaps; do not invent them. Keep evidence strength independent of voice. Proofread-only applies selected authorized correction IDs to the original source; other operations expose explicit permissions and lineage for downstream execution.

Run fidelity checks after every final structure/presentation pass. Uncertain paraphrases require review. Preserve the original on configured fallback and report attempted versus retained changes outside product prose. Automated literal guards are not semantic proof.

Purpose

Transform content to match a specified voice profile. This skill loads voice profiles and applies their characteristics (tone, vocabulary, structure, perspective) to new or existing content.

Evidence constraints are recorded in the natural voice ownership ADR and versioned ledger. Treat phrase highlights as contextual editorial suggestions, never authorship probabilities. Preserve supplied facts, uncertainty and author intent; an assertive tone does not strengthen evidence. Author notes were already part of the cited post-editing study. Neither topic-matched examples nor a fixed example count is established as a universally best choice. The ledger is an evidence contract, not a claim that the planned natural voice pipeline has been qualified.

When This Skill Applies

User asks to "write in X voice" or "use Y tone"
User wants to "make this sound more [casual/formal/technical/etc.]"
User provides content and asks to transform its style
User references a voice profile by name
User wants content to match a specific audience or context

Trigger Phrases

| Natural Language | Action | |------------------|--------| | "Write this in technical voice" | Apply technical-authority profile | | "Make it more casual" | Apply casual-conversational or calibrate toward casual | | "This needs to sound executive" | Apply executive-brief profile | | "Explain like I'm a beginner" | Apply friendly-explainer profile | | "Use the [profile-name] voice" | Load and apply named profile | | "Transform this to match [example]" | Analyze example, apply derived voice |

Voice Profile Locations

Skill checks these locations (in order):

Project: .aiwg/voices/
User: ~/.config/aiwg/voices/
Built-in: voice-framework/voices/templates/

Built-in Voice Profiles

| Profile | Description | Best For | |---------|-------------|----------| | technical-authority | Direct, precise, confident | Docs, architecture, engineering | | friendly-explainer | Approachable, encouraging | Tutorials, onboarding, education | | executive-brief | Concise, outcome-focused | Business cases, stakeholder comms | | casual-conversational | Relaxed, personal | Blog posts, social, newsletters |

Application Process

1. Load Voice Profile

# Load from YAML
profile = load_voice_profile("technical-authority")

2. Analyze Source Content (if transforming)

Current tone characteristics
Vocabulary patterns
Structure patterns
Gap analysis vs target voice

3. Apply Voice Characteristics

Tone Calibration:

Adjust formality level (word choice, contractions)
Preserve evidence strength and all required hedging; adjust expression only
Set warmth (clinical vs personable)
Tune energy (measured vs enthusiastic)

Vocabulary Transformation:

Replace words per prefer/avoid guidance
Introduce domain terminology naturally
Use characteristic phrasing only where natural and supported; never insert signatures mechanically

Structure Adjustment:

Modify sentence length distribution
Adjust paragraph breaks
Reorganize supported material within edit permissions; do not invent examples or analogies that add claims

Perspective Shift:

Adjust narrative person (I, we, you, they)
Preserve supported opinions and attribution; do not invent a viewpoint
Set reader relationship tone

4. Verify Authenticity Markers

Check these properties only when supported by the source; never invent them to satisfy a profile:

Acknowledges uncertainty (if specified)
Shows tradeoffs (if specified)
Uses specific numbers (if specified)
References constraints (if specified)

Usage Examples

Apply Named Voice

User: "Write release notes in technical-authority voice"

Process:
1. Load technical-authority.yaml
2. Generate release notes with:
   - Precise technical terminology
   - Specific version numbers
   - Direct, confident statements
   - Tradeoff acknowledgments where relevant

Transform Existing Content

User: "Make this documentation more friendly for beginners"

Input: "The API endpoint accepts a JSON payload containing the requisite parameters..."

Process:
1. Load friendly-explainer.yaml
2. Analyze: formal, technical, passive
3. Transform to: casual, accessible, active

Output: "To use this endpoint, send it some JSON with the info it needs..."

Calibrate Voice

User: "This is too formal, dial it back 30%"

Process:
1. Identify current formality (~0.8)
2. Calculate target (0.8 - 0.3 = 0.5)
3. Adjust vocabulary and structure for medium formality

Voice Blending

Combine multiple profiles:

User: "Write this with 70% technical-authority and 30% friendly-explainer"

Process:
1. Load both profiles
2. Weighted merge:
   - tone.formality: 0.7 * 0.7 + 0.3 * 0.3 = 0.58
   - tone.warmth: 0.7 * 0.3 + 0.3 * 0.8 = 0.45
   - etc.
3. Apply merged profile

Script Reference

voice_loader.py

Load and validate voice profiles:

python scripts/voice_loader.py --profile technical-authority

voice_analyzer.py

Analyze content against voice profile:

python scripts/voice_analyzer.py --content input.md --profile technical-authority

Integration

Works with:

/voice-apply command for explicit invocation
/voice-create command for generating new profiles
SDLC templates (apply appropriate voice per artifact type)
Marketing templates (brand voice consistency)

Output Format

When reporting voice application:

Voice Applied: technical-authority

Transformations:
- Formality: 0.4 → 0.7 (increased)
- Evidence strength: unchanged; original qualifications retained
- Vocabulary: 12 replacements
- Structure: reordered supported clauses within approved edit scope

Authenticity Check:
✓ Acknowledges tradeoffs
✓ Uses specific numbers
✓ References constraints

References

@$AIWG_ROOT/agentic/code/addons/voice-framework/README.md — Voice framework addon overview and profile documentation
@$AIWG_ROOT/agentic/code/addons/voice-framework/voices/templates/ — Built-in voice profile templates
@$AIWG_ROOT/agentic/code/addons/writing-quality/README.md — Writing quality addon for authenticity enforcement
@$AIWG_ROOT/docs/cli-reference.md — CLI reference for voice commands
@$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/instruction-comprehension.md — Parsing voice and style directives accurately