Guideline Generation

Guideline Generation

Generate comprehensive, LLM-ready brand voice guidelines from any combination of sources — brand documents, sales call transcripts, discovery reports, or direct user input. Transform raw materials into structured, enforceable guidelines with confidence scoring and open questions.

Inputs

Accept any combination of:

• Discovery report from the discover-brand skill (structured, pre-triaged)
• Brand documents uploaded or from connected platforms (PDF, PPTX, DOCX, MD, TXT)
• Conversation transcripts from Gong, Granola, manual uploads, or Notion meeting notes
• Direct user input about their brand voice and values

When a discovery report is provided, use it as the primary input — sources are already triaged and ranked. Supplement with additional analysis as needed.

Generation Workflow

1. Identify and Classify Sources

Determine what the user has provided. If no sources are available:

• Check if a discovery report exists from a previous /brand-voice:discover-brand run
• Check .claude/brand-voice.local.md for known brand material locations
• Suggest running discovery first: /brand-voice:discover-brand

2. Process Sources

For documents: Delegate to the document-analysis agent for heavy parsing. Extract voice attributes, messaging themes, terminology, tone guidance, and examples.

For transcripts: Delegate to the conversation-analysis agent for pattern recognition. Extract implicit voice attributes, successful language patterns, tone by context, and anti-patterns.

For discovery reports: Extract pre-triaged sources, conflicts, and gaps. Use the ranked sources directly.

3. Synthesize Into Guidelines

Merge all findings into a unified guideline document following the template in references/guideline-template.md. Key sections:

"We Are / We Are Not" Table — The core brand identity anchor:

Derive attributes from the most consistent patterns across sources. Each row should have supporting evidence.

Voice Constants vs. Tone Flexes — Clarify what stays fixed and what adapts:

• Voice = personality, values, "We Are / We Are Not" — constant across all content
• Tone = formality, energy, technical depth — flexes by context

Tone-by-Context Matrix:

4. Assign Confidence Scores

Score each section using the methodology in references/confidence-scoring.md:

• High confidence: 3+ corroborating sources, explicit guidance found
• Medium confidence: 1-2 sources, or inferred from patterns
• Low confidence: Single source, inferred, or conflicting data

5. Surface Open Questions

Generate open questions for any ambiguity that cannot be resolved:

## Open Questions for Team Discussion

### High Priority (blocks guideline completion)
1. **[Question Title]**
   - What was found: [conflicting or incomplete info]
   - Agent recommendation: [suggested resolution with reasoning]
   - Need from you: [specific decision or confirmation needed]

Every open question MUST include an agent recommendation. Turn ambiguity into "confirm or override" — never a dead end.

6. Quality Check

Before presenting, verify via the quality-assurance agent (defined in agents/quality-assurance.md):

• All major sections populated (including Brand Personality and Content Examples if sources support them)
• At least 3 voice attributes with evidence
• "We Are / We Are Not" table has 4+ rows
• Tone matrix covers at least 3 contexts
• Confidence scores assigned per section
• Source attribution for all extracted elements
• No PII exposed
• Open questions include recommendations

7. Present and Offer Next Steps

Summarize key findings:

• Total sections generated with confidence breakdown
• Strongest voice attribute and most effective message
• Number of open questions (if any)

8. Save for Future Sessions

The default save location is .claude/brand-voice-guidelines.md inside the user's working folder.

Important: The agent's working directory may not be the user's project root (especially in Cowork, where plugins run from a plugin cache directory). Always resolve the path relative to the user's working folder, not the current working directory. If no working folder is set, skip the file save and tell the user guidelines will only be available in this conversation.

1. Resolve the save path. The file MUST be saved to .claude/brand-voice-guidelines.md inside the user's working folder. Confirm the working folder path before writing. 2. Check if guidelines already exist at that path 3. If they exist, archive the previous version: Rename the existing file to brand-voice-guidelines-YYYY-MM-DD.md in the same directory (using today's date) 4. Save new guidelines to .claude/brand-voice-guidelines.md inside the working folder 5. Confirm to the user with the full absolute path: "Guidelines saved to <full-path>. /brand-voice:enforce-voice will find them automatically in future sessions."

The guidelines are also present in this conversation, so /brand-voice:enforce-voice can use them immediately without loading from file.

After saving, offer: 1. Walk through the guidelines section by section 2. Start creating content with /brand-voice:enforce-voice 3. Resolve open questions

Privacy and Security

Enforce these privacy constraints throughout the entire generation workflow, not only at output time:

• Redact customer names and contact information from all examples
• Anonymize company names in transcript excerpts if requested
• Flag any sensitive information detected during processing

Reference Files

• `references/guideline-template.md` — Complete output template with all sections, field definitions, and formatting guidance
• `references/confidence-scoring.md` — Confidence scoring methodology, thresholds, and examples

Confidence Scoring Methodology

How to assign and interpret confidence scores for generated brand guidelines.

Scoring Levels

High Confidence

The guideline section is well-supported and actionable.

Criteria (must meet at least 3):

• 3+ corroborating sources
• Explicit guidance found in at least one AUTHORITATIVE source
• Consistent across document and conversation analysis
• Specific, actionable instructions (not just vague principles)
• No unresolved conflicts

Example: Voice attribute "Confident but not arrogant" appears in the official style guide, is demonstrated in email templates, and matches patterns in top performer calls.

Medium Confidence

The section is reasonable but could benefit from more data or team confirmation.

Criteria (must meet at least 2):

• 1-2 corroborating sources
• Inferred from patterns rather than explicit instruction
• Minor inconsistencies resolved via recency or authority
• Actionable but some interpretation was required
• May have one unresolved conflict

Example: Tone for social media inferred from email templates and one Slack thread, but no official social media guidelines exist.

Low Confidence

The section is a best-effort recommendation. Team review strongly recommended.

Criteria (must meet at least 2):

• Single source only
• Primarily inferred from indirect evidence
• Significant interpretation required
• Unresolved conflicts between sources
• Limited specificity

Example: Competitive positioning derived from a single sales call where a competitor was discussed, with no supporting documentation.

Section-Level Scoring Guide

Voice Attributes

• High: Attributes appear in official brand guide AND are demonstrated in templates or calls
• Medium: Attributes appear in one document type only, or are inferred from multiple conversations
• Low: Attributes inferred from a single source or from indirect evidence

Messaging Framework

• High: Value propositions documented in official materials AND used consistently in sales conversations
• Medium: Documented but not observed in practice, OR observed but not documented
• Low: Extracted from a single pitch deck or single call

Tone Matrix

• High: Explicit tone guidance exists for the context AND matches observed behavior
• Medium: Tone inferred from 3+ examples of content in that context
• Low: Tone inferred from 1-2 examples, or extrapolated from similar contexts

Terminology

• High: Terms explicitly listed in a style guide or glossary
• Medium: Terms consistently used in templates and calls (pattern-based)
• Low: Terms observed in a single document or inferred from brand personality

Language Patterns (from transcripts)

• High: Pattern observed in 5+ calls across multiple speakers
• Medium: Pattern observed in 3-4 calls or from a single top performer
• Low: Pattern observed in 1-2 calls only

Transcript-Primary Scenarios

When guidelines are generated primarily from conversational sources (no AUTHORITATIVE documents available):

• Voice Attributes derived from 5+ transcripts = Medium (not Low)
• Messaging Framework from consistent patterns across 5+ calls = Medium
• Language Patterns weight increases from 10% to 20% in aggregate calculation (subtract 10% from Voice Attributes)

Note this in the guideline metadata: "Guidelines generated primarily from conversational sources — team review recommended to formalize."

Aggregate Confidence

Calculate overall guideline confidence as the weighted average of section scores:

Convert scores: High = 1.0, Medium = 0.6, Low = 0.3

Example:

• Voice Attributes: High (1.0 x 0.30 = 0.30)
• Messaging: Medium (0.6 x 0.25 = 0.15)
• Tone: Medium (0.6 x 0.20 = 0.12)
• Terminology: High (1.0 x 0.15 = 0.15)
• Language: Low (0.3 x 0.10 = 0.03)
• Overall: 0.75 = Medium-High confidence

Aggregate score thresholds:

• 0.85–1.0 = High
• 0.60–0.84 = Medium
• Below 0.60 = Low

Presentation

Present confidence alongside each section header:

## Voice Attributes (Confidence: High)
[content]

## Tone Matrix (Confidence: Medium)
[content — note: no official social media guidelines found, tone inferred from email patterns]

For Medium and Low confidence sections, include a brief note explaining why confidence is limited and what would raise it.

Relationship to Open Questions

Low confidence sections should generate corresponding open questions:

• Low confidence + conflict = High Priority open question
• Low confidence + gap = Medium Priority open question
• Medium confidence + minor inconsistency = Low Priority open question

Every open question includes a recommendation that, if confirmed, would raise the section's confidence score.

Brand Guidelines Output Template

The complete structure for generated brand voice guidelines. Fill each section based on discovered and analyzed sources. The following is a raw markdown template — copy and fill the sections below. Omit sections with no data rather than including empty placeholders.

[Company Name] Brand Voice Guidelines

Generation Metadata

• Created: [date]
• Version: [N] (incremented from previous if updating)
• Replaces: [previous version date, if applicable]
• Sources: [list of documents and/or conversations analyzed]
• Documents processed: [N]
• Conversations analyzed: [N]
• Discovery report used: [Yes/No]
• Overall confidence: [High/Medium/Low]

---

Executive Summary

[2-3 paragraph overview of the brand voice. What makes this brand distinctive? What is the core personality? How should content feel to the reader?]

---

We Are / We Are Not

The foundational brand identity anchor. Voice is constant — it doesn't change by channel or audience.

Voice Attributes Detail

For each "We Are" attribute:

[Attribute 1]: [Name]

• What it means: [detailed description]
• How it shows up: [specific behaviors in content]
• What to avoid: [the "We Are Not" counterpart, expanded]
• Evidence: [source quote or pattern, with citation]
• Confidence: [High/Medium/Low]

[Repeat for each attribute]

---

Brand Personality

• Archetype: [e.g., "The Expert Friend" — technically deep but never condescending]
• If our brand were a person: [brief personality sketch]
• Core values expressed in voice: [list]

---

Messaging Framework

Primary Value Proposition

[Core value statement — one sentence]

Variations observed:

• "[Variation 1]" (Source: [doc])
• "[Variation 2]" (Source: [doc])

Key Message Pillars

1. [Pillar Name]

• Core idea: [one sentence]
• When to use: [contexts]
• Example phrasing: "[quote]"
• Frequency in conversations: [X]% (if transcript data available)
• Effectiveness: [High/Medium/Low] (if outcome data available)

2. [Pillar Name] [same format]

3. [Pillar Name] [same format]

Competitive Positioning

• vs. [Competitor A]: [how we differentiate]
• vs. [Competitor B]: [how we differentiate]
• vs. Status Quo: [why change is worth it]

---

Tone-by-Context Matrix

Voice is constant. Tone flexes by context. These three dimensions adjust:

Context-Specific Guidelines

Cold Outreach

• Overall tone: [description]
• Opening approach: [what works]
• Do's: [list]
• Don'ts: [list]
• Example: "[sample opening line]"

Discovery Calls

[same structure]

Proposals & RFPs

[same structure]

Social Media

[same structure]

---

Terminology Guide

Must-Use Terms

Preferred Terms

Avoid These Terms

Never-Use Terms

---

Language That Works

Ranked by effectiveness (from conversation analysis, if available):

Top Phrases

1. "[Phrase]" — Context: [when to use], Why it works: [analysis] 2. "[Phrase]" — Context: [when to use], Why it works: [analysis]

Questions That Engage

1. "[Question]" — Leads to: [typical outcome] 2. "[Question]" — Leads to: [typical outcome]

Objection Handling Patterns

1. Objection: "[common objection]" Response pattern: "[how top performers respond]" Why it works: [analysis]

---

Language to Avoid

Anti-Patterns

1. "[Phrase/pattern]" — Problem: [what happens], Better: "[alternative]" 2. "[Phrase/pattern]" — Problem: [what happens], Better: "[alternative]"

---

Content Examples

Excellent Examples

[Full example with annotation explaining what makes it on-brand]

Examples to Avoid

[Full example with annotation explaining what's off-brand and how to fix it]

---

Confidence Scores

---

Open Questions for Team Discussion

High Priority (blocks guideline completion)

1. [Question Title]

• What was found: [description of ambiguity]
• Agent recommendation: [suggested resolution]
• Need from you: [specific decision]

Medium Priority (improves quality)

[same format]

Low Priority (nice to have)

[same format]

---

Data Gaps & Recommendations

[What's missing and specific actions to fill gaps]

• [ ] [Gap 1]: [recommendation to fill it]
• [ ] [Gap 2]: [recommendation to fill it]

---

Appendix: Sources

---

Template Usage Notes

• Omit sections with no data rather than including empty placeholders
• If transcript data is unavailable, omit the "Language That Works" and "Language to Avoid" sections
• If only documents are available (no transcripts), note this in metadata
• "We Are / We Are Not" table should have minimum 4 rows, ideally 5-7
• Tone matrix should cover at minimum: cold outreach, proposals, social media
• All examples must have source attribution
• Every open question must include an agent recommendation