Guideline Generation

1---2name: guideline-generation3description: >4  This skill generates, creates, or builds brand voice guidelines from source5  materials. It should be used when the user asks to "generate brand guidelines",6  "create a style guide", "extract brand voice", "create guidelines from calls",7  "consolidate brand materials", "analyze my sales calls for brand voice",8  "build a brand playbook from documents", "synthesize a voice and tone guide",9  or uploads brand documents, transcripts, or meeting recordings for brand10  analysis. Also triggers when the user has a discovery report and wants to11  convert it into actionable guidelines.12---13 14# Guideline Generation15 16Generate 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.17 18## Inputs19 20Accept any combination of:21- **Discovery report** from the discover-brand skill (structured, pre-triaged)22- **Brand documents** uploaded or from connected platforms (PDF, PPTX, DOCX, MD, TXT)23- **Conversation transcripts** from Gong, Granola, manual uploads, or Notion meeting notes24- **Direct user input** about their brand voice and values25 26When a discovery report is provided, use it as the primary input — sources are already triaged and ranked. Supplement with additional analysis as needed.27 28## Generation Workflow29 30### 1. Identify and Classify Sources31 32Determine what the user has provided. If no sources are available:33- Check if a discovery report exists from a previous `/brand-voice:discover-brand` run34- Check `.claude/brand-voice.local.md` for known brand material locations35- Suggest running discovery first: `/brand-voice:discover-brand`36 37### 2. Process Sources38 39**For documents:** Delegate to the document-analysis agent for heavy parsing. Extract voice attributes, messaging themes, terminology, tone guidance, and examples.40 41**For transcripts:** Delegate to the conversation-analysis agent for pattern recognition. Extract implicit voice attributes, successful language patterns, tone by context, and anti-patterns.42 43**For discovery reports:** Extract pre-triaged sources, conflicts, and gaps. Use the ranked sources directly.44 45### 3. Synthesize Into Guidelines46 47Merge all findings into a unified guideline document following the template in `references/guideline-template.md`. Key sections:48 49**"We Are / We Are Not" Table** — The core brand identity anchor:50 51| We Are | We Are Not |52|--------|------------|53| [Attribute — e.g., "Confident"] | [Counter — e.g., "Arrogant"] |54| [Attribute — e.g., "Approachable"] | [Counter — e.g., "Casual or sloppy"] |55 56Derive attributes from the most consistent patterns across sources. Each row should have supporting evidence.57 58**Voice Constants vs. Tone Flexes** — Clarify what stays fixed and what adapts:59- **Voice** = personality, values, "We Are / We Are Not" — constant across all content60- **Tone** = formality, energy, technical depth — flexes by context61 62**Tone-by-Context Matrix:**63 64| Context | Formality | Energy | Technical Depth | Example |65|---------|-----------|--------|-----------------|---------|66| Cold outreach | Medium | High | Low | "[example phrase]" |67| Enterprise proposal | High | Medium | High | "[example phrase]" |68| Social media | Low | High | Low | "[example phrase]" |69 70### 4. Assign Confidence Scores71 72Score each section using the methodology in `references/confidence-scoring.md`:73- **High confidence**: 3+ corroborating sources, explicit guidance found74- **Medium confidence**: 1-2 sources, or inferred from patterns75- **Low confidence**: Single source, inferred, or conflicting data76 77### 5. Surface Open Questions78 79Generate open questions for any ambiguity that cannot be resolved:80 81```markdown82## Open Questions for Team Discussion83 84### High Priority (blocks guideline completion)851. **[Question Title]**86   - What was found: [conflicting or incomplete info]87   - Agent recommendation: [suggested resolution with reasoning]88   - Need from you: [specific decision or confirmation needed]89```90 91Every open question MUST include an agent recommendation. Turn ambiguity into "confirm or override" — never a dead end.92 93### 6. Quality Check94 95Before presenting, verify via the quality-assurance agent (defined in `agents/quality-assurance.md`):96- All major sections populated (including Brand Personality and Content Examples if sources support them)97- At least 3 voice attributes with evidence98- "We Are / We Are Not" table has 4+ rows99- Tone matrix covers at least 3 contexts100- Confidence scores assigned per section101- Source attribution for all extracted elements102- No PII exposed103- Open questions include recommendations104 105### 7. Present and Offer Next Steps106 107Summarize key findings:108- Total sections generated with confidence breakdown109- Strongest voice attribute and most effective message110- Number of open questions (if any)111 112### 8. Save for Future Sessions113 114The default save location is `.claude/brand-voice-guidelines.md` inside the user's working folder.115 116**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.117 1181. **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.1192. **Check if guidelines already exist** at that path1203. **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)1214. **Save new guidelines** to `.claude/brand-voice-guidelines.md` inside the working folder1225. **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."123 124The guidelines are also present in this conversation, so `/brand-voice:enforce-voice` can use them immediately without loading from file.125 126After saving, offer:1271. Walk through the guidelines section by section1282. Start creating content with `/brand-voice:enforce-voice`1293. Resolve open questions130 131## Privacy and Security132 133Enforce these privacy constraints throughout the entire generation workflow, not only at output time:134- Redact customer names and contact information from all examples135- Anonymize company names in transcript excerpts if requested136- Flag any sensitive information detected during processing137 138## Reference Files139 140- **`references/guideline-template.md`** — Complete output template with all sections, field definitions, and formatting guidance141- **`references/confidence-scoring.md`** — Confidence scoring methodology, thresholds, and examples