dreamcontext 0.5.0

package/dist/skill-packs/brand-voice/SKILL.md

@@ -0,0 +1,115 @@
+---
+description: "Load when writing emails, proposals, presentations, LinkedIn posts, sales content, pitch decks, Slack messages, or any brand-aligned content. Also triggers on 'brand voice', 'on-brand', 'enforce voice', 'write in our voice', 'make this sound like us', 'rewrite in our tone', 'discover brand materials', 'generate brand guidelines', 'brand content audit', 'style guide', 'find brand docs'. Sub-skills: discover-brand (search platforms for brand materials), guideline-generation (create structured guidelines from sources). Agent: discover-brand (autonomous platform search)."
+alwaysApply: false
+ruleType: "Brand Voice System"
+version: "1.0"
+---
+
+## Sub-Skills (Read Before Specific Work)
+
+| When you are about to... | Read first |
+|--------------------------|------------|
+| Search connected platforms for brand materials, run a brand content audit | `discover-brand.md` |
+| Generate, create, or synthesize brand voice guidelines from documents or transcripts | `guideline-generation.md` |
+
+## Agent
+
+| When you need to... | Agent name |
+|---------------------|------------|
+| Autonomously search enterprise platforms for brand materials | `discover-brand` |
+
+---
+
+# Brand Voice Enforcement
+
+Apply existing brand guidelines to all sales and marketing content generation. Load the project's brand guidelines, apply voice constants and tone flexes to the content request, validate output, and explain brand choices.
+
+## Loading Brand Guidelines
+
+Find the project's brand guidelines using this sequence. Stop as soon as you find them:
+
+1. **Core file** -- Check `_dream_context/core/` for a brand voice core file (e.g., `brand_voice.md`). This is the primary location. If found, the guidelines are already part of the project context and may be auto-loaded in the snapshot.
+
+2. **Session context** -- Check if brand guidelines were generated earlier in this session via the guideline-generation sub-skill. If so, they are already in the conversation. Use them directly.
+
+3. **Ask the user** -- If none of the above found guidelines, tell the user:
+   "I couldn't find brand guidelines in `_dream_context/core/`. You can:
+   - Have me discover brand materials across your connected platforms (read `discover-brand.md`)
+   - Have me generate guidelines from documents or transcripts (read `guideline-generation.md`)
+   - Paste guidelines directly into this chat or point me to a file"
+
+   Wait for the user to provide guidelines before proceeding.
+
+Also check the brand voice core file frontmatter for enforcement settings:
+- `strictness`: strict | balanced | flexible (default: balanced)
+- `always_explain`: whether to always explain brand choices (default: false)
+
+## Enforcement Workflow
+
+### 1. Analyze the Content Request
+
+Before writing, identify:
+- **Content type**: email, presentation, proposal, social post, message, etc.
+- **Target audience**: role, seniority, industry, company stage
+- **Key messages needed**: which message pillars apply
+- **Specific requirements**: length, format, tone overrides
+
+### 2. Apply Voice Constants
+
+Voice is the brand's personality -- it stays constant across all content:
+- Apply "We Are / We Are Not" attributes from guidelines
+- Use brand personality consistently
+- Incorporate approved terminology; reject prohibited terms
+- Follow messaging framework and value propositions
+
+Refer to `references/voice-constant-tone-flexes.md` for the "voice constant, tone flexes" model.
+
+### 3. Flex Tone for Context
+
+Tone adapts by content type and audience. Use the tone-by-context matrix from guidelines to set:
+- **Formality**: How formal or casual should this be?
+- **Energy**: How much urgency or enthusiasm?
+- **Technical depth**: How detailed or accessible?
+
+### 4. Generate Content
+
+Create content that:
+- Matches brand voice attributes throughout
+- Follows tone guidelines for this specific content type
+- Incorporates key messages naturally (not forced)
+- Uses preferred terminology
+- Mirrors the quality and style of guideline examples
+
+For complex or long-form content, launch the content-generation agent via the Agent tool.
+For high-stakes content, launch the quality-assurance agent for validation.
+
+### 5. Validate and Explain
+
+After generating content:
+- Briefly highlight which brand guidelines were applied
+- Explain key voice and tone decisions
+- Note any areas where guidelines were adapted for context
+- Offer to refine based on feedback
+
+When `always_explain` is true in the core file frontmatter, include brand application notes with every response.
+
+## Handling Conflicts
+
+When the user's request conflicts with brand guidelines:
+1. Explain the conflict clearly
+2. Provide a recommendation
+3. Offer options: follow guidelines strictly, adapt for context, or override
+
+Default to adapting guidelines with an explanation of the tradeoff.
+
+## Open Questions Awareness
+
+Open questions are unresolved brand positioning decisions flagged during guideline generation, stored in the guidelines under an "Open Questions" section. When generating content, check if the brand guidelines contain open questions:
+- If content touches an unresolved open question, note it
+- Apply the agent's recommendation from the open question unless the user specifies otherwise
+- Suggest resolving the question if it significantly impacts the content
+
+## Reference Files
+
+- **`references/voice-constant-tone-flexes.md`** -- The "voice constant, tone flexes" mental model, "We Are / We Are Not" table structure, and tone-by-context matrix explanation
+- **`references/before-after-examples.md`** -- Before/after content examples per content type showing enforcement in practice

package/dist/skill-packs/brand-voice/discover-brand.md

@@ -0,0 +1,126 @@
+---
+name: discover-brand
+description: >
+  This skill orchestrates autonomous discovery of brand materials across enterprise
+  platforms (Notion, Confluence, Google Drive, Box, SharePoint, Figma, Gong, Granola, Slack).
+  It should be used when the user asks to "discover brand materials",
+  "find brand documents", "search for brand guidelines", "audit brand content",
+  "what brand materials do we have", "find our style guide", "where are our brand docs",
+  "do we have a style guide", "discover brand voice", "brand content audit",
+  or "find brand assets".
+---
+
+# Brand Discovery
+
+Orchestrate autonomous discovery of brand materials across enterprise platforms. This skill coordinates the discover-brand agent to search connected MCP platforms (Notion, Confluence, Google Drive, Box, Microsoft 365, Figma, Gong, Granola, Slack), triage sources, and produce a structured discovery report with open questions.
+
+## Discovery Workflow
+
+### 0. Orient the User
+
+Before starting, briefly explain what's about to happen so the user knows what to expect:
+
+"Here's how brand discovery works:
+
+1. **Search** -- I'll search your connected platforms (Notion, Google Drive, Slack, etc.) for brand-related materials: style guides, pitch decks, templates, transcripts, and more.
+2. **Analyze** -- I'll categorize and rank what I find, pull the best sources, and produce a discovery report with what I found, any conflicts, and open questions.
+3. **Generate guidelines** -- Once you've reviewed the report, I can generate a structured brand voice guideline document from the results.
+4. **Save** -- Guidelines are saved as a core file in `_dream_context/core/` once you approve them. Nothing is written until that step.
+
+The search usually takes a few minutes depending on how many platforms are connected. Ready to get started?"
+
+Wait for the user to confirm before proceeding. If they have questions about the process, answer them first.
+
+### 1. Check Existing Context
+
+Check if a brand voice core file already exists in `_dream_context/core/` (e.g., `brand_voice.md`). If it exists, read it to understand:
+- Company name (from frontmatter or content)
+- Which platforms were previously searched
+- Any known brand material locations
+- Whether this is a refresh or a first-time discovery
+
+If no core file exists, proceed with all connected MCP platforms and standard search depth.
+
+### 2. Validate Platform Coverage
+
+Before confirming scope, check which MCP platforms are actually connected and classify them:
+
+**Document platforms** (where brand guidelines, style guides, templates, and decks live):
+- Notion, Confluence, Google Drive, Box, Microsoft 365 (SharePoint/OneDrive)
+
+**Supplementary platforms** (valuable for patterns, but not where brand docs are stored):
+- Slack, Gong, Granola, Figma
+
+Apply these rules:
+
+1. **If zero document platforms are connected**: **Stop.** Tell the user: "You don't have any document storage platforms connected (Google Drive, SharePoint, Notion, Confluence, or Box). Brand guidelines and style guides almost always live on one of these. Please connect at least one MCP server before running discovery. Gong/Granola/Slack transcripts are valuable supplements but unlikely to contain formal brand documents."
+
+2. **If no Google Drive AND no Microsoft 365 AND no Box**: **Warn** (but proceed): "None of your primary file storage platforms (Google Drive, SharePoint, Box) are connected. Brand documents frequently live on these platforms. Discovery will proceed with [connected platforms], but results may have significant gaps."
+
+3. **If only one platform total is connected**: **Warn** (but proceed): "Only [platform] is connected. Discovery works best with 2+ platforms for cross-source validation. Results from a single platform will have lower confidence scores."
+
+### 3. Confirm Scope with User
+
+Before launching discovery, confirm:
+- Which platforms to search (default: all connected)
+- Whether to include conversation transcripts (Gong, Granola) or just documents
+- Any known locations to prioritize
+
+Keep this brief -- one question, not a questionnaire.
+
+### 4. Delegate to Discover-Brand Agent
+
+Launch the discover-brand agent via the Agent tool. Provide:
+- Company name (from context or user input)
+- Enabled platforms
+- Search depth
+- Any known URLs or locations to check first
+
+The agent executes the 4-phase discovery algorithm autonomously:
+1. **Broad Discovery** -- parallel searches across platforms
+2. **Source Triage** -- categorize and rank sources
+3. **Deep Fetch** -- retrieve and extract from top sources
+4. **Discovery Report** -- structured output with open questions
+
+### 5. Present Discovery Report
+
+When the agent returns, present the report to the user with a summary:
+- Total sources found and analyzed
+- Key brand elements discovered
+- Any conflicts between sources
+- Open questions requiring team input
+
+### 6. Offer Next Steps
+
+After presenting the report, offer:
+1. **Generate guidelines now** -- use the guideline-generation sub-skill with the discovery report as input
+2. **Resolve open questions first** -- work through high-priority questions before generating
+3. **Save report** -- store the discovery report as a knowledge file in `_dream_context/knowledge/`
+4. **Expand search** -- search additional platforms or deeper if coverage is low
+
+## Open Questions
+
+Open questions arise when the discovery agent encounters ambiguity it cannot resolve:
+- Conflicting documents (e.g., 2023 style guide vs. 2024 brand update)
+- Missing critical sections (e.g., no social media guidelines found)
+- Inconsistent terminology across platforms
+
+Every open question includes an agent recommendation. Present questions as "confirm or override" -- not dead ends.
+
+## Integration with Other Skills
+
+- **Guideline Generation**: The discovery report is returned by the discover-brand agent. Pass it directly to the guideline-generation sub-skill as structured input, replacing the need for users to manually gather sources.
+- **Brand Voice Enforcement**: Once guidelines are generated from discovery and saved as a core file, enforcement loads them automatically from `_dream_context/core/`.
+
+## Error Handling
+
+- If zero MCP platforms are connected, inform the user which platforms are supported and how to connect them as MCP servers.
+- If all searches return empty results, flag the discovery as "low coverage" and suggest the user provide documents manually or check platform connections.
+- If a platform is connected but returns permission errors, note the gap and continue with other platforms.
+
+## Reference Files
+
+For detailed discovery patterns and algorithms, consult:
+
+- **`references/search-strategies.md`** -- Platform-specific search queries, query patterns by platform, and tips for maximizing discovery coverage
+- **`references/source-ranking.md`** -- Source category definitions, ranking algorithm weights, and triage decision criteria

package/dist/skill-packs/brand-voice/guideline-generation.md

@@ -0,0 +1,154 @@
+---
+name: guideline-generation
+description: >
+  This skill generates, creates, or builds brand voice guidelines from source
+  materials. It should be used when the user asks to "generate brand guidelines",
+  "create a style guide", "extract brand voice", "create guidelines from calls",
+  "consolidate brand materials", "analyze my sales calls for brand voice",
+  "build a brand playbook from documents", "synthesize a voice and tone guide",
+  or uploads brand documents, transcripts, or meeting recordings for brand
+  analysis. Also triggers when the user has a discovery report and wants to
+  convert it into actionable guidelines.
+---
+
+# 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 sub-skill (structured, pre-triaged)
+- **Brand documents** uploaded or from connected MCP 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 discover-brand run in this session
+- Check `_dream_context/core/` for an existing brand voice core file with source references
+- Check connected MCP platforms for existing materials
+- Suggest running brand discovery first (read `discover-brand.md`)
+
+### 2. Process Sources
+
+**For documents:** Launch the document-analysis agent for heavy parsing. Extract voice attributes, messaging themes, terminology, tone guidance, and examples.
+
+**For transcripts:** Launch 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:
+
+| We Are | We Are Not |
+|--------|------------|
+| [Attribute -- e.g., "Confident"] | [Counter -- e.g., "Arrogant"] |
+| [Attribute -- e.g., "Approachable"] | [Counter -- e.g., "Casual or sloppy"] |
+
+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:**
+
+| Context | Formality | Energy | Technical Depth | Example |
+|---------|-----------|--------|-----------------|---------|
+| Cold outreach | Medium | High | Low | "[example phrase]" |
+| Enterprise proposal | High | Medium | High | "[example phrase]" |
+| Social media | Low | High | Low | "[example phrase]" |
+
+### 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:
+
+```markdown
+## 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, launch the quality-assurance agent to verify:
+- 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 as Core File
+
+Save the generated guidelines as a core file in `_dream_context/core/`. Use the next available core file slot (7+).
+
+**File format:**
+```markdown
+---
+name: brand-voice
+description: "[Company] brand voice guidelines -- voice attributes, tone matrix, messaging framework, terminology"
+type: extended-core
+strictness: balanced
+always_explain: false
+generated_at: [date]
+sources_analyzed: [N]
+overall_confidence: [High/Medium/Low]
+---
+
+[Generated guidelines content]
+```
+
+**Steps:**
+1. Check if a brand voice core file already exists in `_dream_context/core/`
+2. If it exists, confirm with the user before overwriting (offer to archive the old version as a knowledge file)
+3. Save new guidelines to `_dream_context/core/` (e.g., `7.brand_voice.md`)
+4. Confirm to the user: "Brand voice guidelines saved to `_dream_context/core/7.brand_voice.md`. They'll be auto-loaded in future sessions via the snapshot."
+
+After saving, offer:
+1. Walk through the guidelines section by section
+2. Start creating content with brand voice enforcement
+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

package/dist/skill-packs/brand-voice/references/before-after-examples.md

@@ -0,0 +1,194 @@
+# Before/After Content Examples
+
+Concrete examples showing how brand voice enforcement transforms generic content into on-brand output. Each example shows the generic version, the enforced version, and annotations explaining what changed and why.
+
+These examples use a fictional B2B SaaS company for illustration. During enforcement, replace all specifics (data points, product names, metrics) with data from the user's actual brand guidelines and context.
+
+## Cold Outreach Email
+
+### Before (Generic)
+```
+Subject: Quick question about your sales process
+
+Hi [Name],
+
+I wanted to reach out because I think our product could be a great fit
+for your team. We offer an AI-powered platform that helps sales teams
+be more productive.
+
+Would you be open to a quick 15-minute call to learn more?
+
+Best,
+[Sender]
+```
+
+### After (Brand Voice Enforced)
+```
+Subject: [Company] is leaving pipeline on the table
+
+Hi [Name],
+
+Your team closed $12M last quarter — impressive. But our data shows
+mid-market SaaS teams like yours typically lose 23% of qualified pipeline
+to slow follow-ups.
+
+[Product] fixes that. We help sales teams respond to buying signals in
+real time, not hours later. [Customer X] saw their win rate jump 18%
+in the first quarter.
+
+Worth 15 minutes to see if the numbers apply to [Company]?
+
+[Sender]
+```
+
+### What Changed
+- **Voice: Confident** — leads with a bold claim and specific data (not "I think our product could be")
+- **Voice: Data-driven** — concrete numbers (23%, 18%, $12M) replace vague "more productive"
+- **Voice: Direct** — gets to the point immediately, no "I wanted to reach out"
+- **Tone: Energy HIGH** — active language, short sentences, urgency
+- **Tone: Formality MEDIUM** — professional but conversational
+- **Tone: Technical depth LOW** — outcomes and impact, not feature descriptions
+- **Terminology**: "buying signals" and "pipeline" (industry-specific but accessible to VP Sales)
+
+## Follow-Up Email
+
+### Before (Generic)
+```
+Hi [Name],
+
+Just following up on my previous email. I'd love to schedule a call
+to discuss how we can help your team.
+
+Let me know if you're available this week.
+
+Thanks,
+[Sender]
+```
+
+### After (Brand Voice Enforced)
+```
+Hi [Name],
+
+Quick update: we just published our Q4 benchmark report on enterprise
+sales velocity. Three insights jumped out that are relevant to [Company]:
+
+1. Teams using real-time signals close 31% faster than the industry average
+2. The #1 pipeline killer isn't competition — it's response time
+3. Mid-market wins are trending 15% larger when reps personalize within 2 hours
+
+Happy to walk through how these benchmarks compare to your team's numbers.
+The report is attached if you'd rather dig in yourself first.
+
+[Sender]
+```
+
+### What Changed
+- **Voice: Data-driven** — new value in every touch (benchmark data), not just "following up"
+- **Voice: Approachable** — offers two paths (call or self-serve) without pressure
+- **Voice: Confident** — shares proprietary insights, positions as expert
+- **Tone: Energy MEDIUM** — informative, not pushy
+- **Tone: Formality MEDIUM** — professional but not stiff
+- **Key principle applied**: "Add new value each touch" — no empty follow-ups
+
+## Enterprise Proposal Executive Summary
+
+### Before (Generic)
+```
+We are pleased to submit this proposal for your consideration. Our
+company offers a comprehensive AI solution that can help improve your
+sales team's performance. We believe our platform is the best choice
+for organizations looking to modernize their sales operations.
+```
+
+### After (Brand Voice Enforced)
+```
+[Company] processes 2,400 leads per quarter with a 12-person sales team.
+Current pipeline-to-close conversion sits at 18% — below the 24% benchmark
+for enterprise SaaS at your ARR stage.
+
+This proposal outlines how [Product] closes that gap. Our platform
+analyzes buying signals across your existing tech stack and surfaces
+the 3-5 daily actions most likely to advance each deal. Typical results:
++31% win rate, -40% time to close, 2.1x pipeline per rep.
+
+Implementation takes 3 weeks. ROI breaks even at week 6.
+```
+
+### What Changed
+- **Voice: Data-driven** — opens with the client's own metrics, not "we are pleased"
+- **Voice: Direct** — no filler language, every sentence carries information
+- **Voice: Confident** — specific outcomes with numbers, clear implementation timeline
+- **Tone: Formality HIGH** — structured, precise language
+- **Tone: Energy MEDIUM** — measured confidence, not hype
+- **Tone: Technical depth HIGH** — specific features (buying signals, tech stack analysis), ROI math
+
+## LinkedIn Post
+
+### Before (Generic)
+```
+Excited to announce our new feature! We've been working hard on this
+and we think it's going to change the way sales teams work. Check out
+the link below to learn more! #sales #AI #innovation
+```
+
+### After (Brand Voice Enforced)
+```
+The average sales rep spends 4.2 hours/day on tasks that don't close deals.
+
+We analyzed 50,000 sales activities across 200 teams and found the pattern:
+top performers aren't working harder — they're responding faster.
+
+Today we're launching Signal Score: real-time prioritization that tells
+your reps exactly which deal to work next, and why.
+
+Early results from beta: 23% fewer lost deals from delayed follow-up.
+
+Link in comments.
+```
+
+### What Changed
+- **Voice: Data-driven** — opens with a statistic, not "excited to announce"
+- **Voice: Confident** — specific research (50,000 activities, 200 teams)
+- **Voice: Innovative** — describes what's new without hype
+- **Voice: NOT hype-driven** — no "change the way sales teams work", replaced with measurable outcomes
+- **Tone: Formality LOW-MEDIUM** — casual enough for LinkedIn, professional enough for B2B
+- **Tone: Energy HIGH** — short sentences, bold opening stat
+- **Tone: Technical depth LOW** — outcomes-focused, accessible to any reader
+- **Terminology**: Avoided "revolutionary" and "game-changing" (prohibited terms)
+
+## Internal Slack Message
+
+### Before (Generic)
+```
+Hey team, just a reminder that we should all be using the approved
+messaging when talking to prospects. Please refer to the brand
+guidelines document for more information.
+```
+
+### After (Brand Voice Enforced)
+```
+Heads up — we updated the competitive positioning section in the brand
+guidelines. Two big changes:
+
+1. Against [Competitor]: lead with implementation speed (3 weeks vs. their 3 months)
+2. Against Status Quo: new stat — teams using manual processes lose 23% of pipeline to timing
+
+Updated doc is pinned in #sales-enablement. Questions? Tag me.
+```
+
+### What Changed
+- **Voice: Direct** — specific changes, not vague "please refer to"
+- **Voice: Data-driven** — concrete differentiators with numbers
+- **Voice: Approachable** — casual, helpful tone appropriate for Slack
+- **Tone: Formality LOW** — contractions, short sentences, "tag me"
+- **Tone: Energy MEDIUM** — informative without being overly enthusiastic
+- **Key principle**: Internal comms can be less polished, but voice attributes still apply
+
+## Using These Examples
+
+When enforcing brand voice, reference the relevant content type example to calibrate:
+1. Match the content type to the closest example above
+2. Note which voice attributes are most active for that type
+3. Apply the tone settings (formality, energy, technical depth)
+4. Check "We Are Not" boundaries — make sure content doesn't cross them
+5. Verify terminology compliance (preferred terms used, prohibited terms absent)