generate-guidelines
Skill1 starsChanged 7 months agoMITView on GitHub
Generate brand voice guidelines from documents, transcripts, discovery reports, or any combination of source materials. Produce tone attributes, vocabulary rules, messaging pillars, do/don't examples, and channel-specific guidance. Trigger with "generate brand guidelines", "create a style guide", "extract brand voice", "build guidelines from", or "create voice guidelines".
In this repository164 other files it gives its agents.
- instrument-data-to-allotropeSkill
- literature-reviewSkill
- nextflow-developmentSkill
- scientific-problem-selectionSkill
- scvi-toolsSkill
- single-cell-rna-qcSkill
- discover-brandSkill
- enforce-voiceSkill
- csat-reportSkill
- customer-escalationSkill
- customer-researchSkill
- draft-responseSkill
- kb-articleSkill
- sentiment-analysisSkill
- ticket-triageSkill
- analyzeSkill
- build-dashboardSkill
- create-vizSkill
- data-context-extractorSkill
- data-modelingSkill
- data-pipelineSkill
- etl-designSkill
- explore-dataSkill
- sql-queriesSkill
- statistical-analysisSkill
- validate-dataSkill
- write-querySkill
- accessibility-reviewSkill
- component-librarySkill
- design-critiqueSkill
- design-handoffSkill
- design-systemSkill
- frontend-designSkill
- research-synthesisSkill
- user-researchSkill
- ux-copySkill
- wireframingSkill
- Agent DevelopmentSkill
- CLAUDE.md ManagementSkill
- MCP Server BuilderSkill
- Plugin DevelopmentSkill
- Prompt EngineeringSkill
- Skill CreatorSkill
- curriculum-designSkill
- lesson-planningSkill
- quiz-generatorSkill
- study-guideSkill
- tutoringSkill
- api-designSkill
- architectureSkill
- ci-cd-pipelineSkill
- code-reviewSkill
- database-migrationSkill
- debugSkill
- dependency-auditSkill
- deploy-checklistSkill
- documentationSkill
- error-handlingSkill
- git-workflowSkill
- incident-responseSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 33
Discovery report: If a brand discovery was run, use it as the primary input.
- Distinctive: line 48
Personality traits: If the brand were a person, how would they speak?
- Distinctive: line 63
Create terminology and language guidelines:
- Distinctive: line 68
Industry jargon policy: When to use technical terms vs.
- Distinctive: line 171
Action: Read the discovery report, extract voice patterns, define tone attributes, build vocabulary and messaging rules, produce the full …
- Distinctive: line 186
Keep the guideline document scannable.
- Distinctive: line 189
Test the guidelines by having someone unfamiliar with the brand write a paragraph using them.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Brand Voice Guideline Generation
Generate comprehensive brand voice guidelines from source materials including documents, call transcripts, discovery reports, website content, and existing brand assets. Produce actionable tone attributes, vocabulary rules, messaging pillars, and do/don't examples.
Workflow
Step 1: Ingest Source Materials
Collect and process all available inputs:
- Discovery report: If a brand discovery was run, use it as the primary input.
- Existing guidelines: Previous brand guides, style guides, or messaging documents.
- Content samples: Website copy, blog posts, emails, social posts that represent the desired voice.
- Transcripts: Sales calls, support calls, webinars, podcasts, leadership talks.
- Stakeholder input: Direct descriptions of how the brand should sound.
- Visual identity: Color palette, typography, and design language for alignment.
Step 2: Extract Voice Patterns
Analyze the source materials to identify consistent patterns:
- Tone patterns: What emotional qualities appear consistently across materials?
- Vocabulary frequency: Which words and phrases appear repeatedly?
- Sentence structure: Short and punchy, long and detailed, or mixed?
- Formality level: Where does the content consistently land on the formality spectrum?
- Personality traits: If the brand were a person, how would they speak?
- Audience relationship: How does the brand address its audience (peer, authority, guide, partner)?
Step 3: Define Tone Attributes
Establish 3-5 core tone attributes with calibration:
For each attribute, define:
- What it means: Clear definition of the tone quality.
- What it is not: The extreme to avoid (e.g., "confident, not arrogant").
- Scale placement: Where the brand sits on a spectrum.
- Examples: Sentences that demonstrate the attribute correctly and incorrectly.
Step 4: Build Vocabulary Rules
Create terminology and language guidelines:
- Approved terms: Words and phrases the brand should use consistently.
- Banned terms: Words and phrases to avoid with reasons and alternatives.
- Product terminology: Correct names, capitalization, and formatting for products and features.
- Industry jargon policy: When to use technical terms vs. plain language.
- Inclusive language: Guidance on gender-neutral, accessible, and respectful language.
Step 5: Define Messaging Pillars
Establish core messages the brand consistently communicates:
- Primary value proposition: The single most important message.
- Supporting pillars: 3-5 key themes that appear across brand communications.
- Proof points: Evidence and examples that support each pillar.
- Elevator pitch: A concise brand description for quick reference.
Step 6: Create Do/Don't Examples
Provide concrete examples for each guideline dimension:
- Tone do/don't: Side-by-side examples of correct vs. incorrect tone.
- Vocabulary do/don't: Banned terms paired with approved alternatives.
- Messaging do/don't: On-message vs. off-message examples.
- Channel-specific do/don't: How the voice adapts (or should not adapt) per channel.
Step 7: Channel-Specific Guidance
Define voice adjustments for each communication channel:
- Website: Tone, length, formality expectations.
- Blog: Depth, personality, educational approach.
- Email: Subject line style, greeting conventions, sign-off preferences.
- Social media: Platform-specific voice adjustments, emoji and hashtag policy.
- Sales materials: Confidence level, competitive positioning language.
- Support communications: Empathy calibration, technical language limits.
Output Format
## Brand Voice Guidelines: <brand name>
**Created**: <date>
**Version**: 1.0
**Based on**: <list of source materials analyzed>
### Brand Essence
<1-2 sentence description of who the brand is and how it communicates>
### Tone Attributes
#### <Attribute 1>
- **Definition**: <what this means for our voice>
- **Not**: <the extreme we avoid>
- **Do**: "<example sentence>"
- **Don't**: "<example sentence>"
#### <Attribute 2>
<same structure>
#### <Attribute 3>
<same structure>
### Messaging Pillars
| Pillar | Core Message | Proof Points |
|--------|-------------|-------------|
| <pillar name> | <message> | <evidence> |
| <pillar name> | <message> | <evidence> |
| <pillar name> | <message> | <evidence> |
**Elevator Pitch**: <concise brand description>
### Vocabulary Guide
**Always Use**:
| Term | Instead Of | Why |
|------|-----------|-----|
| <approved> | <banned> | <reason> |
**Never Use**:
| Term | Use Instead | Why |
|------|------------|-----|
| <banned> | <approved> | <reason> |
**Product Names**:
| Product | Correct Format | Common Mistakes |
|---------|---------------|----------------|
| <product> | <correct> | <incorrect variations> |
### Channel-Specific Guidance
| Channel | Formality | Length | Special Notes |
|---------|-----------|-------|---------------|
| Website | <level> | <guidance> | <notes> |
| Blog | <level> | <guidance> | <notes> |
| Email | <level> | <guidance> | <notes> |
| Social | <level> | <guidance> | <notes> |
| Sales | <level> | <guidance> | <notes> |
| Support | <level> | <guidance> | <notes> |
### Quick Reference Card
<one-page summary of the most critical guidelines for daily use>Examples
User: "Generate brand guidelines from our discovery report" Action: Read the discovery report, extract voice patterns, define tone attributes, build vocabulary and messaging rules, produce the full guideline document.
User: "Create voice guidelines from these 10 blog posts and 3 sales call transcripts" Action: Analyze all materials for consistent patterns, identify the natural brand voice, formalize it into guidelines with do/don't examples.
User: "We have no brand guide -- create one from our website and product docs" Action: Crawl key website pages, read product documentation, extract the implicit brand voice, generate guidelines that formalize and strengthen it.
User: "Update our brand guidelines based on feedback that we sound too corporate" Action: Review current guidelines and recent content, identify overly formal patterns, adjust tone attributes and examples toward the desired direction.
Best Practices
- Base guidelines on observed patterns, not aspirations alone. The guidelines should feel recognizable to the team.
- Define what the brand is NOT as clearly as what it IS. "Confident, not arrogant" is more actionable than just "confident."
- Keep the guideline document scannable. Long brand guides go unread.
- Include a one-page quick reference card for daily use by writers and marketers.
- Provide real before/after examples, not abstract rules. Concrete examples teach faster than definitions.
- Test the guidelines by having someone unfamiliar with the brand write a paragraph using them. If they can produce on-brand content, the guidelines work.
- Plan for version control. Brand voice evolves; guidelines should be dated and versioned.
- Involve stakeholders in reviewing the draft guidelines before finalizing. Buy-in is essential for adoption.
- Channel-specific guidance prevents the false assumption that one voice fits all contexts.
- Pair guidelines with enforcement (the enforce-voice skill) for ongoing compliance.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

