enforce-voice
Skill1 starsChanged 7 months agoMITView on GitHub
Apply brand guidelines to content creation by checking tone, terminology, messaging pillars, and flagging deviations. Use when reviewing a draft for brand consistency, writing content that must match brand voice, editing copy to align with guidelines, or auditing existing content. Trigger with "check brand voice", "apply brand guidelines", "is this on-brand", "review for brand consistency", or "enforce voice".
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
- generate-guidelinesSkill
- 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 43
Read the content to be reviewed and classify it:
- Distinctive: line 63
Verify language choices against the guidelines:
- Distinctive: line 66
Required terms: Check whether approved terminology is used consistently.
- Distinctive: line 67
Product names: Verify correct capitalization and formatting of product and feature names.
- Distinctive: line 69
Competitor mentions: Check the policy on naming competitors.
- Distinctive: line 156
When guidelines are ambiguous, note the ambiguity rather than making a judgment call.
- Distinctive: line 158
If no brand guidelines are available, offer to run brand discovery and guideline generation first.
≈ “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 Enforcement
Apply brand guidelines to content by checking tone, terminology, messaging pillars, and formatting conventions. Flag deviations by severity and provide specific corrections.
Workflow
Step 1: Load Brand Guidelines
Retrieve and parse the applicable brand guidelines:
- Stored guidelines: Load from the configured brand guide file or memory.
- Tone attributes: Extract the defined tone descriptors (e.g., confident but not arrogant, helpful but not patronizing).
- Terminology rules: Approved terms, banned terms, and required substitutions.
- Messaging pillars: Core value propositions and key messages.
- Formatting conventions: Capitalization rules, punctuation preferences, number formatting.
- Channel-specific rules: Adjustments for email vs. social vs. website vs. formal documents.
Step 2: Analyze the Content
Read the content to be reviewed and classify it:
- Content type: Blog post, email, social post, landing page, internal doc, presentation.
- Target audience: Who the content is written for.
- Purpose: Inform, persuade, support, announce, sell.
- Channel: Where the content will be published.
- Length: Word count and structure overview.
Step 3: Check Tone Alignment
Evaluate the content's tone against brand guidelines:
- Tone consistency: Does the content match the defined tone attributes throughout?
- Tone shifts: Are there sections where the tone changes inappropriately?
- Emotional register: Is the emotional intensity appropriate for the content type?
- Formality level: Does the formality match the guidelines for this channel?
- Brand personality: Does the content sound like the brand would sound?
Step 4: Check Terminology and Messaging
Verify language choices against the guidelines:
- Banned terms: Flag any words or phrases on the do-not-use list.
- Required terms: Check whether approved terminology is used consistently.
- Product names: Verify correct capitalization and formatting of product and feature names.
- Messaging pillars: Confirm alignment with core value propositions.
- Competitor mentions: Check the policy on naming competitors.
- Inclusive language: Flag language that conflicts with inclusivity guidelines.
Step 5: Check Formatting and Style
Review mechanical elements:
- Capitalization: Title case vs. sentence case per guidelines.
- Punctuation: Oxford comma, exclamation point limits, dash usage.
- Number formatting: Numerals vs. words, currency, percentages.
- Abbreviations: First-use expansion, approved acronyms.
- Link text: Descriptive link text vs. "click here."
Step 6: Produce the Review
Compile findings with severity ratings and specific fixes.
Output Format
## Brand Voice Review
**Content**: <title or description>
**Type**: <content type>
**Channel**: <where it will be published>
**Overall Alignment**: On-brand / Mostly on-brand / Needs work / Off-brand
### Summary
<2-3 sentence assessment of overall brand alignment>
### Deviations Found
#### Critical (must fix before publishing)
| # | Location | Issue | Guideline | Suggested Fix |
|---|----------|-------|-----------|---------------|
| 1 | <paragraph/line> | <what is wrong> | <relevant rule> | <specific correction> |
#### Moderate (should fix)
| # | Location | Issue | Guideline | Suggested Fix |
|---|----------|-------|-----------|---------------|
| 1 | <paragraph/line> | <what is wrong> | <relevant rule> | <specific correction> |
#### Minor (consider fixing)
| # | Location | Issue | Guideline | Suggested Fix |
|---|----------|-------|-----------|---------------|
| 1 | <paragraph/line> | <what is wrong> | <relevant rule> | <specific correction> |
### Tone Assessment
- **Target tone**: <from guidelines>
- **Actual tone**: <what was detected>
- **Alignment**: Strong / Moderate / Weak
- **Notes**: <specific observations>
### Terminology Check
- **Banned terms found**: <list or "none">
- **Missing required terms**: <list or "none">
- **Product name errors**: <list or "none">
### Positive Highlights
- <elements that are well-aligned with brand voice>
### Revised Version (optional)
<If requested, provide the full content with corrections applied>Examples
User: "Check if this blog post matches our brand voice" Action: Load stored brand guidelines, analyze the post for tone, terminology, and messaging alignment, flag deviations with corrections.
User: "Review this email campaign draft for brand consistency" Action: Apply email-specific brand rules, check tone for the audience, verify terminology and formatting, produce the review.
User: "Is this landing page on-brand? Fix anything that isn't." Action: Review the landing page against guidelines, flag issues, and produce a revised version with all corrections applied.
User: "Audit our top 5 blog posts for brand voice consistency" Action: Review each post against guidelines, identify common deviation patterns across posts, recommend systemic fixes.
Best Practices
- Load the most current version of brand guidelines. Outdated rules create false flags.
- Severity matters. A banned term in a headline is critical; a minor tone wobble in a long blog post is minor.
- Provide the specific correction, not just the problem. "Too casual" is less useful than replacing the exact sentence.
- Respect the writer's voice within the brand guidelines. Enforcement should align, not flatten.
- For channel-specific content, apply channel-specific rules. Social media voice may be deliberately more casual than website copy.
- Highlight what the content does well. Positive reinforcement encourages continued alignment.
- When guidelines are ambiguous, note the ambiguity rather than making a judgment call.
- Track recurring deviations across content to identify training opportunities or guideline gaps.
- If no brand guidelines are available, offer to run brand discovery and guideline generation first.
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.

