Audit content and assets for brand compliance — style guide validation, tone of voice checking, visual identity consistency, brand asset management, and cross-channel coherence.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Invoke this skill when:
Skill({ skill: 'brand-compliance' });
Check written content against the brand's style guide:
Grammar and Language:
Formatting:
Output: List each violation with exact text, rule violated, severity, and suggested fix.
Score content against the brand voice profile across key dimensions:
Voice Dimensions (score 1–5 per dimension):
Tone Analysis:
Default voice profile (use when brand profile not provided):
When reviewing design assets or code with visual specifications:
Logo Usage:
Color Palette:
Typography:
Imagery and Icons:
Verify asset usage compliance:
Asset Categories:
Checks:
Evaluate consistency across channels when multiple touchpoints are provided:
Core Brand Elements (must be consistent across all channels):
Channel-Specific Adaptations (acceptable variations):
Coherence Score: Rate 1–5 per channel pair reviewed.
Produce a structured report:
# Brand Compliance Report
**Content/Asset:** [name]
**Date:** [date]
**Audited By:** brand-compliance skill
## Summary
- Total Findings: N
- Errors (Blocking): N
- Warnings (Informational): N
- Passed: N
## Findings
| # | Area | Finding | Severity | Suggested Fix |
| --- | ------ | ------------------------------------ | -------- | ------------------ |
| 1 | Style | [exact text] uses "..." (prohibited) | ERROR | Replace with "..." |
| 2 | Tone | Formality score 5 vs. target 3 | WARNING | Rephrase: "..." |
| 3 | Visual | Logo minimum size violated | ERROR | Use 40px minimum |
## Tone Score
| Dimension | Target | Actual | Delta | Status |
| --------- | ------ | ------ | ----- | ------ |
| Formality | 3 | 4 | +1 | WARN |
| Warmth | 4 | 4 | 0 | PASS |
| Authority | 4 | 3 | -1 | WARN |
| Energy | 3 | 3 | 0 | PASS |
## Overall Compliance Score
[N]% compliant (errors weighted 3x, warnings weighted 1x)
## Next Steps
1. [Action for error #1]
2. [Action for error #2]
Example 1: Copy Audit
User: "Review this product description for brand compliance"
Agent: [Reads content → runs Steps 1–2 → produces findings table with severity]
Output: 3 errors (prohibited terms, wrong capitalization), 2 warnings (tone slightly too formal), 92% compliance score
Example 2: Visual Asset Audit
User: "Check this landing page design for brand compliance"
Agent: [Reads design specs/CSS → runs Steps 3–5 → produces visual findings]
Output: 1 error (off-palette color #E5E5E5 used), 3 warnings (typography weight inconsistency), 88% compliance
Example 3: Cross-Channel Review
User: "Compare our Instagram and web copy for brand coherence"
Agent: [Reads both → runs Step 5 → coherence score]
Output: 85% coherent, tagline wording differs across channels (warning), CTA variations acceptable
Input validated against schemas/input.schema.json before execution.
Output contract defined in schemas/output.schema.json.
Pre-execution hook: hooks/pre-execute.cjs
Post-execution hook: hooks/post-execute.cjs (emits observability event)
tokens.json or approved color/type files when available, not just memory.| Anti-Pattern | Why It Fails | Correct Approach |
|---|---|---|
| Blocking CI on warnings | Excessive friction disables compliance checks | Block only on errors (severity: ERROR); log warnings |
| Tone feedback without target profile | Subjective judgments are inconsistent | Require or default to a numeric voice profile |
| Generic "off-brand" findings | No actionable remediation | Every finding must include suggested fix text |
| Auditing only written copy, ignoring visual | Brand violations are often visual | Run all 5 audit steps unless scope explicitly limited |
| Approving assets without version check | Deprecated assets slip through | Always verify asset version against approved DAM |
Before starting:
Read .claude/context/memory/learnings.md
After completing:
.claude/context/memory/learnings.md.claude/context/memory/issues.md.claude/context/memory/decisions.mdASSUME INTERRUPTION: If it's not in memory, it didn't happen.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
The English summary is being prepared. Showing the original description.
Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.
The English summary is being prepared. Showing the original description.
N-round opposing-stance debates for trade-off analysis. Assigns pro/con roles to agents, runs structured debate rounds with quality scoring, and produces a moderator synthesis with confidence-rated recommendation. Generalizable to architecture, technology, security, and design decisions.
The English summary is being prepared. Showing the original description.
Force adversarial code review stance that eliminates confirmation bias — reviewer must find issues or re-analyze
The English summary is being prepared. Showing the original description.
Creates specialized AI agents on-demand when no existing agent matches a request. Use when the Router cannot find a suitable agent for a task. Enables self-evolution by generating persistent agents.
The English summary is being prepared. Showing the original description.
LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations
The English summary is being prepared. Showing the original description.