菜单
Audit content and assets for brand compliance — style guide validation, tone of voice checking, visual identity consistency, brand asset management, and cross-channel coherence.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/oimiragieo/agent-studio --skill brand-compliance命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Agent frontmatter enhancements — disallowedTools, mcpServers scoping, fork_eligible field
Context management — pre-compact persistence, threshold alignment, microcompact/circuit breaker detection
Hook enhancements — updatedInput for bash safety prefixes, suppressOutput for verbose blocks, denial-based routing feedback
正在显示 SKILL.md
基于 SOC 职业分类
| name | brand-compliance |
| description | Audit content and assets for brand compliance — style guide validation, tone of voice checking, visual identity consistency, brand asset management, and cross-channel coherence. |
| version | 1.0.0 |
| model | sonnet |
| invoked_by | both |
| user_invocable | true |
| tools | ["Read","Write","Edit","Grep","Glob"] |
| agents | ["brand-guardian","marketing-strategist"] |
| category | Specialized |
| tags | ["brand","compliance","style-guide","tone-of-voice","visual-identity","brand-assets","cross-channel"] |
| best_practices | ["Validate against brand guidelines before publishing","Score tone objectively using a voice profile","Provide specific remediation suggestions, not just flags","Separate error (blocking) from warning (informational) findings"] |
| error_handling | graceful |
| streaming | supported |
| verified | false |
| lastVerifiedAt | "2026-03-02T00:00:00.000Z" |
| source | builtin |
| trust_score | 100 |
| provenance_sha | d89c3fa73b2ed997 |
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.