返回技能列表

explicit-checker

bitwize-music-studio
更新于 2 days ago
7 次查看
209
37
209
在 GitHub 上查看
general

关于

This skill scans song lyrics for explicit content and verifies that explicit flags match the actual findings. It reports word counts per track and flags any mismatches for accurate content ratings. Use it before music generation or release to ensure proper distributor submissions.

快速安装

Claude Code

推荐
主要方式
npx skills add bitwize-music-studio/claude-ai-music-skills -a claude-code
插件命令备选方式
/plugin add https://github.com/bitwize-music-studio/claude-ai-music-skills
Git 克隆备选方式
git clone https://github.com/bitwize-music-studio/claude-ai-music-skills.git ~/.claude/skills/explicit-checker

在 Claude Code 中复制并粘贴此命令以安装该技能

技能文档

Your Task

Path to scan: $ARGUMENTS

  1. Scan all lyrics for explicit words
  2. Report findings with word counts per track
  3. Flag mismatches (explicit content but flag says No, or vice versa)
  4. Provide summary suitable for distributor submission

Explicit Content Checker

You scan lyrics for explicit content to ensure proper flagging before release.


Explicit Words (Require Explicit = Yes)

These words and variations require the explicit flag:

CategoryWords
F-wordfuck, fucking, fucked, fucker, motherfuck, motherfucker
S-wordshit, shitting, shitty, bullshit
B-wordbitch, bitches
C-wordscunt, cock, cocks
D-worddick, dicks
P-wordpussy, pussies
A-wordasshole, assholes
Slurswhore, slut, n-word, f-word (slur)
Profanitygoddamn, goddammit

Clean Words (No Explicit Flag Needed)

These are acceptable without explicit flag:

  • damn, hell, crap, ass, bastard, piss

Note: "damn" alone is clean, but "goddamn" is explicit.


Override Support

The MCP check_explicit_content tool automatically loads and merges user overrides from {overrides}/explicit-words.md. No manual config read or merge logic needed — pass lyrics text and get results with overrides applied.

Override File Format

{overrides}/explicit-words.md:

# Custom Explicit Words

## Additional Explicit Words
- slang-term
- regional-profanity
- artist-specific-explicit

## Not Explicit (Override Base)
- hell (context: historical/literary)
- damn (context: emphasis)

Workflow

For Album Path

  1. Call list_tracks(album_slug) — get all tracks with metadata
  2. For each track:
    • Call extract_section(album_slug, track_slug, "lyrics") — get lyrics text
    • Call check_explicit_content(lyrics_text) — returns matches with line numbers (overrides auto-merged)
    • Get Explicit flag from track metadata
    • Compare flag vs. content
  3. Generate report

For Single Track

  1. Call extract_section(album_slug, track_slug, "lyrics") — get lyrics text
  2. Call check_explicit_content(lyrics_text) — scan for explicit words
  3. Get Explicit flag from track metadata via get_track(album_slug, track_slug)
  4. Report findings

Output Format

EXPLICIT CONTENT SCAN
Album: [Album Name]
Date: [Scan Date]

TRACK RESULTS:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Track 01: [Title]
  Flag: No
  Content: Clean
  Status: ✓ OK

Track 02: [Title]
  Flag: Yes
  Content: fuck (3), shit (2), bitch (1)
  Status: ✓ OK (flag matches content)

Track 03: [Title]
  Flag: No
  Content: fuck (1)
  Status: ⚠️ MISMATCH - Contains explicit content but flag is No

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

SUMMARY:
  Total tracks: 10
  Clean tracks: 7
  Explicit tracks: 3
  Mismatches: 1

ALBUM EXPLICIT FLAG: Yes (any track explicit = album explicit)

ACTION REQUIRED:
  - Track 03: Set Explicit flag to Yes

Mismatch Detection

Flag Says No, Content Is Explicit

⚠️ MISMATCH: Track contains explicit content but Explicit flag is "No"
ACTION: Set Explicit: Yes in track file

Flag Says Yes, Content Is Clean

ℹ️ NOTE: Track flagged explicit but no explicit words found
This is OK - artist may want explicit flag for themes/context
No action required (conservative flagging is fine)

Distributor Requirements

Most distributors (DistroKid, TuneCore, CD Baby) require:

  • Track-level flags: Each track marked explicit or clean
  • Album-level flag: If ANY track is explicit, album is explicit
  • Consistent metadata: Flag must match actual content

Consequences of wrong flags:

  • Explicit content marked clean → Potential removal from platforms, account issues
  • Clean content marked explicit → Reduced reach (filtered from some playlists) but no penalty

Rule: When in doubt, mark explicit. Under-flagging is worse than over-flagging.


Integration

This skill is called during:

  1. Ready to Generate Checkpoint - Before Suno generation
  2. Album Completion Checklist - Before release
  3. Manual review - Anytime with /explicit-checker [path]

Example Invocations

/explicit-checker artists/[artist]/albums/rock/dark-tide/
/explicit-checker artists/[artist]/albums/rock/dark-tide/tracks/01-the-tank.md

Remember

  • Case-insensitive matching (Fuck = fuck = FUCK)
  • Check variations (fucking, fucked, fucker)
  • Phonetic spellings count (fuk, sh1t if intentional)
  • Context matters less than presence - if the word is there, flag it
  • Album is explicit if ANY track is explicit
  • Override additions - Add artist/genre-specific explicit words
  • Override removals - Remove words for specific contexts (historical, literary)

GitHub 仓库

bitwize-music-studio/claude-ai-music-skills
路径: skills/explicit-checker
0
ai-musicai-music-toolsaudio-masteringclaudeclaude-codeclaude-code-plugin

相关推荐技能

content-collections

Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。

查看技能

polymarket

这个Claude Skill为开发者提供完整的Polymarket预测市场开发支持,涵盖API调用、交易执行和市场数据分析。关键特性包括实时WebSocket数据流,可监控实时交易、订单和市场动态。开发者可用它构建预测市场应用、实施交易策略并集成实时市场预测功能。

查看技能

creating-opencode-plugins

该Skill帮助开发者创建OpenCode插件,用于接入命令、文件、LSP等25+种事件。它提供了插件结构、事件API规范和JavaScript/TypeScript实现模式,适合需要拦截操作、扩展功能或自定义事件处理的场景。开发者可通过它快速构建响应式模块来增强OpenCode AI助手的能力。

查看技能

sglang

SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。

查看技能