返回技能列表

verify-sources

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

关于

The verify-sources skill guides developers through a human review checkpoint for music track sources before generation. It identifies tracks needing verification, timestamps approvals, and updates track files when sources require human validation. This ensures all sources are real and accessible, acting as a critical gate between research and Suno generation.

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/verify-sources

在 Claude Code 中复制并粘贴此命令以安装该技能

技能文档

Your Task

Input: $ARGUMENTS (album name)

Guide the user through source verification for all tracks with pending sources in the specified album.


Source Verification Skill

You facilitate the human source verification gate — the critical checkpoint between research and generation. No track should be generated on Suno until a human has verified that all sources are real, accessible, and accurately represented.


Step 1: Find the Album

  1. Call find_album(name) — fuzzy match by name, slug, or partial
  2. If not found, MCP returns available albums

Step 2: Identify Pending Tracks

  1. Call get_pending_verifications(album_slug="{album}") — returns pending tracks for the target album
  2. If no album specified, call get_pending_verifications() for all albums

If no pending tracks:

All tracks in [album] have been verified. No action needed.

If pending tracks exist, list them:

SOURCE VERIFICATION: [Album Title]
===================================

Tracks needing verification:
  1. [track-slug] — [track-title]
  2. [track-slug] — [track-title]
  ...

Total: X tracks pending verification

Step 3: Walk Through Each Track

For each pending track:

  1. Call extract_links(album_slug, track_slug) — extracts markdown links from the track file
  2. Call extract_links(album_slug, "SOURCES.md") — get the full citation list
  3. Read RESEARCH.md (if it exists) for evidence chains, confidence levels, and claim-to-source mappings — this gives the human verifier context for what each source is supposed to support, not just the URL
  4. Present sources to the user:
TRACK: [track-title]
--------------------
Sources referenced in this track:

  1. [Source Name](URL) — [brief description of what it supports]
  2. [Source Name](URL) — [brief description]
  ...

Please verify:
  - Each URL is accessible and contains the claimed information
  - No sources are fabricated or hallucinated
  - Claims in lyrics are supported by cited sources

Type "verified" to confirm, or describe any issues.
  1. Wait for user response:
    • If "verified" (or equivalent affirmative) → update the track
    • If issues reported → note them, ask user how to proceed

Step 4: Update Track Files

When user confirms verification for a track:

  1. Call update_track_field(album_slug, track_slug, "sources-verified", "✅ Verified (YYYY-MM-DD)") — updates the field and auto-rebuilds state cache

    • Use today's date
  2. Confirm the update:

✅ [track-title] — Sources verified (2025-02-06)
  1. Move to next pending track

Step 5: Update Album Status (Auto-Advance)

After processing all tracks, check if the album status should advance:

  1. Call get_album_progress(album_slug) — check how many tracks are now verified

  2. If ALL tracks are verified (no more pending):

    • Read the album README to check current album status
    • If album status is Research Complete:
      • Update album README: change | **Status** | Research Complete || **Status** | Sources Verified |
      • Report: "Album status advanced: Research Complete → Sources Verified"
    • If album status is In Progress:
      • Report: "All track sources verified. Album status stays In Progress (already past research phase)."
  3. If some tracks still pending:

    • Report how many remain and which ones
  4. Rebuild state cache: Call rebuild_state() to ensure MCP server has fresh data

  5. Summary report:

VERIFICATION COMPLETE
=====================
Album: [title]
Tracks verified: X/Y
Album status: [previous] → [new status]
Date: YYYY-MM-DD

All sources verified. This album is cleared for lyric writing.
Next step: /bitwize-music:lyric-writer [track] (write lyrics from verified sources)

Partial verification report (if some tracks still pending):

VERIFICATION PROGRESS
=====================
Album: [title]
Tracks verified this session: X
Tracks still pending: Y
  - [track-slug] — [reason if known]

Album status: unchanged ([current])
Resume verification later with /bitwize-music:verify-sources [album]

Handling Issues

If the user reports a problem with a source:

  1. Document the issue in the track file as a comment or note
  2. Do NOT mark as verified — keep status as Pending
  3. Suggest resolution:
    • Source URL broken → "Can you find an updated URL?"
    • Source doesn't support claim → "Should we revise the lyric, or find a supporting source?"
    • Source is fabricated → "I'll remove this source. Do we need to revise the track?"
  4. After resolution, re-present for verification

Remember

  • Never auto-verify — this skill exists specifically for human review
  • Present sources clearly — the user needs to actually check each URL
  • Date-stamp everything — verification dates matter for audit trail
  • One track at a time — don't rush through, each track matters
  • Update state cache — after changes, run indexer update so MCP server has fresh data

GitHub 仓库

bitwize-music-studio/claude-ai-music-skills
路径: skills/verify-sources
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