Verify Sources logo

Verify Sources

Organization
bitwize-music-studio
verify-sources

Captures human source verification for tracks, timestamps it, and updates track files. Use when sources need human review before generation.

Overview

Publisherbitwize-music-studio
Repositoryclaude-ai-music-skills
Skill nameverify-sources
Stars
546
Forks
130
Bundled files
Instructions only
LicenseCC0-1.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by bitwize-music-studio on GitHub. Read the source before you install it.

Installation

Install the Verify Sources AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/bitwize-music-studio/claude-ai-music-skills/tree/main/skills/verify-sources
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/bitwize-music-studio/claude-ai-music-skills.git /tmp/claude-ai-music-skills
mkdir -p .claude/skills
cp -r /tmp/claude-ai-music-skills/skills/verify-sources .claude/skills/verify-sources
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Verify Sources in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Verify Sources on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Verify Sources is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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

Frequently asked questions

What does the Verify Sources AI skill do?

Captures human source verification for tracks, timestamps it, and updates track files. Use when sources need human review before generation.

Why use Verify Sources on TypingMind?

Because you install it once and use it with any model. Verify Sources is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Verify Sources in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/bitwize-music-studio/claude-ai-music-skills/tree/main/skills/verify-sources. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Verify Sources?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Verify Sources?

As many as you like. As long as a model supports skills, you can use Verify Sources with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Verify Sources AI skill free?

Yes. It is published on GitHub by bitwize-music-studio under the CC0-1.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇