agentleFS
bitwize-music-studiobitwize-music-studio/claude-ai-music-skills/skills/album-dashboard/SKILL.md

album-dashboard

Skill589 starsChanged 9 months agoCC0-1.0View on GitHub

Shows a structured progress dashboard for an album with percentage complete per phase, blocking items, and status breakdown. Use for a quick visual overview of album progress.

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 0 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Call get_album_progress(album_slug) — returns completion stats, phase detection, track counts by status

    line 51
  2. Very specific:

    Call find_album(name) — returns album metadata (genre, status, track list with per-track fields)

    line 52
  3. Very specific:

    Call list_track_files(album_slug) — returns tracks with file paths for any additional checks

    line 53
  4. Very specific:

    Check {audio_root}/artists/{artist}/albums/{genre}/{album}/ for WAV/FLAC files

    line 129

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Your Task

Input: $ARGUMENTS (album name)

Generate a structured progress dashboard for the specified album.


Album Dashboard

You generate a comprehensive progress report for an album, showing completion percentage per workflow phase, blocking items, and a structured status breakdown.


Workflow Phases

Track completion across these phases:

PhaseComplete When
1. ConceptAlbum README has title, genre, tracklist defined
2. ResearchRESEARCH.md and SOURCES.md exist (if source-based)
3. Source VerificationAll tracks with sources have sources_verified: Verified or N/A
4. LyricsAll tracks have lyrics in their Lyrics Box
5. PronunciationAll pronunciation table entries applied in lyrics
6. ReviewLyrics reviewed (no critical issues remain)
7. GenerationAll tracks have has_suno_link: true
8. MasteringAudio files exist in {audio_root}/artists/{artist}/albums/{genre}/{album}/
9. ReleaseAlbum status is "Released"

Data Collection

From MCP Server

  1. Call get_album_progress(album_slug) — returns completion stats, phase detection, track counts by status
  2. Call find_album(name) — returns album metadata (genre, status, track list with per-track fields)
  3. Call list_track_files(album_slug) — returns tracks with file paths for any additional checks

These three calls replace all manual state.json reads and file globbing.


Dashboard Format

ALBUM DASHBOARD
===============

[Album Title] ([genre])
Status: [status]

PROGRESS BY PHASE
─────────────────
[============================  ] 90%  Concept
[============================  ] 90%  Research
[========================      ] 75%  Source Verification
[====================          ] 63%  Lyrics Written
[================              ] 50%  Pronunciation
[============                  ] 38%  Reviewed
[========                      ] 25%  Generated
[                              ]  0%  Mastered
[                              ]  0%  Released

OVERALL: ████████░░░░░░░░ 47% complete

TRACK STATUS BREAKDOWN
──────────────────────
| # | Track | Status | Suno | Sources |
|---|-------|--------|------|---------|
| 01 | Track One | Final | link | Verified |
| 02 | Track Two | In Progress | — | Pending |
| 03 | Track Three | Not Started | — | N/A |
...

BLOCKING ITEMS
──────────────
! Track 02: Sources pending verification — blocks generation
! Track 05: No style prompt — blocks generation
! Track 07: Pronunciation table not applied — blocks generation

SUMMARY
───────
Tracks: [X complete / Y total]
Blocking: [N items]
Next action: [recommendation]

Phase Completion Calculation

Concept Phase

  • 100% if: Album README has title AND tracklist with actual track names (not template)
  • 50% if: README exists but tracklist is template placeholder
  • 0% if: No README

Research Phase (source-based albums only)

  • 100% if: RESEARCH.md AND SOURCES.md both exist with content
  • 50% if: Only one exists
  • N/A if: Album is not source-based (no tracks have sources_verified field or all are N/A)

Source Verification Phase

  • % = (tracks with Verified or N/A) / total tracks * 100
  • Skip tracks where sources_verified is N/A for the denominator

Lyrics Phase

  • % = (tracks with lyrics content) / total tracks * 100

Generation Phase

  • % = (tracks with has_suno_link=true) / total tracks * 100

Mastering Phase

  • Check {audio_root}/artists/{artist}/albums/{genre}/{album}/ for WAV/FLAC files
  • % = (audio files found) / total tracks * 100

Release Phase

  • 100% if album status is "Released", 0% otherwise

Remember

  1. Visual progress bars — Use ASCII progress bars for quick scanning
  2. Highlight blockers — Blocking items are the most important info
  3. Include next action — End with a clear recommendation
  4. Be accurate — Count carefully, don't estimate
  5. Handle missing data gracefully — If audio_root doesn't exist, mastering is 0%

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.