Back to Skills

next-step

bitwize-music-studio
Updated 2 days ago
4 views
209
37
209
View on GitHub
Othergeneral

About

The next-step skill analyzes album project states and recommends the optimal single next action when users ask "what should I do next?" It determines workflow position by checking session context or scanning all albums, then provides specific guidance. This skill acts as a workflow router, using tools like Read, Glob, and bitwize-music-mcp to assess progress and direct next steps.

Quick Install

Claude Code

Recommended
Primary
npx skills add bitwize-music-studio/claude-ai-music-skills -a claude-code
Plugin CommandAlternative
/plugin add https://github.com/bitwize-music-studio/claude-ai-music-skills
Git CloneAlternative
git clone https://github.com/bitwize-music-studio/claude-ai-music-skills.git ~/.claude/skills/next-step

Copy and paste this command in Claude Code to install this skill

Documentation

Your Task

Input: $ARGUMENTS (optional album name)

Analyze current project state and recommend the single best next action.


Next Step Advisor

You analyze the current state of albums and tracks and recommend the optimal next action. You are a workflow router — you figure out WHERE the user is and tell them exactly WHAT to do next.


Logic

If No Album Specified

  1. Call get_session() — check last_album from session context
  2. If session has a last album, call get_album_progress(album_slug) to analyze it
  3. If no session context, call list_albums() to find all albums, then get_album_progress() on each to pick the most actionable
  4. If no albums exist, recommend creating one

If Album Specified

  1. Call find_album(name) — fuzzy match by name, slug, or partial
  2. Call get_album_progress(album_slug) — get status, phase, track counts
  3. Recommend next action based on detected phase

Decision Tree

Analyze album and track statuses to determine the optimal next action.

Instrumental detection: Check each track's frontmatter for instrumental: true or Track Details table for **Instrumental** | Yes. Instrumental tracks bypass the lyrics workflow (lyric-writer, pronunciation-specialist, lyric-reviewer) and go directly to /bitwize-music:suno-engineer for Style Box creation.

Album Status = "Concept"
  → "Define the album concept. Run the 7 Planning Phases with /bitwize-music:album-conceptualizer"

Album Status = "Research Complete"
  → Any tracks Sources Pending?
    YES → "Sources need verification. Review SOURCES.md and verify each source."
    NO  → First "Not Started" track instrumental?
      YES → "Create Style Box for instrumental track [name]. Use /bitwize-music:suno-engineer"
      NO  → "Ready to write! Pick a track and use /bitwize-music:lyric-writer"

Album has tracks with status "Not Started"
  → First not-started track instrumental?
    YES → "Create Style Box for instrumental track [name]. Use /bitwize-music:suno-engineer directly"
    NO  → "Write lyrics for track [first not-started track]. Use /bitwize-music:lyric-writer"

Album has tracks with status "In Progress" (lyrics partially written)
  → "Finish lyrics for track [first in-progress track]. Use /bitwize-music:lyric-writer"

Album has tracks with status "Sources Pending"
  → "Verify sources for track [name]. Check SOURCES.md, then update sources_verified field."

All tracks have lyrics (or Style Box for instrumentals), none generated
  → Has vocal tracks?
    YES → "Run /bitwize-music:pronunciation-specialist on vocal tracks, then /bitwize-music:lyric-reviewer for final QC, then /bitwize-music:pre-generation-check to validate all gates (instrumental tracks auto-skip lyrics gates)."
    NO (all instrumental) → "All Style Boxes ready! Run /bitwize-music:pre-generation-check to validate gates before generating on Suno."

Some tracks generated, some not
  → Any Generated tracks without ✓ in Generation Log Rating?
    YES → "Track [name] needs review. Listen and approve (mark ✓ in Generation Log) or regenerate.
           Style issue → /bitwize-music:suno-engineer to revise Style Box, then regenerate
           Lyrics issue → /bitwize-music:lyric-writer to fix lyrics, then regenerate
           Bad luck → Regenerate on Suno (non-deterministic, same settings may give better result)"
    NO  → "Generate track [first un-generated track] on Suno. Use /bitwize-music:suno-engineer"

All tracks generated, none Final
  → "All tracks generated! Review each track:
     Mark keepers with ✓ in Generation Log, regenerate rejected ones.
     Once all approved, batch-approve:
     Use update_track_field(album_slug, track_slug, 'status', 'Final') for each.
     Once all Final, album advances to Complete."

All tracks generated, some Final
  → Any Generated (non-Final) without ✓?
    YES → "Review track [name] — approve (✓) or regenerate"
    NO  → "All reviewed! Batch-approve remaining: update_track_field(album_slug, track_slug, 'status', 'Final') for each.
           Then import audio with /bitwize-music:import-audio, then master with /bitwize-music:mastering-engineer"

All tracks Final
  → "All tracks approved! Import audio with /bitwize-music:import-audio, then master with /bitwize-music:mastering-engineer"

Album Status = "Complete"
  → "Album is complete! Release with /bitwize-music:release-director"

Album Status = "Released"
  → "This album is released! Consider promotional content with /bitwize-music:promo-director"
  → Also suggest: "Start a new album? Check your ideas with /bitwize-music:album-ideas list"

Output Format

NEXT STEP
=========

Album: [name] ([genre]) — [status]
Progress: [X/Y tracks complete]

RECOMMENDED ACTION:
  [Clear, specific instruction with skill name]

WHY:
  [One sentence explaining why this is the right next step]

AFTER THAT:
  [Brief mention of what comes after this step]

When Analyzing Multiple Albums

If no album specified and multiple exist:

NEXT STEP
=========

You have X albums. Here's the most actionable:

PRIORITY 1: [album-name] ([genre])
  Status: [status] | Progress: [X/Y tracks]
  → [Recommended action]

Also in progress:
  - [album-2] — [brief status]
  - [album-3] — [brief status]

Or start something new:
  - /bitwize-music:album-ideas list (X ideas pending)
  - /bitwize-music:new-album

Priority Rules

When multiple albums are in progress, prioritize:

  1. Closest to completion — An album with 7/8 tracks done beats one with 2/10
  2. Unblocked work — An album waiting for source verification is blocked; one needing lyrics is not
  3. Last worked on — Favor the album from the last session (continuity)
  4. Higher track count — Bigger album = more investment to protect

Remember

  1. One clear recommendation — Don't list 5 options. Pick the best one.
  2. Include the skill name — "/bitwize-music:lyric-writer" not "write lyrics"
  3. Be specific about which track — "Write lyrics for track 04-the-escape" not "write some lyrics"
  4. Explain why briefly — Users trust recommendations they understand
  5. Don't repeat resume — If user just ran resume, don't re-print all the same info

GitHub Repository

bitwize-music-studio/claude-ai-music-skills
Path: skills/next-step
0
ai-musicai-music-toolsaudio-masteringclaudeclaude-codeclaude-code-plugin

Related Skills

llamaguard

Other

LlamaGuard is Meta's 7-8B parameter model for moderating LLM inputs and outputs across six safety categories like violence and hate speech. It offers 94-95% accuracy and can be deployed using vLLM, Hugging Face, or Amazon SageMaker. Use this skill to easily integrate content filtering and safety guardrails into your AI applications.

View skill

cost-optimization

Other

This Claude Skill helps developers optimize cloud costs through resource rightsizing, tagging strategies, and spending analysis. It provides a framework for reducing cloud expenses and implementing cost governance across AWS, Azure, and GCP. Use it when you need to analyze infrastructure costs, right-size resources, or meet budget constraints.

View skill

quantizing-models-bitsandbytes

Other

This skill quantizes LLMs to 8-bit or 4-bit precision using bitsandbytes, achieving 50-75% memory reduction with minimal accuracy loss. It's ideal for running larger models on limited GPU memory or accelerating inference, supporting formats like INT8, NF4, and FP4. The skill integrates with HuggingFace Transformers and enables QLoRA training and 8-bit optimizers.

View skill

dispatching-parallel-agents

Other

This Claude Skill dispatches multiple agents to investigate and fix 3+ independent problems concurrently. It is designed for scenarios involving unrelated failures that can be resolved without shared state or dependencies. The core capability is parallel problem-solving, assigning one agent per independent problem domain to maximize efficiency.

View skill