v2.0.0 to v3.0.0

92 added, 484 removed. Audit A to A.

What this update changes in the checks

No check changed: every fixed check gives the same answer before and after this update.

A tripped check is a label, not a verdict: read the matched text and the lines below. This week's updates that newly trip a check.

---
name: suno-ai-mastery
- description: Expert prompt engineering and music generation with Suno AI v4.5+ for professional-quality songs across all genres with advanced composition techniques
- version: 2.0.0
+ description: Design professional song and instrumental direction for the newest stable Suno model using genre, harmony, rhythm, arrangement, vocal persona, production, dynamics, and controlled iteration. Use for Suno composition strategy, arrangement, production troubleshooting, covers, extensions, and remasters.
+ version: 3.0.0
---
- # Suno AI Mastery v4.5+
+ # Suno AI Mastery
- You are a world-class Suno AI music producer with deep expertise in the **v4.5+** platform (released July 2025). This skill covers the complete Suno ecosystem including new professional audio tools, prompt engineering, and production workflows.
+ ## Freshness rule
+ Suno changes quickly. Do not hardcode an old model as current. When operating the UI, capture it and select the newest stable model available to the logged-in account unless the user requests another. Treat exact character limits and feature names as UI facts to verify, not memory.
+
Suno, Atlas Cloud, and MuAPI are paid services. Use Suno's product UI for its full editing suite. When API automation is needed, Atlas Cloud and MuAPI are optional routes to Suno generation; they are never required for prompt design. Confirm the model and price in the live provider catalog before submitting, and get user approval before any paid generation.
### Optional MuAPI Generation
The sibling `muapi_music.py` helper maps a song idea and style into MuAPI's asynchronous Suno API. It is dry-run by default:
```bash
- python3 <skill-directory>/muapi_music.py \\
- "Late-night city lo-fi piano with rain" \\
- --style "lo-fi hip-hop, mellow piano" \\
+ python3 <skill-directory>/muapi_music.py \
+ "Late-night city lo-fi piano with rain" \
+ --style "lo-fi hip-hop, mellow piano" \
--instrumental
```
Review the JSON payload first. To make exactly one paid submission, set `MUAPI_API_KEY` and add `--submit`. The helper never retries the generation POST; it only performs bounded GET polling for the returned request.
```bash
- python3 <skill-directory>/muapi_music.py \\
- "A hopeful song about finding your way home" \\
- --style "indie pop, warm guitar, layered vocals" \\
- --title "Way Home" \\
+ python3 <skill-directory>/muapi_music.py \
+ "A hopeful song about finding your way home" \
+ --style "indie pop, warm guitar, layered vocals" \
+ --title "Way Home" \
--submit
```
Use the live MuAPI model schema before generation. The current catalog lists this generation at $0.09 per request; confirm the price before submission. The completed result includes generated audio in `outputs`.
### Optional Atlas Cloud Generation
The sibling `atlas_music.py` helper maps this skill's inspiration or custom-lyrics prompt into Atlas Cloud's asynchronous audio API. It is dry-run by default:
```bash
python3 <skill-directory>/atlas_music.py \
"Late-night city lo-fi piano with rain" \
--instrumental
```
Review the JSON payload first. To make exactly one paid submission, set `ATLASCLOUD_API_KEY` and add `--submit`. The helper never retries the generation POST; it only performs bounded GET polling for the returned prediction.
```bash
python3 <skill-directory>/atlas_music.py \
"[Verse]\nNeon streets on a rainy night\n[Chorus]\nDrive on, drive on" \
--custom \
--title "Midnight Drive" \
--style "synthwave, female vocal, cinematic" \
--vocal-gender Female \
--submit
```
Use the live model catalog and schema rather than assuming model availability. For `suno/chirp-v4-5-all`, inspiration mode uses the prompt as a song description, while `--custom` uses it as lyrics. A completed prediction returns audio URLs in `outputs`.
---
- ## Platform Overview (v4.5+ Current State)
-
- ### What's New in v4.5+
-
- | Feature | Description |
- |---------|-------------|
- | **8-Minute Songs** | Generate coherent tracks up to 8 minutes (up from 4 min) |
- | **Add Vocals** | Layer AI vocals onto instrumental tracks |
- | **Add Instrumentals** | Add AI backing tracks to vocal recordings |
- | **Inspire** | Generate music based on your playlist's style/mood |
- | **Persona** | Imbue tracks with specific vocal characters |
- | **Replace** | Non-destructive section replacement |
- | **Extend** | Seamlessly extend existing generations |
- | **Remaster** | Upgrade quality of any Suno track |
- | **Covers** | Genre-switch while preserving melody |
- | **1,200+ Genres** | Expanded style vocabulary with better blending |
- | **Prompt Enhancement** | AI helper transforms ideas into detailed prompts |
-
- ### Generation Modes
-
- 1. **Create Mode**: Full song from text prompt
- 2. **Custom Mode**: Separate lyrics and style control
- 3. **Add Vocals**: Vocals over instrumentals
- 4. **Add Instrumentals**: Backing over vocals
- 5. **Inspire Mode**: Playlist-informed generation
- 6. **Covers Mode**: Re-style existing audio
- 7. **Extend Mode**: Continue existing generations
- 8. **Remaster Mode**: Quality upgrade existing tracks
-
- ---
-
- ## Prompt Engineering Framework
-
- ### The Colon Syntax (v4.5+ Best Practice)
-
- v4.5+ responds better to structured prompts using colons:
-
- ```
- Genre: melodic house
- Mood: euphoric, uplifting
- BPM: 124
- Instruments: analog synths, warm pads, crisp drums
- Vocal: female, ethereal, breathy
- Production: wide stereo, pristine clarity
- ```
-
- ### The 5-Tier Prompt Hierarchy
-
- **Tier 1: Genre Foundation** (Most Important)
- ```
- Primary: "Progressive House"
- Sub-genre: "Melodic Techno"
- Era/Influence: "Anjunadeep aesthetic"
- Fusion: "with orchestral elements"
- ```
-
- **Tier 2: Mood & Energy**
- ```
- Emotion: "euphoric", "melancholic", "aggressive"
- Energy: "high-energy", "laid-back", "building"
- Atmosphere: "dark", "ethereal", "gritty", "warm"
- ```
-
- **Tier 3: Instrumentation**
- ```
- Lead: Piano, synth lead, guitar
- Rhythm: 808s, live drums, percussion
- Texture: Pads, strings, atmospherics
- Vocal: Style, gender, delivery
- ```
-
- **Tier 4: Tempo & Rhythm**
- ```
- BPM: Exact number or range
- Feel: "swung", "straight", "syncopated"
- Groove: "driving", "laid-back", "bouncy"
- ```
-
- **Tier 5: Production & Structure**
- ```
- Mix: "wide", "intimate", "cinematic"
- Quality: "lo-fi", "pristine", "analog warmth"
- Dynamics: "building crescendo", "dynamic contrast"
- ```
-
- ---
-
- ## Artist Anchoring (Power Technique)
-
- Suno was trained on real music. Anchor prompts to artists for reliable results:
-
- ```
- "In the style of The Weeknd meets Daft Punk"
- "Influenced by Bon Iver and James Blake"
- "Hans Zimmer epic orchestral meets Aphex Twin glitch"
- ```
-
- **Best Practice**: Combine 2-3 artist references for unique fusion:
- ```
- "Radiohead atmospheric rock meets Massive Attack trip-hop
- with Sigur Rós ethereal vocals"
- ```
-
- ---
-
- ## Structure Tags (Custom Mode)
-
- In the **Lyrics** panel, use these tags:
-
- ### Essential Tags
- ```
- [Intro]
- [Verse]
- [Pre-Chorus]
- [Chorus]
- [Bridge]
- [Outro]
- [Instrumental]
- [Drop]
- ```
-
- ### Advanced Tags
- ```
- [Verse 1], [Verse 2] - Numbered sections
- [Hook] - Short memorable phrase
- [Ad-lib] - Improvised vocals
- [Breakdown] - Stripped-back section
- [Build] - Rising tension
- [Refrain] - Repeated phrase
- [Spoken Word] - Spoken delivery
- [Whispered] - Whispered vocals
- [Belted] - Powerful vocals
- [a] - Lowercase for soft delivery
- [A] - Uppercase for powerful delivery
- ```
-
- ### Structure Example
- ```
- [Intro - Atmospheric, 8 bars]
-
- [Verse 1]
- Lyrics here with natural rhythm
- Building the story line by line
-
- [Pre-Chorus - Building energy]
- Rising anticipation before the drop
-
- [Chorus - Full power, anthemic]
- The main hook that sticks in your head
- Repeat it loud, let it spread
-
- [Verse 2]
- Second verse development
- New perspective on the theme
-
- [Bridge - Stripped back, emotional]
- Different energy, moment of reflection
-
- [Final Chorus - Maximum intensity]
- Everything we've built releases here
-
- [Outro - Fade with atmosphere]
- ```
-
- ---
-
- ## Vocal Direction System
-
- ### Voice Characteristics
- ```
- Gender: male, female, androgynous
- Range: soprano, alto, tenor, baritone, bass
- Age: youthful, mature, aged
- Quality: raspy, smooth, breathy, powerful, crystalline
- ```
-
- ### Delivery Styles
- ```
- Whispered → Spoken → Sung → Belted → Screamed
- Intimate → Present → Powerful → Explosive
-
- Examples:
- "Whispered intimate delivery building to powerful belted chorus"
- "Raspy baritone, Johnny Cash meets Leonard Cohen"
- "Ethereal soprano with Björk-like unconventional phrasing"
- ```
-
- ### Vocal Techniques
- ```
- Vibrato: "rich vibrato", "straight tone", "subtle vibrato"
- Runs: "melismatic R&B runs", "gospel-style riffs"
- Harmonies: "layered 3-part harmonies", "octave doubling"
- Effects: "vocoder", "auto-tune effect", "choir"
- ```
-
- ### v4.5+ Vocal Improvements
- The new model supports:
- - Microtonal pitch variation (more human-like)
- - Formant shifting (richer tonal variety)
- - Emotional range from whisper-soft to vibrato-rich
- - Better breath sounds and vocal artifacts
-
- ---
-
- ## Genre-Specific Templates
-
- ### Hip-Hop/Trap
- ```
- Genre: Modern trap with melodic elements
- BPM: 140
- Instruments: Heavy 808s, crisp hi-hats, atmospheric synths,
- sampled vocal chops
- Vocal: Confident rap delivery, melodic hooks, ad-libs
- Production: Hard-hitting, spacious mix, vinyl texture
- ```
-
- ### EDM/House
- ```
- Genre: Progressive house with trance undertones
- BPM: 126
- Instruments: Lush synth pads, driving bassline, euphoric leads,
- precise electronic drums
- Vocal: Ethereal female, chopped and pitched
- Production: Wide stereo, sidechain pumping, festival-ready
- Drop: Massive with layered synths and sub bass
- ```
-
- ### R&B/Soul
- ```
- Genre: Neo-soul meets contemporary R&B
- BPM: 75
- Instruments: Warm Rhodes, melodic bass, brush drums,
- subtle strings
- Vocal: Smooth melismatic delivery with runs and riffs
- Production: Intimate, warm analog saturation, sensual
- ```
-
- ### Rock/Alternative
- ```
- Genre: Alternative rock with shoegaze textures
- BPM: 128
- Instruments: Layered distorted guitars, driving drums,
- ambient pedal effects, melodic bass
- Vocal: Raw and emotional, quiet-loud dynamics
- Production: Wall of sound in chorus, intimate verses
- ```
-
- ### Orchestral/Cinematic
- ```
- Genre: Epic orchestral hybrid, film score quality
- BPM: Building from 90 to 140
- Instruments: Full orchestra (strings, brass, woodwinds),
- taiko drums, modern hybrid elements
- Production: Cinematic wide mix, Hans Zimmer influence
- Dynamics: Quiet intimate opening building to massive climax
- ```
-
- ### Lo-Fi/Chill
- ```
- Genre: Lo-fi hip hop with jazz elements
- BPM: 85
- Instruments: Dusty piano samples, mellow bass, soft drums,
- vinyl crackle, rain ambience
- Vocal: Subtle vocal samples, mostly instrumental
- Production: Warm, compressed, nostalgic bedroom feel
- ```
-
- ---
-
- ## New v4.5+ Workflows
-
- ### Add Vocals Workflow
- For adding vocals to instrumental tracks:
-
- 1. Upload or select instrumental track
- 2. Craft vocal-specific prompt:
- ```
- Vocal Style: Soulful female with gospel influence
- Delivery: Powerful and emotive with melismatic runs
- Lyrics: [Your lyrics with structure tags]
- Blend: Sit prominently in mix, complement existing arrangement
- ```
-
- ### Add Instrumentals Workflow
- For adding backing to vocal recordings:
-
- 1. Upload vocal track
- 2. Craft instrumental prompt:
- ```
- Genre: Contemporary pop production
- Match: Complement existing vocal melody and rhythm
- Instruments: Clean electric guitar, warm synth bass,
- programmed drums, subtle strings
- Production: Modern radio-ready, leave space for vocals
- ```
-
- ### Inspire Workflow
- Generate from your playlists:
+ ## Translate intent into seven musical layers
- 1. Create/select a playlist with reference tracks
- 2. Suno analyzes style, mood, sonic traits
- 3. Add guidance prompt:
- ```
- Inspired by my playlist but with:
- - More electronic production elements
- - Faster tempo around 128 BPM
- - Female vocals instead of male
- - Brighter, more euphoric mood
- ```
+ 1. **Form:** song length, section sequence, bar/energy proportions.
+ 2. **Rhythm:** BPM range, meter, pocket, swing/syncopation, density.
+ 3. **Harmony:** tonal center/mode, harmonic tension, cadence character, rate of change.
+ 4. **Melody:** register, contour, motif behavior, hook interval/mouthfeel.
+ 5. **Timbre:** focal instruments, supporting textures, negative space.
+ 6. **Performance:** vocal persona, articulation, dynamics, ensemble behavior.
+ 7. **Production:** era without trademarks, spatial image, saturation/clarity, transient character, dynamic arc.
- ### Persona Feature
- Create consistent vocal characters:
+ A prompt is not a keyword dump. It is an arrangement brief compressed into natural language.
- ```
- Persona: "Midnight Soul"
- Voice: Deep baritone with slight rasp
- Influence: Barry White meets Frank Ocean
- Delivery: Smooth, intimate, seductive
- Use for: All R&B and soul tracks in this project
- ```
+ ## Style prompt order
- ### 8-Minute Extended Compositions
- For longer-form music:
+ Use this order so the model receives priorities clearly:
+ ```text
+ Genre/fusion; emotional state and energy; tempo/meter/pocket; focal instrumentation; vocal persona and delivery; section-to-section dynamic journey; production and spatial character; ending behavior.
```
- Structure for 8-minute progressive track:
- [Intro - 0:00-0:45]
- Atmospheric, minimal, setting the scene
-
- [First Movement - 0:45-2:30]
- Verse-chorus structure, establishing themes
-
- [Development - 2:30-4:00]
- New elements, building complexity
-
- [Breakdown - 4:00-5:00]
- Stripped back, emotional core
+ Name 3–6 important instruments. Over-specification makes arrangements muddy and generic.
- [Build - 5:00-5:45]
- Rising tension toward climax
+ ## No named-artist shortcuts
- [Peak - 5:45-7:00]
- Maximum intensity, all elements
+ Do not write "in the style of", "sounds like", or named-voice references. Translate a reference into attributes:
+ - decade or production era;
+ - vocal range, grain, intimacy, articulation;
+ - drum pocket and bass behavior;
+ - harmonic vocabulary;
+ - arrangement density;
+ - spatial and saturation choices;
+ - emotional/dynamic movement.
- [Resolution - 7:00-8:00]
- Gentle descent, callback to opening, fade
- ```
+ This produces more original work and avoids imitation/voice-clone requests.
- ---
+ ## Vocal persona
- ## Editing Tools (v4.5+)
+ Specify a person-like performance, not only gender:
+ - range: contralto, alto, tenor, baritone, etc.;
+ - grain: clear, smoky, weathered, breath-edged, dry;
+ - placement: close-mic, room-present, distant, choir-backed;
+ - articulation: conversational, legato, clipped, melismatic, restrained;
+ - arc: almost spoken → sung → open belt → fragile close;
+ - harmony behavior: unison, thirds, octave doubles, call-response.
- ### Replace
- Replace specific sections while keeping the rest:
- - Select problematic section
- - Describe what you want instead
- - Maintains coherence with surrounding sections
+ Avoid "perfect" or celebrity voice language. Human detail beats generic power.
- ### Extend
- Continue a track seamlessly:
- - Works from any point in the song
- - Maintains musical coherence
- - Great for building out ideas
+ ## Dynamic architecture
- ### Remaster
- Upgrade audio quality:
- - Apply to older v3.x generations
- - Improves clarity and production
- - Doesn't change musical content
+ Map energy by section. A useful default is not a rule:
- ### Covers
- Re-style while preserving melody:
- ```
- Original: Folk ballad at 70 BPM
- Cover prompt: "Epic orchestral arrangement,
- full symphony, cinematic production,
- preserve original melody and lyrics"
+ ```text
+ Intro 2 → Verse 4 → Pre 6 → Chorus 8 → Verse 5 → Bridge 3/7 → Final Chorus 9 → Outro 2
```
- ---
-
- ## Troubleshooting Guide
+ Contrast is the engine: sparse/dense, dry/wet, low/high register, solo/stacked, held/pulsed, silence/impact. The final chorus should change because the story changed.
- ### Problem: Muddy Vocals
- ```
- Solutions:
- - Add "clear vocals prominent in mix"
- - Specify "sparse instrumentation to create space"
- - Use "dry vocal with subtle room reverb"
- - Try "acapella intro to establish vocal clarity"
- ```
+ ## Structural and performance tags
- ### Problem: Generic/Boring Output
- ```
- Solutions:
- - Add artist anchoring (2-3 specific references)
- - Use unusual genre fusion
- - Specify dynamic contrast (quiet-loud)
- - Add unique instrumentation
- - Include emotional arc description
- ```
+ Use only high-value tags in lyrics:
+ - `[Intro]`, `[Verse 1]`, `[Pre-Chorus]`, `[Chorus]`, `[Bridge]`, `[Outro]`;
+ - one performance cue such as `intimate`, `harmonized`, `spoken`, `stripped`, `full lift`;
+ - an instrumental cue only when arrangement depends on it.
- ### Problem: Structure Incoherence
- ```
- Solutions:
- - Use Custom Mode with explicit structure tags
- - Specify "cohesive song structure"
- - Add "distinct section contrast"
- - Use "memorable hook" and "strong chorus"
- ```
+ Keep 1–3 cues per section. Contradictory or crowded tags reduce control.
- ### Problem: Wrong Energy/Tempo
- ```
- Solutions:
- - Specify exact BPM: "exactly 128 BPM"
- - Use multiple tempo descriptors
- - Describe energy arc: "building from 90 to 140 BPM"
- - Add feel descriptors: "driving", "laid-back", "hypnotic"
- ```
+ ## Exclusions
- ### Problem: Off-Pitch Vocals
- ```
- Solutions:
- - Regenerate (vocal tuning varies per generation)
- - Add "professional trained vocalist"
- - Specify "on-pitch melodic delivery"
- - Try different vocal style descriptors
- - Use Remaster to improve existing generation
- ```
+ Use Exclude Styles to protect the thesis. Typical exclusions:
+ - unwanted vocal type or choir;
+ - genre drift;
+ - excessive distortion, trap hats, festival drops, cinematic swells;
+ - spoken samples;
+ - long intro/outro;
+ - abrupt ending;
+ - dense midrange for narration beds.
- ---
+ Do not use exclusions to negate half the prompt. If the positive direction is unclear, rewrite it.
- ## Complete Prompt Examples
+ ## Controlled iteration
- ### Example 1: Modern Pop Hit
- ```
- Genre: Contemporary pop with 80s synthwave influence
- BPM: 118
- Mood: Nostalgic yet euphoric, summer anthem energy
- Instruments: Analog synths, punchy drums, groovy bass,
- shimmering arpeggios, subtle guitar
- Vocal: Male, The Weeknd influence, smooth with falsetto moments
- Production: Wide stereo, radio-ready polish, big reverb on snare
- Structure: Catchy verse, explosive chorus with layered vocals,
- stripped bridge, triumphant final chorus
- ```
+ 1. **One Create action** yields the initial take pair.
+ 2. Review both against the same brief; do not move the goalposts.
+ 3. Name the strongest 15–30 seconds and the single largest failure.
+ 4. Choose one operation: regenerate prompt, replace section, extend, cover, or remaster.
+ 5. Change one dominant variable at a time so learning compounds.
- ### Example 2: Emotional Ballad
- ```
- Genre: Piano ballad with orchestral swells
- BPM: 65
- Mood: Heartbreaking, vulnerable, cathartic release
- Instruments: Solo grand piano intro, building to full strings,
- subtle cello, distant choir in finale
- Vocal: Female soprano, Adele-like power with intimate verses,
- raw emotion, vibrato-rich sustained notes
- Production: Intimate and close in verses, wide and cinematic
- in chorus, natural concert hall reverb
- Dynamics: Whispered opening building to full-power climax
- ```
+ For extensions, restate the core genre, vocal persona, and ending target to reduce drift.
- ### Example 3: Festival EDM
- ```
- Genre: Melodic dubstep meets future bass
- BPM: 150
- Mood: Euphoric, emotional, high-energy release
- Instruments: Massive supersaw leads, wobble bass, crisp drums,
- vocal chops, white noise risers
- Vocal: Ethereal female hook, pitched and chopped
- Production: Festival-ready, massive drops, sidechain compression,
- Illenium meets Seven Lions
- Drop: Heavy yet melodic, emotional chord progression,
- rhythmic bass design
- Build: 32-bar tension with filter sweep and snare roll
- ```
+ ## Troubleshooting
- ---
+ - **Generic output:** strengthen premise, focal instrument, rhythmic pocket, and dynamic contradiction; remove adjectives.
+ - **Muddy vocal:** reduce instrumentation, request close/dry vocal and restrained midrange, use a sparse verse.
+ - **Flat song:** define section jobs and explicit energy contrast; add a silence or stripped bridge.
+ - **Wrong tempo/feel:** state BPM plus pocket (half-time, swung, straight, syncopated).
+ - **Mispronunciation:** spell out numbers/acronyms and respell the problem word phonetically.
+ - **Overlong intro:** state immediate vocal entry or exact short intro behavior; exclude long intro.
+ - **Weak ending:** specify hard stop, final held chord, unresolved cutoff, or long fade.
- ## Iteration Best Practice
+ ## Output
- **Generation 1: Explore**
- - Broad prompt, test concept
- - Listen for: genre feel, mood accuracy, vocal style
+ Provide one recommended production direction and, only when useful, one deliberate alternate that changes a single thesis variable. Include why the recommendation best serves the emotional contract.
- **Generation 2: Refine**
- - Add specifics based on Gen 1 learnings
- - Adjust what didn't work, keep what did
+ ## Shared fundamentals and provider boundary
- **Generation 3: Polish**
- - Full detail including dynamics and structure
- - Production quality specifications
+ Read the relevant modules in `https://github.com/frankxai/agentic-music-producer-os/blob/18dc9bee02001befb3a2a3bd7747b78f798dff13/docs/MUSIC-FUNDAMENTALS.md`, then `https://github.com/frankxai/agentic-music-producer-os/blob/18dc9bee02001befb3a2a3bd7747b78f798dff13/docs/PROVIDER-CAPABILITIES.md` and `https://github.com/frankxai/agentic-music-producer-os/blob/18dc9bee02001befb3a2a3bd7747b78f798dff13/docs/MUSIC-FACTORY-CONTRACT.md` when selecting tools or executing production. Canonical public source: https://github.com/frankxai/agentic-music-producer-os. The craft precedes the provider packet.
- **Generation 4-6: Perfect**
- - Generate multiple takes
- - Use Replace for problem sections
- - Apply Remaster if needed
+ Suno v6 is the documented baseline checked 2026-10-01; capture the actual account model, settings, limits and credit cost before operating. No official public generation API was verified. Preserve the approved lyrics across adapters. Score/text analysis and a prompt review do not prove audio quality. Record real listening and measurements separately; keep unknown values null. Personal preferences and artist canon remain in their owner project.
- ---
+ Resolve `docs/...` paths from the repository root, not from the skill folder. If using only this skill outside a checkout, read the same named documents from the canonical public source.
- ## Integration Notes
- This skill integrates with:
- - **suno-prompt-architect**: for ambient and meditation tracks
- - **brand-voice**: for branded content that must sound like the brand
+ ## Current craft and production integration
- ---
+ Checked 2026-10-01. Use the public [music fundamentals](https://github.com/frankxai/agentic-music-producer-os/blob/18dc9bee02001befb3a2a3bd7747b78f798dff13/docs/MUSIC-FUNDAMENTALS.md), [provider register](https://github.com/frankxai/agentic-music-producer-os/blob/18dc9bee02001befb3a2a3bd7747b78f798dff13/docs/PROVIDER-CAPABILITIES.md) and [factory contract](https://github.com/frankxai/agentic-music-producer-os/blob/18dc9bee02001befb3a2a3bd7747b78f798dff13/docs/MUSIC-FACTORY-CONTRACT.md). They cover harmony/voice leading, groove, motif, prosody, hooks, form, vocals, arrangement, low end, mixing, measured delivery, provenance and durable jobs. Load only the modules needed for this task.
- *Master v4.5+ to unlock professional AI music production. Every great track starts with a great prompt—and now you have the tools to edit, extend, and perfect until it's exactly right.*
+ Keep local artist/persona canon, identity, preferences and account entitlements scoped to this project. Shared craft does not assign a singer or overwrite canon. Select the current account-visible Suno model (documented baseline v6); no official public Suno generation API was verified. Lyria, Eleven Music and fal MiniMax Music 3 have separate documented API routes and constraints. A skill or MCP tool is not a connected generation account.
- **Sources:**
- - [Suno v4.5 Official Blog](https://suno.com/blog/introducing-v4-5)
- - [Suno Help: Better Prompts](https://help.suno.com/en/articles/5782977)
+ Preserve approved lyrics across adapters. Prepare, authorize/reserve, submit, reconcile, archive, listen, measure, attest rights and stage release separately. Bind receipts to exact contract/asset hashes. Never infer audio quality, measured BPM, playback, rights or publication from a text review or completed job. Unknown paid submissions remain held for reconciliation; no blind rerender.