musical-dna — Claude Code skill: describe sound without names
Breaks an artist's music into techniques and sonic qualities so you can describe it without naming anyone. Useful for AI music prompts.
npx skills add jwynia/agent-skills --skill musical-dna -a claude-codeWhat musical-dna does
The skill takes 3–5 representative tracks and works through six dimensions: rhythmic foundation, harmonic architecture, instrumental techniques, production aesthetics, genre fusion and energy architecture. What comes out are standalone phrases like "slapped bass with muted ghost notes" or "swung triplet feel at 95 BPM" — usable on their own, with no artist attached.
Inside there is a dimension table and a three-step process: pick the tracks, deconstruct each dimension, then convert observations into prompt-ready phrases. Drums get kit composition, stick technique, kick and hi-hat patterns. Guitar gets pickup choice, effects chain and tuning. Harmony covers chord progressions, modes and melodic contour.
The rule throughout is how, not who. That matters if you need to sidestep a direct artist comparison — in a generation prompt, a release description, or when recombining elements into something new. The source text cuts off partway through song structure, so the energy and dynamics side is only partly covered.
What it helps with
- describe a track's sound without naming the artist
- build a technique vocabulary for a music generation prompt
- break a song into rhythm, harmony and production
- combine techniques from different genres in one description
- explain to a client how a track should sound
Example prompts for the agent
- Analyze the sound of these 4 tracks across the six dimensions and write phrases with no artist names
- Build a music generation prompt: rhythm, harmony, effects, production
- Describe the guitar tone and drum pattern so someone could reproduce it
How to install musical-dna
1Skills CLI (Vercel)
npx skills add jwynia/agent-skills --skill musical-dna -a claude-code2Manually: put the files in place
~/.claude/skills/musical-dna/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/musical-dna/
1Skills CLI (Vercel)
npx skills add jwynia/agent-skills --skill musical-dna -a codex2Manually: put the files in place
.agents/skills/musical-dna/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add jwynia/agent-skills --skill musical-dna -a cursor2Manually: put the files in place
.cursor/skills/musical-dna/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install jwynia/agent-skills musical-dna2Manually: put the files in place
.github/skills/musical-dna/SKILL.md1Skills CLI (Vercel)
npx skills add jwynia/agent-skills --skill musical-dna -a gemini-cli2Platform CLI
gemini skills install https://github.com/jwynia/agent-skills --path skills/creative/music/musical-dnaManually: put the files in place
.devin/skills/musical-dna/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add jwynia/agent-skills --skill musical-dna -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about musical-dna
How do I install musical-dna in Claude?
Run npx skills add jwynia/agent-skills --skill musical-dna -a claude-code. The skill lands at ~/.claude/skills/musical-dna/SKILL.md.
What does musical-dna do?
It deconstructs an artist's or band's music across six dimensions and turns the observations into descriptive phrases about technique and sound. The artist's name never appears in those phrases.
Which platforms support the skill?
Beyond Claude there are install commands for Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode. Each one differs by the -a flag.
Source text
SKILL.md · MIT
--- name: musical-dna description: Extract descriptive musical characteristics from any artist or band without using their name, building a vocabulary of sonic qualities for AI music generation, music description, or creative recombination. license: MIT metadata: author: jwynia version: "1.0" type: utility mode: evaluative domain: music --- # Musical DNA Analysis ## Purpose Extract descriptive musical characteristics from any artist or band **without using their name**, building a vocabulary of sonic qualities for AI music generation, music description, or creative recombination. Replace "sounds like [Artist]" with specific, technique-focused descriptions. ## Core Principle **How, not who.** Describe techniques, approaches, and sonic qualities rather than referencing artists. This enables: - Ethical AI music generation - Precise communication about sound - Creative recombination of elements - Genre-independent vocabulary ## Quick Reference: Six Dimensions | Dimension | What to Analyze | |-----------|-----------------| | Rhythmic Foundation | Drums, tempo, bass lines, time signatures | | Harmonic Architecture | Chords, modes, progressions, melodies | | Instrumental Techniques | Playing styles, effects, timbres | | Production Aesthetics | Recording feel, mix, spatial treatment | | Genre Fusion | Influence integration, innovation points | | Energy Architecture | Song structure, dynamics, emotional trajectory | --- ## Analysis Process ### Step 1: Select Representative Tracks Choose 3-5 tracks that capture: - Their most recognizable sound - Range across their catalog - Both typical and boundary-pushing examples ### Step 2: Systematic Deconstruction Work through each dimension, focusing on specific techniques and approaches. ### Step 3: Extract Prompt-Ready Phrases Convert observations into standalone descriptive phrases that work without artist context. --- ## Dimension 1: Rhythmic Foundation ### Drum Character - **Kit composition**: Acoustic, electronic, hybrid, sampled - **Stick technique**: Brushes, rods, mallets, standard sticks - **Snare approach**: Rim shots, ghost notes, cross-stick, tight vs. ringy - **Kick pattern**: Four-on-floor, syncopated, polyrhythmic, sparse - **Hi-hat work**: Open/closed patterns, 16th note rides, swung - **Fill style**: Busy, minimal, tom-heavy, snare rolls ### Time & Tempo - **Time signatures**: 4/4, 3/4, 6/8, odd meters (5/4, 7/8) - **Tempo range**: Locked BPM or flexible? Fast, mid, slow? - **Subdivision emphasis**: 8ths, 16ths, triplets, swung - **Polyrhythmic layering**: Multiple meters happening simultaneously ### Bass Line DNA - **Technique**: Fingered, picked, slapped, synth, upright - **Role**: Rhythmic anchor vs. melodic counterpoint - **Range**: Sub-bass heavy, mid-focused, full range - **Kick relationship**: Locked, complementary, independent **Example Phrases:** - "Driving 8th-note hi-hat over syncopated kick" - "Slapped bass with muted ghost notes" - "Swung triplet feel at 95 BPM" --- ## Dimension 2: Harmonic Architecture ### Chord Progressions - **Major/minor balance**: Predominantly one or mixed? - **Modal inflections**: Dorian darkness, Mixolydian brightness - **Chromatic movement**: Smooth voice leading, sudden shifts - **Chord density**: Triads, 7ths, extended (9ths, 11ths, 13ths) - **Harmonic rhythm**: Slow changes (1/bar) or rapid (2+/bar) ### Tonal Centers - **Key preferences**: Sharp keys, flat keys, open-string friendly - **Modulation**: None, gradual, sudden, frequent - **Scale choices**: Natural minor, harmonic minor, pentatonic, modes - **Dissonance tolerance**: Clean resolution, lingering tension ### Melodic Contour - **Range**: Wide intervals or narrow - **Movement**: Stepwise, leaping, arpeggiated - **Phrase length**: Short punchy or long flowing - **Repetition balance**: Hooks vs. development **Example Phrases:** - "Minor key with Dorian 6th inflection" - "Slow harmonic rhythm, one chord per 4 bars" - "Wide interval leaps in vocal melody" --- ## Dimension 3: Instrumental Techniques ### Guitar Approaches - **Pickup selection**: Bridge (bright), neck (warm), split - **Tone shaping**: Treble-forward, mid-scoop, bass-heavy - **Technique**: Fingerpicking, flatpicking, hybrid, percussive - **Tuning**: Standard, drop D, open tunings, baritone ### Effects Chain - **Distortion type**: Overdrive, fuzz, high-gain, clean - **Time-based**: Reverb (room, hall, plate), delay (analog, digital, tape) - **Modulation**: Chorus, phaser, flanger, tremolo, vibrato - **Pitch**: Octave, harmonizer, whammy - **Dynamics**: Compression (heavy, light, none) ### Other Instruments - **Keys/synth**: Analog warmth, digital precision, organ, piano - **Percussion**: Auxiliary (tambourine, shaker), world instruments - **Brass/strings**: Section vs. solo, dry vs. lush - **Electronics**: Samples, loops, glitches, synthesis **Example Phrases:** - "Neck pickup through mild tube overdrive" - "Slap-back delay with plate reverb" - "Fingerpicked acoustic with percussive body hits" --- ## Dimension 4: Production Aesthetics ### Spatial Characteristics - **Environment feel**: Professional studio, live room, bedroom, outdoor - **Reverb treatment**: Dry, intimate, expansive, cavernous - **Stereo field**: Wide, narrow, mono-compatible - **Depth staging**: Everything forward, layered front-to-back ### Mix Philosophy - **Prominence hierarchy**: Drums-first, vocal-forward, guitar-heavy - **Frequency allocation**: Each instrument's spectral home - **Dynamic range**: Compressed, dynamic, limiting - **Clarity vs. saturation**: Pristine separation vs. glued warmth ### Sonic Texture - **Signal path**: Clean, saturated, distorted, degraded - **High frequency**: Bright, airy, rolled-off, harsh - **Low end**: Tight, boomy, sub-heavy, absent - **Midrange**: Scooped, present, honky, balanced **Example Phrases:** - "Bedroom recording aesthetic with lo-fi saturation" - "Drum-forward mix with tight low end" - "Vintage tape warmth with rolled-off highs" --- ## Dimension 5: Genre Fusion Analysis ### Influence Mapping - **Primary foundation**: The dominant genre base (60%+) - **Secondary elements**: Strong secondary influence (20-30%) - **Tertiary accents**: Occasional flavor (10% or less) ### Integration Methods - **Temporal placement**: Genre X in verses, genre Y in choruses - **Instrumental assignment**: Drums from A, guitars from B - **Transition approach**: Seamless blend vs. jarring contrast - **Era mixing**: Vintage techniques + modern production ### Innovation Points - **Boundary crossing**: Where conventions are broken - **Novel combinations**: Unexpected genre marriages - **Signature fusion**: Their unique contribution **Example Phrases:** - "Math rock precision over post-punk foundation" - "Hip-hop production sensibility applied to folk songwriting" - "Grunge dynamics with shoegaze texture" --- ## Dimension 6: Energy Architecture ### Song Structure - **Intro character**: Atmospheric, punchy, fade-in, cold start - **Verse energy**: Pulled back, driving, building - **Chorus intensity**: Lift, explosion, subtle shift - **Bridge/breakdown**: Contrast, climax, reflection - **Outro approach**: Fade, stop, resolve, evolve ### Dynamic Range - **Intensity curves**: Gradual build, sudden shifts, flat line - **Peak placement**: Early, middle, late, multiple - **Release patterns**: Sudden drop, gradual decay ### Emotional Trajectory - **Mood arc**: Single state, journey, oscillation - **Tension cycles**: Build-release frequency - **Climax character**: Cathartic, devastating, transcendent **Example Phrases:** - "Slow build across 4 minutes to explosive final chorus" - "Sudden dynamic drops creating tension" - "Verse-chorus contrast via density rather than volume" --- ## Documentation Template ### One-Sentence DNA ``` [Rhythmic approach] + [harmonic character] + [instrumental signature] + [production aesthetic] ``` **Example:** "Syncopated post-punk drumming over minor modal progressions, angular clean guitar with chorus effect, dry room recording with bass-forward mix" ### Detailed Breakdown ```markdown ## Rhythmic Signature - Time feel: - Drum character: - Bass approach: - Syncopation style: ## Harmonic DNA - Chord tendencies: - Scale preferences: - Progression patterns: ## Instrumental Character - Guitar tone/technique: - Effects signature: - Other key instruments: ## Production Fingerprint - Recording aesthetic: - Mix characteristics: - Sonic texture: ## Genre Fusion Map - Primary foundation: - Secondary elements: - Innovation points: ## Energy Architecture - Typical structure: - Dynamic range: - Build patterns: ``` ### Extractable Prompt Elements List 5-10 standalone phrases usable in AI generation: - "..." - "..." --- ## Ethical Guidelines ### Do - Combine elements from multiple analyses - Focus on techniques and approaches - Build reusable vocabulary - Create novel fusions ### Don't - Copy complete profiles directly - Replicate signature riffs/melodies - Use as "sounds like [Artist]" substitute - Claim to reproduce specific artists --- ## Anti-Patterns ### 1. The Name Drop **Pattern:** Using artist names as shorthand instead of technique descriptions. "Sounds like Radiohead" instead of describing the actual sonic qualities. **Why it fails:** Defeats the entire purpose. Artist names are black boxes that convey different things to different people and may produce copyright issues in AI generation. **Fix:** Never use artist names in final output. For every "sounds like X," unpack what that actually means in terms of rhythm, harmony, production, etc. ### 2. The Single Dimension **Pattern:** Analyzing only one dimension (usually rhythm or production) while ignoring others. Producing incomplete profiles. **Why it fails:** Musical identity emerges from interaction of all dimensions. A rhythmic profile without harmonic context is useless for generation. **Fix:** Force yourself through all six dimensions. Even if an artist seems "about the guitar sound," their rhythmic choices matter. ### 3. The Genre Substitute **Pattern:** Describing music by genre labels instead of techniques. "Post-punk" instead of describing what makes it post-punk. **Why it fails:** Genre labels are contested categories, not techniques. AI systems need concrete instructions, not genre negotiations. **Fix:** Treat genre labels as starting points requiring unpacking. What rhythmic, harmonic, and production choices define this genre for this artist? ### 4. The Representative Track Trap **Pattern:** Analyzing one famous song and extrapolating to entire catalog. Missing range and evolution. **Why it fails:** Artists vary. Their most famous song may not be representative. Analysis from one track produces narrow profiles. **Fix:** Analyze 3-5 tracks from different periods and modes. Look for both constants and variations. ### 5. The Technical Overdose **Pattern:** Including so much technical detail that prompts become unusable. Every possible parameter specified. **Why it fails:** AI generation systems can't process unlimited context. Overly detailed prompts get truncated or confuse the model. **Fix:** Distill to 5-10 essential phrases. Prioritize what makes this artist distinct rather than comprehensive. ## Integration Points **Inbound:** - From listening to music you want to analyze **Outbound:** - To AI music generation prompts - To `lyric-diagnostic` for complete song analysis **Complementary:** - `lyric-diagnostic`: Lyrical analysis (words) - This skill: Musical analysis (sounds)
© jwynia · MIT · jwynia/agent-skills