livepilot 1.10.7 → 1.10.9

package/livepilot/skills/livepilot-performance-engine/SKILL.md

@@ -1,122 +0,0 @@
----
-name: livepilot-performance-engine
-description: This skill should be used when the user asks to "perform live", "what's safe to do during a show", "scene handoff", "energy flow", "performance mode", "safe moves", or wants live performance support with safety constraints.
----
-
-# Performance Engine — Safety-First Live Performance
-
-The performance engine enforces a strict safety model for live performance. Every action is classified before execution. Destructive operations are blocked. Risky operations require user confirmation. Only safe operations execute freely.
-
-## Safety Classification
-
-Every performance action falls into one of four tiers.
-
-### Safe — Execute Freely
-
-These actions are non-destructive and audience-invisible if they fail. Execute without asking.
-
-- `fire_scene` / `fire_clip` — launch scenes or clips (the core of live performance)
-- `set_track_send` with small delta — nudge send levels (reverb/delay throws)
-- `set_device_parameter` on mapped macros — macro knob adjustments
-- `set_track_mute` / `set_track_solo` — mute/solo toggles
-- `set_track_volume` with delta <= 3 dB — volume nudges
-- `set_track_pan` with delta <= 0.2 — subtle pan shifts
-- Filter sweeps via `set_device_parameter` on Auto Filter — smooth frequency movement
-
-### Caution — Require User Confirmation
-
-These actions are audible and may cause a noticeable glitch if wrong. Always ask before executing.
-
-- `set_tempo` with delta <= 5 BPM — tempo nudge (can destabilize synced elements)
-- `toggle_device` — enable/disable effects (may cause pops or silence)
-- `set_track_pan` with delta > 0.2 — large pan moves are disorienting live
-- `set_track_volume` with delta > 3 dB — large volume jumps
-
-Present the action to the user: "I will [action]. This may [risk]. Confirm?"
-
-### Blocked — Never Execute During Performance
-
-These actions risk audible disasters, data loss, or session corruption during a live show.
-
-- `delete_device` / `find_and_load_device` — device chain surgery causes audio interruption
-- `create_arrangement_clip` / `create_clip` / `delete_clip` — clip creation/deletion
-- `create_midi_track` / `create_audio_track` / `delete_track` — track structure changes
-- `add_notes` / `modify_notes` / `remove_notes` — note editing while playing
-- `set_clip_loop` / `set_clip_warp_mode` — clip property changes while playing
-- `flatten_track` / `freeze_track` — CPU-intensive operations
-- Any arrangement-view editing tools
-
-If the user requests a blocked action during performance mode, explain why it is blocked and suggest a safe alternative: "That requires editing the device chain, which can cause audio dropouts during a live show. Instead, try [safe alternative]."
-
-### Unknown — Treat as Blocked
-
-Any action not explicitly classified above defaults to blocked. Do not experiment with unclassified actions during a live performance.
-
-## Performance Loop
-
-### Step 1 — Get State
-
-Call `get_performance_state` to read the current session state:
-- Playing status, current tempo, time signature
-- Which scenes and clips are currently playing
-- Track arm states, solo/mute states
-- Current energy level estimate
-
-### Step 2 — Get Safe Moves
-
-Call `get_performance_safe_moves` to get a list of contextually appropriate safe actions based on the current state. The response is filtered by what makes musical sense right now — not just what is technically safe.
-
-### Step 3 — Check Safety
-
-Before executing any user request, call `check_safety(move_type)` to verify the classification. The response confirms: `safe`, `caution`, or `blocked` with an explanation.
-
-### Step 4 — Execute Safe/Caution Only
-
-- Safe: execute immediately
-- Caution: present to user, wait for confirmation, then execute
-- Blocked: refuse with explanation and alternative
-
-### Step 5 — Scene Handoff
-
-For transitioning between scenes (the primary live performance action), call `plan_scene_handoff(from_scene, to_scene)` to get a transition plan:
-
-- Which clips change between the scenes
-- Recommended launch timing (quantization)
-- Volume/send adjustments to smooth the handoff
-- Any tempo changes between scenes
-
-Execute the handoff plan using safe actions only.
-
-## Energy Flow
-
-During a live set, track the energy trajectory:
-
-1. `get_performance_state` includes an `energy_estimate` (0.0-1.0)
-2. Use scene ordering to build energy arcs: low-energy scenes for intros/breakdowns, high-energy for drops/peaks
-3. `plan_scene_handoff` accounts for energy delta — large energy jumps get transition suggestions
-
-## Performance Mode Entry
-
-When the user says "performance mode", "going live", or "starting the show":
-
-1. Call `get_performance_state` to verify the session is ready
-2. Confirm the safety model with the user: "Performance mode active. I will only execute safe actions freely and ask before caution-level moves. Destructive edits are blocked."
-3. Switch to a response style optimized for speed: short confirmations, no lengthy explanations mid-performance
-4. Prioritize scene launches and safe parameter nudges
-
-## Performance Mode Exit
-
-When the user says "done performing", "show's over", or "exit performance mode":
-
-1. Confirm: "Performance mode ended. Full editing capabilities restored."
-2. Resume normal operation with all tools available
-
-## Emergency Actions
-
-If something goes wrong during a live show:
-
-- `stop_all_clips` — emergency silence (use only if requested)
-- `set_master_volume(0.0)` — fade to silence
-- `set_track_mute` on the problem track — isolate the issue
-
-Never call `undo` during a live performance — it may revert a scene launch or clip state in unpredictable ways.

package/livepilot/skills/livepilot-performance-engine/references/performance-safety.md

@@ -1,98 +0,0 @@
-# Performance Safety Reference
-
-Complete classification of every LivePilot action for live performance contexts.
-
-## Safe Actions (No Confirmation Needed)
-
-| Action | Tool | Notes |
-|--------|------|-------|
-| Launch scene | `fire_scene` | Core performance action |
-| Launch clip | `fire_clip` | Individual clip triggering |
-| Stop clip | `stop_clip` | Individual clip stop |
-| Stop track clips | `stop_track_clips` | Clear a track |
-| Volume nudge (small) | `set_track_volume` | Delta <= 3 dB only |
-| Send nudge | `set_track_send` | Small adjustments to reverb/delay throws |
-| Macro nudge | `set_device_parameter` | On mapped macro controls only |
-| Filter sweep | `set_device_parameter` | On Auto Filter frequency parameter |
-| Mute toggle | `set_track_mute` | Non-destructive, reversible |
-| Solo toggle | `set_track_solo` | Non-destructive, reversible |
-| Pan nudge (small) | `set_track_pan` | Delta <= 0.2 only |
-| Master volume | `set_master_volume` | For overall level control |
-| Continue playback | `continue_playback` | Resume from pause |
-| Jump to cue | `jump_to_cue` | Navigate arrangement cue points |
-| Get state | `get_performance_state` | Read-only, always safe |
-| Get playing clips | `get_playing_clips` | Read-only |
-| Get scene matrix | `get_scene_matrix` | Read-only |
-| Any get_* tool | various | All read-only tools are safe |
-
-## Caution Actions (Require Confirmation)
-
-| Action | Tool | Risk |
-|--------|------|------|
-| Tempo nudge | `set_tempo` | May destabilize warped audio, synced plugins |
-| Device toggle | `toggle_device` | May cause audio pop, click, or silence |
-| Large pan move | `set_track_pan` | Disorienting for audience if sudden |
-| Large volume jump | `set_track_volume` | Jarring if delta > 3 dB |
-| Fire scene clips | `fire_scene_clips` | Selective scene launch, less predictable |
-| Set scene tempo | `set_scene_tempo` | Changes tempo on next scene fire |
-
-### Confirmation Protocol
-
-Present as: "[Action description]. Risk: [what could go wrong]. Confirm?"
-
-Keep confirmations short during performance. One line maximum.
-
-## Blocked Actions (Never During Performance)
-
-### Device Chain Surgery
-- `find_and_load_device` — loading causes audio thread hiccup
-- `delete_device` — removing active device causes dropout
-- `load_device_by_uri` — same as find_and_load
-- `load_browser_item` — browser loading is unpredictable latency
-
-### Track Structure
-- `create_midi_track` / `create_audio_track` / `create_return_track` — track creation pauses audio engine momentarily
-- `delete_track` — data loss, audio interruption
-- `duplicate_track` — CPU spike
-- `set_track_routing` — routing changes can cause feedback or silence
-
-### Clip Editing
-- `create_clip` / `delete_clip` / `duplicate_clip` — structural changes while playing
-- `set_clip_loop` / `set_clip_warp_mode` / `quantize_clip` — property changes on playing clips
-- `add_notes` / `modify_notes` / `remove_notes` — note editing mid-playback
-
-### Arrangement Editing
-- All `*_arrangement_*` tools — arrangement view editing during performance
-- `set_arrangement_automation` — automation lane changes
-
-### Heavy Operations
-- `freeze_track` / `flatten_track` — CPU-intensive, blocks audio thread
-- `start_recording` — may cause unexpected monitoring behavior
-- `capture_audio` / `capture_midi` — resource-intensive
-
-### Data Operations
-- `undo` / `redo` — unpredictable state reversion during live playback
-- `memory_learn` / `memory_delete` — non-urgent, save for after the show
-- `import_midi_to_clip` — file I/O during performance
-
-## Emergency Procedures
-
-### Audio Problem
-1. `set_track_mute(track_index, true)` on the problem track
-2. If problem persists: `set_master_volume(0.0)` for fade to silence
-3. Last resort: `stop_all_clips` for emergency silence
-
-### Feedback Loop
-1. `set_track_mute` on the suspected track immediately
-2. `set_track_send` to zero on all sends for that track
-3. Gradually unmute after identifying the routing issue
-
-### Wrong Scene Launched
-1. Immediately `fire_scene` on the correct scene
-2. Or `stop_all_clips` and restart from the correct point
-3. Do not use `undo` — it may revert more than intended
-
-### CPU Spike
-1. `set_track_mute` on the most CPU-heavy tracks (check `get_session_info` for device counts)
-2. `toggle_device` to bypass heavy effects (with caution confirmation skipped in emergency)
-3. If critical: `stop_all_clips` and restart with fewer active tracks

package/livepilot/skills/livepilot-release/SKILL.md

@@ -1,130 +0,0 @@
----
-name: livepilot-release
-description: Release checklist for LivePilot — run before ANY push, publish, or "update everything" request. Covers every file, channel, and artifact that references version numbers, tool counts, or project state.
----
-
-# LivePilot Release Checklist
-
-Run this checklist EVERY time the user says "update everything", "push", "release", "make sure everything is current", or similar.
-
-## 1. Version Strings (must ALL match)
-
-- [ ] `package.json` → `"version"`
-- [ ] `package-lock.json` → `"version"` (run `npm install --package-lock-only` if stale)
-- [ ] `server.json` → `"version"` (TWO locations: top-level and package)
-- [ ] `livepilot/.Codex-plugin/plugin.json` → `"version"` (primary Codex manifest)
-- [ ] `livepilot/.claude-plugin/plugin.json` → `"version"` (must match Codex plugin)
-- [ ] `.claude-plugin/marketplace.json` → `"version"` in plugins array
-- [ ] `mcp_server/__init__.py` → `__version__`
-- [ ] `remote_script/LivePilot/__init__.py` → `__version__` (log message auto-uses it)
-- [ ] `m4l_device/livepilot_bridge.js` → version in ping response
-- [ ] `CLAUDE.md` → header line
-- [ ] `livepilot/skills/livepilot-core/references/overview.md` → header line
-- [ ] `CHANGELOG.md` → latest version header
-- [ ] `docs/social-banner.html` → version display
-- [ ] `docs/M4L_BRIDGE.md` → ping response example
-
-**How to check:** `grep -rn "1\.[0-9]\.[0-9]" package.json server.json livepilot/.Codex-plugin/plugin.json livepilot/.claude-plugin/plugin.json .claude-plugin/marketplace.json mcp_server/__init__.py remote_script/LivePilot/__init__.py m4l_device/livepilot_bridge.js CHANGELOG.md CLAUDE.md livepilot/skills/livepilot-core/references/overview.md docs/social-banner.html docs/M4L_BRIDGE.md`
-
-## 2. Tool Count (must ALL match)
-
-Current: **323 tools across 45 domains**.
-Core (no M4L): **289**. Bridge (M4L): **30** (backed by 28 bridge commands).
-
-Verify: `grep -rc "@mcp.tool" mcp_server/tools/ | grep -v ":0" | awk -F: '{sum+=$2} END{print sum}'`
-
-Files that reference tool count:
-- [ ] `README.md` — header ("323 tools. 45 domains"), bridge section ("281 core...36 bridge")
-- [ ] `package.json` → `"description"`
-- [ ] `server.json` → `"description"`
-- [ ] `manifest.json` → `"description"`
-- [ ] `livepilot/.Codex-plugin/plugin.json` → `"description"` (primary Codex manifest)
-- [ ] `livepilot/.claude-plugin/plugin.json` → `"description"` (must match Codex plugin)
-- [ ] `.claude-plugin/marketplace.json` → `"description"`
-- [ ] `CLAUDE.md` → "323 tools across 45 domains"
-- [ ] `CONTRIBUTING.md` → tool count in intro
-- [ ] `livepilot/skills/livepilot-core/SKILL.md` — tool/domain count
-- [ ] `livepilot/skills/livepilot-core/references/overview.md` — tool/domain count
-- [ ] `docs/manual/index.md` — domain table with correct per-domain counts
-- [ ] `docs/manual/getting-started.md` — "281 core tools...36 bridge"
-- [ ] `docs/manual/tool-reference.md` — all domains present with correct counts
-- [ ] `docs/manual/tool-catalog.md` — all tools present (CI-tested)
-- [ ] `docs/manual/tool-catalog-generated.md` — regenerated from source
-- [ ] `docs/TOOL_REFERENCE.md` — all domains present with correct counts
-- [ ] `docs/M4L_BRIDGE.md` — "281 core tools...36 bridge"
-- [ ] `docs/social-banner.html`
-- [ ] `tests/test_tools_contract.py` → expected total count
-- [ ] `tests/test_skill_contracts.py` → catalog sync test passes
-
-**How to check:** `grep -rn "168\|139\|135\|127\|115\|107" --include="*.md" --include="*.json" --include="*.py" --include="*.html" . | grep -v node_modules | grep -v .git | grep -v __pycache__ | grep -v CHANGELOG`
-
-## 3. Domain Count
-
-Current: **45 domains**: transport, tracks, clips, notes, devices, scenes, mixing, browser, arrangement, memory, analyzer, automation, theory, generative, harmony, midi_io, perception, agent_os, composition, motif, research, planner, project_brain, runtime, evaluation, mix_engine, sound_design, transition_engine, reference_engine, translation_engine, performance_engine, song_brain, preview_studio, hook_hunter, stuckness_detector, wonder_mode, session_continuity, creative_constraints, device_forge, sample_engine, atlas, composer, experiment, musical_intelligence, semantic_moves.
-
-- [ ] All files that mention domain count say "45 domains"
-- [ ] Domain lists include ALL 45 (especially newer domains — they're the most often omitted)
-
-## 4. npm Registry
-
-- [ ] `npm view livepilot version` matches local version
-- [ ] If not: `npm publish`
-
-## 5. GitHub
-
-- [ ] Repo description matches current tool count and features
-- [ ] Topics are current (should include: ai, mcp, ableton, livepilot, max-for-live, audio-analysis)
-- [ ] Latest release matches current version (`gh release list`)
-- [ ] Release notes are current
-
-## 6. Plugin Cache
-
-- [ ] `~/.claude/plugins/cache/dreamrec-LivePilot/livepilot/` has current version directory
-- [ ] Old version directories removed
-- [ ] `~/.claude/plugins/installed_plugins.json` → `livepilot@dreamrec-LivePilot` entry: update `version`, `installPath`, `gitCommitSha`, `lastUpdated`
-
-## 7. Social/Promotional Assets
-
-- [ ] `docs/social-banner.html` — tool count, version, domain list
-- [ ] `docs/social-banner.png` — regenerated from HTML (must match)
-- [ ] GitHub repo social preview image (Settings > Social preview)
-
-## 8. Documentation Content
-
-- [ ] `README.md` — features match current capabilities, "Coming" section is accurate
-- [ ] `docs/manual/getting-started.md` — install instructions current
-- [ ] `docs/manual/tool-reference.md` — all 45 domains listed, all 323 tools present
-- [ ] `docs/TOOL_REFERENCE.md` — all 45 domains present with correct counts
-- [ ] `docs/M4L_BRIDGE.md` — architecture accurate, core/bridge counts correct
-
-## 9. Derived Artifacts
-
-- [ ] `m4l_device/LivePilot_Analyzer.amxd` — frozen JS matches source? All commands present?
-- [ ] If `livepilot_bridge.js` changed → amxd needs rebuilding in Max editor
-
-## 10. Code Consistency
-
-- [ ] `@mcp.tool()` count matches documented tool count: `grep -r "@mcp.tool" mcp_server/tools/ | wc -l`
-- [ ] No dead imports or unused code in recently changed files
-- [ ] Remote script version matches MCP server version
-- [ ] All tests pass: `python3 -m pytest tests/ -v`
-
-## 11. Automated Checks
-
-- [ ] `python scripts/sync_metadata.py --check` — all metadata in sync
-- [ ] `python -m pytest tests/test_command_boundary_audit.py` — no invalid TCP targets
-- [ ] `python -m pytest tests/test_move_annotations.py` — all moves annotated
-- [ ] `python -m pytest tests/test_capability.py` — capability contract works
-- [ ] `python -m pytest tests/test_capability_probe.py` — doctor probe works
-
-## 12. Release Smoke Board
-
-- [ ] Run through `docs/manual/release-smoke-board.md` scenarios against real Ableton session
-- [ ] All preview modes correctly labeled (audible/metadata/analytical)
-- [ ] Persistence survives server restart
-
-## Quick Verify Command
-
-```bash
-echo "=== Versions ===" && grep -h '"version"' package.json server.json manifest.json livepilot/.Codex-plugin/plugin.json livepilot/.claude-plugin/plugin.json .claude-plugin/marketplace.json | head -8 && grep __version__ mcp_server/__init__.py remote_script/LivePilot/__init__.py && echo "=== Tool count ===" && grep -rc "@mcp.tool" mcp_server/ | grep -v ":0" | awk -F: '{sum+=$2} END{print "Total:", sum}' && echo "=== Tests ===" && python3 -m pytest tests/ -q 2>&1 | tail -1
-```

package/livepilot/skills/livepilot-sample-engine/SKILL.md

@@ -1,105 +0,0 @@
----
-name: livepilot-sample-engine
-description: >
-  This skill should be used when the user asks to "sample", "chop",
-  "slice a loop", "find me a sample", "load a sample", "flip this",
-  "resample", "vocal chop", "found sound", "texture from", "turn this into",
-  "break", "one-shot", "load into Simpler", or when get_sample_opportunities
-  finds gaps in the song's sample usage.
----
-
-# Sample Engine — AI Sample Manipulation for Ableton Live
-
-The Sample Engine is LivePilot's intelligence layer for sample discovery,
-analysis, critique, and creative manipulation. It turns raw samples into
-musical elements through 29 techniques drawn from Dilla, Burial, Amon Tobin,
-Four Tet, and DJ Premier.
-
-## Philosophy: Surgeon vs Alchemist
-
-Every sample workflow is guided by one of two philosophies:
-
-- **Surgeon** — Precision. Match key, align tempo, carve frequencies, blend
-  seamlessly. The sample should sound like it was always part of the track.
-- **Alchemist** — Transformation. Reverse, stretch, destroy, rebuild.
-  The original creator shouldn't recognize their sample.
-- **Auto** (default) — Context decides. Building a clean layer? Surgeon.
-  Stuck and need surprise? Alchemist. The critics and intent determine which.
-
-## 6 MCP Tools
-
-| Tool | Purpose |
-|------|---------|
-| `analyze_sample` | Build SampleProfile — material type, key, BPM, recommendations |
-| `evaluate_sample_fit` | 6-critic battery — key, tempo, frequency, role, vibe, intent fit |
-| `search_samples` | Search Splice library, Ableton browser, and local filesystem |
-| `suggest_sample_technique` | Recommend techniques from the 29-recipe library |
-| `plan_sample_workflow` | End-to-end plan: analyze + critique + technique + compiled steps |
-| `get_sample_opportunities` | Analyze song for where samples could improve it |
-
-## Workflow Modes
-
-### Direct Request
-User asks to do something specific with a sample:
-```
-"Chop this vocal into a rhythm"
- -> analyze_sample -> evaluate_sample_fit(intent="rhythm")
- -> suggest_sample_technique -> execute
-```
-
-### Discovery Mode
-User wants to find and use a sample:
-```
-"Find me a dark vocal for this track"
- -> search_samples(query="dark vocal") -> present candidates
- -> user picks -> analyze -> critique -> plan -> execute
-```
-
-### Wonder Mode Integration
-When stuck, Wonder Mode can suggest sample-based variants:
-- 6 sample-domain semantic moves in the registry
-- Compiled plans require agent to supply `file_path` from prior `search_samples` results
-- Diagnosis detects: no_organic_texture, stale_drums, dense_but_static
-- Note: Wonder does not yet auto-call `search_samples` — the agent must chain the calls
-
-## Golden Rules
-
-1. **Always analyze before loading** — `analyze_sample` tells you what
-   the material is before you commit to a technique
-2. **Always critique before executing** — `evaluate_sample_fit` catches
-   key clashes, tempo mismatches, and frequency masking before they happen
-3. **Respect the intent** — "rhythm" and "texture" need different approaches
-   even for the same sample
-4. **Start from the nearest technique** — don't improvise a workflow when
-   a proven recipe exists in the library
-5. **Present both plans** — surgeon and alchemist. Let the user choose.
-
-## Material Types
-
-| Type | Detection | Best Simpler Mode | Best Warp Mode |
-|------|-----------|-------------------|----------------|
-| vocal | "vocal", "vox", "voice" in name | Slice (Region) | Complex Pro |
-| drum_loop | "drum", "break", "beat" in name | Slice (Transient) | Beats |
-| instrument_loop | "guitar", "piano", "synth" | Slice (Beat) | Complex Pro |
-| one_shot | "kick", "snare", "clap", short | Classic | Complex |
-| texture | "ambient", "pad", "drone" | Classic | Texture |
-| foley | "foley", "field", "recording" | Classic | Texture |
-| fx | "fx", "riser", "sweep" | Classic | Complex |
-| full_mix | full mix, long duration | Slice (Beat) | Complex Pro |
-
-## 6 Sample Critics
-
-Each scores 0.0-1.0 on one dimension of fitness:
-
-1. **Key Fit** — Circle-of-fifths distance from song key
-2. **Tempo Fit** — BPM match including half/double time
-3. **Frequency Fit** — Spectral overlap with existing mix
-4. **Role Fit** — Does this fill a missing role in the song?
-5. **Vibe Fit** — Taste graph alignment (if evidence exists)
-6. **Intent Fit** — Does the material serve the stated goal?
-
-## Reference Docs
-
-- `references/sample-techniques.md` — Full 29-technique catalog
-- `references/sample-critics.md` — Critic scoring details
-- `references/sample-philosophy.md` — Surgeon vs Alchemist guide

package/livepilot/skills/livepilot-sample-engine/references/sample-critics.md

@@ -1,87 +0,0 @@
-# Sample Critics — Scoring Reference
-
-## Key Fit Critic
-
-Uses circle-of-fifths distance between sample key and song key.
-
-| Distance | Score | Relationship | Action |
-|----------|-------|-------------|--------|
-| 0 fifths | 1.0 | Same key | Load directly |
-| 1 fifth | 0.85 | Relative major/minor, dominant/subdominant | Layer with care |
-| 2 fifths | 0.7 | Closely related | Works for most intents |
-| 3 fifths | 0.55 | Moderately distant | Transpose or use as texture |
-| 4 fifths | 0.4 | Distant | Heavy filtering needed |
-| 5+ fifths | 0.25-0.3 | Chromatic clash | Intentional tension only |
-| Unknown | 0.0 | Key not detected | Verify by ear |
-
-**Weight adjustment:** For "texture" intent, key_fit weight drops 50% (pitch matters less).
-
-## Tempo Fit Critic
-
-Compares sample BPM against session tempo including half/double time relationships.
-
-| Deviation | Score | Action |
-|-----------|-------|--------|
-| <1% | 1.0 | Exact match, no warping |
-| <2% | 0.95 | Near-exact, minimal warp |
-| <5% | 0.8 | Light warp, quality preserved |
-| <10% | 0.6 | Moderate warp, choose mode carefully |
-| <15% | 0.4 | Significant — use Texture mode for ambient |
-| >15% | 0.2 | Extreme — texture use only |
-| Half time | 0.9 | Set warp to half-time |
-| Double time | 0.9 | Set warp to double-time |
-| Unknown | 0.0 | Estimate from onsets or verify |
-
-## Frequency Fit Critic
-
-Requires M4L bridge spectral data. Without it, returns neutral 0.5.
-
-| Situation | Score | Action |
-|-----------|-------|--------|
-| Fills empty frequency gap | 1.0 | Perfect complement |
-| Partial overlap, manageable | 0.7 | Suggest EQ carving |
-| Heavy masking | 0.3 | Aggressive filtering or texture use |
-| Full spectrum into dense mix | 0.1 | Transformation source only |
-
-## Role Fit Critic
-
-Cross-references material_type against existing track names/roles.
-
-| Situation | Score | Action |
-|-----------|-------|--------|
-| Fills missing role | 1.0 | "No percussion texture — this fills the gap" |
-| Complements existing | 0.7 | "Adds variety to palette" |
-| Redundant | 0.3 | "Already 3 synth layers — use as texture" |
-
-## Vibe Fit Critic
-
-Uses TasteGraph when evidence exists (>0 entries). Otherwise neutral 0.5.
-
-Compares brightness, density, complexity of sample against user's taste profile.
-
-## Intent Fit Critic
-
-Compatibility matrix — how well the material serves the stated intent:
-
-| Material \ Intent | rhythm | texture | layer | melody | vocal | atmosphere | transform |
-|-------------------|--------|---------|-------|--------|-------|------------|-----------|
-| vocal | 0.6 | 0.6 | 0.8 | 0.9 | 1.0 | 0.5 | 0.9 |
-| drum_loop | 1.0 | 0.5 | 0.6 | 0.2 | — | 0.3 | 0.9 |
-| instrument_loop | 0.5 | 0.6 | 1.0 | 1.0 | 0.3 | 0.5 | 0.9 |
-| one_shot | 0.9 | 0.4 | 0.3 | 0.5 | — | 0.3 | 0.8 |
-| texture | 0.2 | 1.0 | 0.7 | 0.3 | 0.2 | 1.0 | 0.8 |
-| foley | 0.5 | 0.8 | 0.4 | — | — | 0.9 | 0.8 |
-| fx | 0.3 | 0.7 | 0.3 | — | — | 0.8 | 0.7 |
-
-## Composite Score
-
-Default weights:
-```
-overall = key_fit(0.20) + tempo_fit(0.20) + frequency_fit(0.20)
-        + role_fit(0.15) + vibe_fit(0.10) + intent_fit(0.15)
-```
-
-Weights shift by intent:
-- **texture/atmosphere:** key_fit 0.10, tempo_fit 0.10, frequency_fit 0.25
-- **rhythm:** tempo_fit 0.25, key_fit 0.10
-- **melody:** key_fit 0.30, intent_fit 0.20

package/livepilot/skills/livepilot-sample-engine/references/sample-philosophy.md

@@ -1,51 +0,0 @@
-# Surgeon vs Alchemist — The Dual Philosophy
-
-## When to be a Surgeon
-
-The sample should serve the song without drawing attention to itself.
-
-- **Building a clean layer** — matching key, tempo, frequency
-- **Adding percussion variety** — break layering under existing drums
-- **Key-matched melodic layers** — transpose and blend
-- **Chord stab extraction** — isolate and retrigger cleanly
-- **User says:** "blend", "layer", "match", "fit", "complement"
-
-**Surgeon priorities:** Key accuracy > tempo precision > frequency carving > volume balance
-
-## When to be an Alchemist
-
-The sample is raw material for transformation. The result should surprise.
-
-- **Stuck on a boring section** — inject chaos via destruction
-- **Need organic texture** — reverse, stretch, scatter
-- **Vocal as instrument** — chop syllables into rhythm
-- **One-sample challenge** — constraint breeds creativity
-- **User says:** "flip", "destroy", "mangle", "transform", "surprise me"
-
-**Alchemist priorities:** Novelty > texture > emotion > originality
-
-## Auto Mode Decision Tree
-
-```
-User said "blend/layer/match/fit"?     -> Surgeon
-User said "flip/destroy/mangle/weird"? -> Alchemist
-Wonder Mode (stuck rescue)?            -> Alchemist
-Intent is "texture" or "atmosphere"?   -> Alchemist
-Intent is "layer" or "melody"?         -> Surgeon
-Intent is "rhythm"?                    -> Both available, lean Surgeon for drums, Alchemist for vocals
-Intent is "transform" or "challenge"?  -> Alchemist
-No clear signal?                       -> Present both, let user choose
-```
-
-## The Masters
-
-| Producer | Philosophy | Signature |
-|----------|-----------|-----------|
-| J Dilla | Both | Surgical chop points, alchemical timing/swing |
-| Burial | Alchemist | Ghostly vocal fragments, vinyl crackle as instrument |
-| Amon Tobin | Alchemist | 80+ samples per track, serial destruction |
-| Four Tet | Alchemist | Found-sound countermelody, collage composition |
-| DJ Premier | Surgeon | Perfect stab isolation, rhythmic precision |
-| Madlib | Alchemist | Blind crate digging, cross-genre flipping |
-| RZA | Both | Cinematic soul sampling with dialogue and detuning |
-| Bon Iver | Surgeon | Pitch-shifted vocal stacks, harmonic layering |