Integrations

ableton-live

Try it

Connect and operate the Loophole Bridge (Ableton Live MCP server). Use when the user wants to check Live/bridge prerequisites, wire an MCP client to Loophole, or run a Live editing recipe (humanize, build arrangement, batch rename, chord from prompt). Triggers: "is my Ableton bridge working", "set up loophole", "connect Claude to Ableton", "/doctor", "/setup".

What it does

A thin developer-experience layer for the Loophole Bridge, the MCP server that controls Ableton Live 12 over the official Extensions SDK. This skill closes the loop between "the bridge is installed" and "the agent uses it well." It does three things and nothing more.

The skill document

ableton-live (alias: loophole)

A thin developer-experience layer for the Loophole Bridge, the MCP server that controls Ableton Live 12 over the official Extensions SDK. This skill closes the loop between "the bridge is installed" and "the agent uses it well." It does three things and nothing more.

It never talks to Live directly. It does not embed tool logic, re-implement the bridge, or import any bridge or SDK code. The bridge is the only thing that touches the Live Object Model. Every Live operation in this skill is a call to one of the bridge's MCP tools.

What this skill does

  1. /doctor runs five prerequisite checks (Live running, extension installed, Node version, bridge port reachable, token present) and prints a PASS or a specific FIX line for each, then one verdict. See doctor.md. It never auto-runs /setup.
  2. /setup reads the port and bearer token from bridge.json, then emits one merge-safe MCP client block for Claude Code, Claude Desktop, or Cursor. It never writes or replaces a config file. See setup.md.
  3. Recipes are reusable snippets for common Live edits, each a named sequence of real bridge tool calls. See recipes/: humanize-midi, build-arrangement, batch-rename, chord-from-prompt.

How the pieces connect

flowchart LR
  U["User intent"] --> SK["ableton-live skill"]
  SK --> DOC["/doctor: 5 checks"]
  SK --> SET["/setup: emit merge-safe config block"]
  SK --> REC["recipes: tool sequences"]
  DOC -. "reads" .-> BJ["bridge.json"]
  SET -. "reads" .-> BJ
  REC --> BR["Loophole Bridge (MCP tools)"]
  BR --> LIVE["Ableton Live 12 Suite"]
  classDef accent fill:#E9A23B,stroke:#9A6A1A,color:#160F02,font-weight:bold;
  class BR accent

The skill reads bridge.json (for /doctor and /setup) and issues MCP tool calls (for recipes). It does not reach past the bridge.

The bridge tools the recipes use

The recipes reference only these registered MCP tools. No recipe invents a tool.

ToolRead or writeWhat it does
live_get_song_overviewreadtempo, scale, grid, counts, and current opaque track references
live_find_trackreadresolve a track name or substring to current opaque track references
live_list_clipsreadlist a track's session slots and clips with current opaque references
live_get_notesreadread all MIDI notes from one clip
live_set_tempowriteset the Set tempo in BPM
live_set_track_propswriteset a track's name, mute, solo, or arm in one serialized mutation
live_set_noteswritereplace all MIDI notes in one clip in one serialized mutation
live_create_trackwritecreate one empty MIDI or audio track
live_create_midi_clipwritecreate an empty MIDI clip in a session clip slot
live_set_paramwriteset one device parameter using its returned opaque session reference
live_insert_devicewriteinsert a built-in Live device on a track
live_render_trackwriterender a track's pre-FX audio over a beat range to a WAV

Mutation boundaries (read before running any recipe)

Each write tool is a separate mutation. Simple setters are designed to initiate their write inside one transaction, but real Live undo behavior remains an E2E gate. Never call a multi-tool recipe atomic. Creating a clip and then filling it uses two mutations because the SDK must return the clip before notes can be assigned. State the mutation count before writing and tell the user to inspect Live's undo history.

Beta limits the recipes inherit

These come from the bridge and extensions, not from the skill, and the recipes state them where they apply:

  • MIDI notes only. No automation, MIDI CC, clip gain, or routing API in this beta.
  • live_create_midi_clip targets Session clip slots, not the Arrangement timeline. The Session-to-Song extension preflights, then runs ordered clear, create, and populate mutation phases. Its receipt reports 0 intended undo entries for a no-op, 2 for cue-only, or 3 when it clears, creates, and populates. Partial errors expose the exact undoStepsToRestore.

All object references are opaque and session-scoped. Use the value returned by the current list or read call unchanged. Never construct a value such as lhref_trk_, and re-list after structural changes.

  • live_insert_device is built-in Live devices only (no third-party or VST).
  • live_render_track is pre-FX and practical for audio tracks.
  • Scale and tempo are read from the Set; the recipes do not guess a key. Assume 4/4 unless a scene signature is read.
  • User-invoked only.

Related skills

Join a video meeting as an AI bot with voice, avatar, and screenshare across four operating modes.

by johnpatternai21 installs8 stars

Generate and edit Draw.io, Mermaid, and Excalidraw diagrams from natural language using a structured JSON spec.

by nssa.io1.0k installs47 stars

Stores durable facts in a categorized, plain-markdown vault on disk, alongside your agent's built-in memory.

by Iván555 installs18 stars

Trade crypto, manage a multi-chain wallet, and query an AI analyst from one CLI.

by lowesyang162 installs109 stars

Find why your productivity system keeps failing, then apply the smallest fix — capacity math, bottleneck routing, durable local notes.

by Iván854 installs69 stars

More from othmanadi

Browse all skills

Persistent markdown planning files keep multi-step agent work organized and recoverable across context loss and /clear.

by othmanadi881 installs60 stars

Gives AI coding agents temporal awareness via a hook-backed ledger and decision rules. Activates whenever an agent reasons about recency, retry windows, memory staleness, deploy cooldowns, idle detection, or any "when / how long ago" question. Required for autonomous or long-running agents.

by othmanadi

Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging agent behavior, investigating errors, analyzing tool calls, checking memory operations, or examining agent performance. Automatically fetches recent traces and analyzes execution patterns. Requires langsmith-fetch CLI installed.

by othmanadi

A live visual Kanban board and continuity layer for long-running agentic tasks. Nobody wants to read a markdown plan or stare at raw HTML while an agent grinds for an hour, so Plandeck turns the plan into a board that organizes itself. Use it when a task is multi-step, long-running, or needs visual planning. Break the work into cards, declare which card depends on which, and Plandeck computes the critical path, auto-promotes cards to Ready as their dependencies clear, rolls up story-point estimates into an honest percent complete, and names the one next action. Plans, observed transitions, and last-known-good snapshots stay as plain files on disk, so they survive /clear and context resets. After a reset, run plandeck next to recover the single next move and its recent history. If the plan stops parsing, run plandeck doctor before using git. Renders a live board in the browser over SSE. Triggers on plan a project, break down a task, kanban board, task board, visual plan, long-running ag

by othmanadi

Build generative UI with OpenUI — any LLM provider, any backend language. Scaffold, integrate, validate.

by othmanadi1 installs

The barber for your coding agents' config. Weighs everything every agent on this machine loads (instruction files, memory, MCP servers, hooks, skills, commands, subagents, plugins, leftovers), prices each item in tokens from your own transcripts, and parks the dead weight with a receipt and an undo. Use this skill whenever the user mentions config bloat, a heavy or slow session start, tokens burned before the first word, too many MCP servers, hooks that are slow or fire on every prompt, skills or commands or plugins nobody invokes, cleaning up or auditing CLAUDE.md or AGENTS.md, Codex config, or asks what does my agent actually load, why is my context full before I type, which of these servers can I turn off, or what is this plugin costing me. Use it even when they only say the session feels bloated or startup got slow, and even when they mention /context, /doctor or /skill-doctor.

by othmanadi1 installs