agentleFS
PantaniPantani/ableton-mind/.claude/skills/local-copilot/SKILL.md

local-copilot

Skill9 starsChanged 5 months agoMITView on GitHub

Use this for any ableton-mind local LLM/copilot work: Ollama, OpenAI-compatible endpoints, `ableton-mind chat`, `ableton-mind ask`, `llm-run`, tool tiers, safe/default read-only policy, local browser UI, headless prompts, model pull, handoff, or docs/tests for the local copilot. Also use for follow-ups like re-run, update, debug, harden, add a model backend, or port more tdmcp copilot behavior.

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 3 are distinctive, and 7 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 7

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill when adding, debugging or extending the ableton-mind local LLM feature.

    line 8
  2. Very specific:

    Read src/llm/config.ts, src/llm/tools.ts, src/llm/agent.ts, src/llm/server.ts and src/cli/chat.ts.

    line 12
  3. Very specific:

    Read tests/llm-local-copilot.test.ts and the latest relevant QA report.

    line 13
  4. Very specific:

    Check _workspace/tdmcp-compatible-features.md for deferred tdmcp-inspired items.

    line 14
  5. Very specific:

    Keep the default tier read-only (safe).

    line 19
  6. Distinctive:

    Never expose destructive or broad routing/mixer tools to a local model without a safety review.

    line 20
  7. Very specific:

    Do not copy TouchDesigner-specific prompts, paths or tools from tdmcp.

    line 23
  8. Very specific:

    Prefer explicit JSON Schemas in src/llm/tools.ts over new schema-conversion dependencies.

    line 27
  9. Distinctive:

    Add or update tests whenever changing config defaults, tool tier membership, agent loop behavior, CLI parsing or server endpoints.

    line 29
  10. Distinctive:

    Run focused checks first:

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

local-copilot

Use this skill when adding, debugging or extending the ableton-mind local LLM feature.

Context Check

  1. Read src/llm/config.ts, src/llm/tools.ts, src/llm/agent.ts, src/llm/server.ts and src/cli/chat.ts.
  2. Read tests/llm-local-copilot.test.ts and the latest relevant QA report.
  3. Check _workspace/tdmcp-compatible-features.md for deferred tdmcp-inspired items.
  4. Confirm whether the request is UI chat, headless ask, model/backend, safety tier, docs, or QA.

Safety Rules

  • Keep the default tier read-only (safe). Use explicit --write for simple mutations and --creative for recipes/browser load.
  • Never expose destructive or broad routing/mixer tools to a local model without a safety review.
  • Preserve the bridge-offline behavior: the chat UI can open without Live; live tools must return clear bridge errors.
  • Browser server stays loopback-only and must reject non-loopback Host/Origin.
  • Do not copy TouchDesigner-specific prompts, paths or tools from tdmcp.

Implementation Rules

  • Prefer explicit JSON Schemas in src/llm/tools.ts over new schema-conversion dependencies.
  • The local copilot should use existing ToolDefinition handlers, not duplicate Ableton business logic.
  • Add or update tests whenever changing config defaults, tool tier membership, agent loop behavior, CLI parsing or server endpoints.
  • Public docs belong in English root docs and matching Portuguese pages under docs/pt/.

Verification

Run focused checks first:

npm run typecheck
npx vitest run tests/llm-local-copilot.test.ts

For broader changes, add:

npm run lint
npm run test
npm run build

Live/Ollama validation is optional unless the task changes runtime connectivity. If skipped, report it explicitly.

Test Scenarios

  • Normal: ableton-mind ask --read-only "What is in this set?" with Ollama reachable and bridge connected.
  • Offline bridge: ableton-mind chat --no-ollama --no-open opens the local UI even when Live is closed; live tool calls return a bridge-offline error.
  • Safety: default config resolves to safe; --write switches to standard; --creative exposes recipes/browser load.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.