Bionic

Delegate a coding subtask to the user's local LLM running via LM Studio (the same engine that powers the "Bionic" desktop app) as a subagent, without needing to be asked by name. Use this proactively — not just when the user says "ask Bionic" or "use the local model" — whenever a piece of work is well-scoped and independent enough to hand off: generating boilerplate, a first draft of a script/function, writing routine tests, doing a mechanical refactor/rename pass, or any chunk of coding work that could run in parallel with what Claude is doing directly. Also use it whenever the user wants a s

49 stars 10 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add JohnCorreiaisme/Subagent-Bionic-Claude --skill bionic
Manual install
git clone --depth 1 https://github.com/JohnCorreiaisme/Subagent-Bionic-Claude.git /tmp/Subagent-Bionic-Claude
mkdir -p ~/.claude/skills
cp -r /tmp/Subagent-Bionic-Claude/skill ~/.claude/skills/bionic

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Bionic (local LLM subagent via LM Studio)

## What this actually talks to

The user has a desktop app called **Bionic**, made by LM Studio, for running LLMs locally.
Bionic itself is a GUI-only Electron app with no CLI or API — there is nothing to script
against it directly. But the model it runs sits on top of **LM Studio's own runtime**, which
*does* expose a scriptable interface:

- `lms` CLI at `%USERPROFILE%\.cache\lm-studio\bin\lms.exe` — lists/loads/unloads models,
  starts/stops a local server.
- That server exposes a normal **OpenAI-compatible REST API** (default `http://127.0.0.1:1234`)
  once started.

So "ask Bionic" in practice means: make sure a model is loaded in LM Studio, and send it the
task over that local REST API. The user does not need Bionic.exe running at all for this to
work — LM Studio's own server is the actual engine.

## Configuration panel

There's a clickable config app, **"Subagent BionicClaude"** (desktop shortcut, or run
`scripts\Subagent-BionicClaude.ps1` directly), where the user sets: which model to use by
default, the server port, temperature, and max tokens, plus buttons to start/stop the server
and load/unload/download models. Settings saved there land in `config.json` next to this
SKILL.md, and `bionic-ask.ps1` reads that file automatically for any parameter not explicitly
passed on the command line — so if the user says "I changed the default model in the panel,"
Read the full skill on GitHub

Details

Skill name
bionic
Path
skill/SKILL.md
License
MIT
Repo updated
26 August 2026

FAQ

What does the Bionic skill do?

Delegate a coding subtask to the user's local LLM running via LM Studio (the same engine that powers the "Bionic" desktop app) as a subagent, without needing to be asked by name. Use this proactively — not just when the user says "ask Bionic" or "use the local model" — whenever a piece of work is well-scoped and independent enough to hand off: generating boilerplate, a first draft of a script/function, writing routine tests, doing a mechanical refactor/rename pass, or any chunk of coding work that could run in parallel with what Claude is doing directly. Also use it whenever the user wants a s

How do I install the Bionic skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add JohnCorreiaisme/Subagent-Bionic-Claude --skill bionic. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Bionic popular?

It lives in JohnCorreiaisme/Subagent-Bionic-Claude, which has 49 GitHub stars and 10 forks.

Related skills

Spine Hero

47

enoch3712/spine-hero-skill

Use when animating a 2D game character from a single painting on a skeletal rig (Spine or similar), such as cutting the painting into parts, authoring an idle, walk, run or combat move as code on the rig, making a reference video for timing, painting hidden parts or swappable gear, gating captured clips with scripted checks, or planning a team of AI models for that work.

AI, LLMs & Agents14

Ae MCP

49

ishu86/after-effects-mcp

Drive Adobe After Effects through the ae-mcp tools. Use when the user wants to create, edit, animate or render anything in After Effects - compositions, text, shape layers and bezier paths, trim paths and other shape operators, masks, keyframes and easing, expressions, effects and particles (CC Particle World, Particle Systems II, Particle Playground), 3D layers with cameras, lights and extrusion, lower thirds, title cards, transitions, logo reveals, markers, and the render queue or Adobe Media Encoder. Trigger on phrases like "in After Effects", "make a motion graphic", "animate this", "add k

AI, LLMs & Agents11

Xhs AI Tools Writer

45

mini20201314-crypto/xhs-ai-tools-writer

小红书 AI 工具向编稿工作流。用于写/改小红书笔记:ChatGPT、Claude、Cursor、 Midjourney、效率插件等真实测评与场景干货。触发词:小红书、xhs、编稿、 笔记、标题、AI工具测评、Cursor、ChatGPT种草、科技干货。 Use when writing Xiaohongshu notes about AI tools, productivity apps, or tech how-tos.

AI, LLMs & Agents20

Artcraft MCP

49

theCosmicCrafter/artcraft-mcp

Guide to using the ArtCraft MCP Server tools. Use this when the user wants to interact with ArtCraft's generation capabilities, such as generating images/videos, uploading media, or checking job statuses via the ArtCraft API.

AI, LLMs & Agents12

Building LLM Backed Features

115

wdm0006/python-skills

Builds application features on top of an LLM API in Python — prompt surfaces that drift apart, structured outputs, context budgeting, model/config wiring, filtered evaluator sets, keeping live-model calls out of default CI, evaluating stochastic output, and presenting model output truthfully. Use when adding an LLM call to an app, designing structured outputs or prompt templates, filtering audit rules, wiring model config, or testing/evaluating LLM-backed analysis.

AI, LLMs & Agents18

Adopt Project

75

sneg55/agent-starter

Apply agent-starter patterns to an EXISTING project - audits the codebase, proposes components by invasiveness tier (hooks, skills, CLAUDE.md, lint configs, patterns), and applies only what the developer approves. Use when the user says adopt, retrofit, "apply agent-starter to this project", or wants starter patterns in an existing codebase.

AI, LLMs & AgentsIn 1 list

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.