octocode-mannequin
Use when posing, animating, or explaining a 3D human skeleton/manikin: anatomical joints, ROM clamps, walk/run/dance/backflip sequences, Three.js viewer, or agent-driven WebMCP figure control (reach/look_at). Phrases like pose the manikin, skeleton scheme, animate a walk cycle. Not for general 3D scenes, physics/ragdoll, IK foot-locking, or mocap import.
How do I install this agent skill?
npx skills add https://github.com/bgauryy/octocode --skill octocode-mannequinIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The octocode-mannequin skill is a 3D humanoid skeleton rig and movement protocol implementation. It provides a Node.js CLI for pose validation and a Three.js-based interactive viewer. No security risks were identified; the skill follows safe practices for file handling and uses well-known services for external dependencies.
- Socketpass
No alerts
- Snykwarn
Risk: MEDIUM · 2 issues
What does this agent skill do?
Octocode Mannequin
Anatomically-named 22-bone humanoid rig (arms-down neutral, bilaterally mirrored) plus a movement protocol that
clamps every joint to real range of motion, with a root 6-DOF channel (translate/pitch/yaw/roll) for travel,
turns, jumps and backflips — a Node CLI, a self-contained Three.js viewer (grounded, smooth Catmull-Rom
animation), and WebMCP tools an agent drives live. Flow: SCHEME → COMMAND → CLAMP+FK → RENDER → DRIVE.
Hard rules
scripts/skeleton.mjsis the single source of truth for bones/joints/ROM/movements; references and the viewer mirror it. The viewer re-implements the clamp/sideSign/FK math — any change must be made in BOTH files and re-verified (they must stay identical).- Movement commands use anatomical names valid for that joint, never raw signed degrees and never a movement
outside the joint's allowlist — read
references/movement-protocol.mdbefore composing one; the CLI and the tools reject those. - Treat ROM values as rig defaults, not medical fact — read
references/rom-table.mdbefore quoting a limit.
Gate
Writing a viewer file (viewer --out <file>.html) overwrites that path, and agent-driving needs a fresh
non-headless Chrome on a new port: confirm the output path and get the user's OK before the first write or
browser launch.
Workflow
- Run
node scripts/skeleton.mjs schemefirst to inspect bones + joint DOF/ROM/movements; for the hierarchy readreferences/anatomy-scheme.md, for the constraint model readreferences/joint-constraints.md, and for exact degrees readreferences/rom-table.md. - Compose a pose command using
references/movement-protocol.md, runnode scripts/skeleton.mjs pose --cmd '...', readwarnings/clamped; then validate an animation by runningskeleton.mjs sequence --file frames.json. - To render, run
node scripts/skeleton.mjs viewer --out <file>.html [--pose pose.json], open it, drag sliders or callwindow.applyPose/window.playSequencefrom the console — ready animations live inassets/(run-cycle.json,backflip.json,dance.json,idle.jsonfor alive breathing/sway); for the viewer's mechanics readreferences/viewer-guide.md. - To agent-drive it live, load
references/webmcp-agent.mdand serve the viewer's WebMCP tools over CDP — 11 tools incl. task-spacereach(put a hand/foot at a world point) andlook_at;get_scheme.guideis the frame/units contract. Discover, invoke, verify withget_poseor a screenshot.
Stop when: the pose verifies via get_pose or a screenshot; clamped:true shows the joint is already at its ROM
limit (that is the answer — do not push past it); a movement is rejected as invalid for the joint (retry with the
reported allowlist, never with raw degrees); reach returns reached:false with a residual distance (the target is
out of range — re-target, do not re-invoke unchanged); tool discovery returns WEBMCP_NO_TOOLS or fewer than 11
tools (fall back to window.applyPose via Runtime.evaluate); screenshots come back blank (Chrome is headless —
relaunch non-headless); or the request needs physics, IK foot-locking, or mocap (out of scope, say so).
When NOT this skill
General 3D scene setup, or physics/ragdoll simulation, IK foot-locking, balance, collision, or mocap (BVH/glTF)
import. Motion is keyframed kinematics — a backflip is authored, not simulated; for why that scope was
chosen read references/references.md.
Progressive refs
| Ref | When |
|---|---|
references/anatomy-scheme.md | Building/explaining the bone hierarchy |
references/joint-constraints.md | DOF/constraint model + verified rotation directions per joint |
references/rom-table.md | Exact degree limits per movement |
references/movement-protocol.md | Writing/validating a pose command |
references/viewer-guide.md | Generating/driving the Three.js viewer |
references/webmcp-agent.md | Agent-driving the manikin via WebMCP + CDP |
references/references.md | Provenance / why a design choice was made |
Scripts
- Run
node scripts/skeleton.mjsfor thescheme/pose/sequence/viewersubcommands (--help); zero npm installs. WebMCP CDP mechanics are delegated to theoctocode-chrome-devtoolsskill.
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/bgauryy/octocode/octocode-mannequin">View octocode-mannequin on skillZs</a>