# Send Pywayne Vio Se3 to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "se3",
    "name": "Pywayne Vio Se3",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/wangyendt/se3",
    "canonicalUrl": "https://clawhub.ai/wangyendt/se3",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/se3",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=se3",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "SKILL.md"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "se3",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-03T07:49:31.769Z",
      "expiresAt": "2026-05-10T07:49:31.769Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=se3",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=se3",
        "contentDisposition": "attachment; filename=\"se3-0.1.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "se3"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/se3"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/se3",
    "downloadUrl": "https://openagent3.xyz/downloads/se3",
    "agentUrl": "https://openagent3.xyz/skills/se3/agent",
    "manifestUrl": "https://openagent3.xyz/skills/se3/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/se3/agent.md"
  }
}
```
## Documentation

### Quick Start

import numpy as np
from pywayne.vio.SE3 import *

# Create SE(3) transformation from rotation and translation
R = np.eye(3)
t = np.array([1, 2, 3])
T = SE3_from_Rt(R, t)

# Lie algebra operations
xi = np.array([0.1, 0.2, 0.3, 0.05, 0.1, 0.15])  # [rho, theta]
T_from_xi = SE3_Exp(xi)  # se(3) vector -> SE(3)
xi_recovered = SE3_Log(T_from_xi)  # SE(3) -> se(3) vector

### Basic Matrix Operations

Create/Verify SE(3) matrices:

check_SE3(T) - Validate 4x4 matrix is valid SE(3)
SE3_from_Rt(R, t) - Construct from rotation matrix and translation
SE3_to_Rt(T) - Extract rotation matrix and translation vector

Combine/invert transformations:

SE3_mul(T1, T2) - Matrix multiplication (compose transforms)
SE3_inv(T) - Matrix inverse
SE3_diff(T1, T2, from_1_to_2=True) - Compute relative transform

### Lie Group/Lie Algebra Mappings

Vector form (preferred):

SE3_Exp(xi) - se(3) 6D vector -> SE(3) matrix, xi = [rho, theta]
SE3_Log(T) - SE(3) matrix -> se(3) 6D vector

Matrix form (theoretical):

SE3_exp(xi_hat) - se(3) 4x4 matrix -> SE(3) matrix
SE3_log(T) - SE(3) matrix -> se(3) 4x4 matrix
SE3_skew(xi) - 6D vector -> 4x4 Lie algebra matrix
SE3_unskew(xi_hat) - 4x4 matrix -> 6D vector

Naming convention: Uppercase = vector, lowercase = matrix

### Representation Conversions

Quaternion + translation:

SE3_from_quat_trans(q, t) - q is wxyz quaternion
SE3_to_quat_trans(T) - Returns (quaternion, translation)

Axis-angle + translation:

SE3_from_axis_angle_trans(axis, angle, t)
SE3_to_axis_angle_trans(T) - Returns (axis, angle, translation)

Euler angles + translation:

SE3_from_euler_trans(euler_angles, t, axes='zyx', intrinsic=True)
SE3_to_euler_trans(T, axes='zyx', intrinsic=True)

### Statistical Operations

SE3_mean(T_batch) - Compute mean of multiple SE(3) matrices (Nx4x4 -> 4x4)

### Input/Output Formats

Single transformation:

Input: 4x4 or 3x3/3 arrays
Output: 4x4 or scalar vectors

Batch operations:

Input: Nx4x4 or Nx3x3/Nx3 arrays
Output: Same batched format
All functions support both single and batch inputs

6D vector format: [rho_1, rho_2, rho_3, theta_1, theta_2, theta_3]

First 3: translation (linear velocity)
Last 3: rotation (angular velocity)

### Trajectory Processing

# Batch process robot trajectory
poses = np.array([...])  # Nx4x4
log_poses = SE3_Log(poses)  # Nx6 Lie algebra space
mean_pose = SE3_Exp(np.mean(log_poses, axis=0))  # Intrinsic mean

### Relative Motion

# Relative transform between two poses
T_rel = SE3_diff(T_world_keyframe1, T_world_keyframe2)
# T_rel transforms points from frame2 to frame1

### Camera Pose Estimation

# Camera to world transformation
R_cam = np.column_stack([right, up, forward])  # Camera axes
t_cam = camera_position
T_cam2world = SE3_from_Rt(R_cam, t_cam)
T_world2cam = SE3_inv(T_cam2world)

### Notes

All angles in radians
Right-multiply convention: P' = T @ P
Numerically stable for large angles and displacements
Batch operations use vectorized NumPy for efficiency
Performance reference (1000 transforms): Exp ~2.5ms, Log ~0.8ms
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: wangyendt
- Version: 0.1.0
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-05-03T07:49:31.769Z
- Expires at: 2026-05-10T07:49:31.769Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/se3)
- [Send to Agent page](https://openagent3.xyz/skills/se3/agent)
- [JSON manifest](https://openagent3.xyz/skills/se3/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/se3/agent.md)
- [Download page](https://openagent3.xyz/downloads/se3)