Skip to content

Instantly share code, notes, and snippets.

View csvance's full-sized avatar

Carroll Vance csvance

  • Medical Metrics Inc.
  • Houston, Texas
View GitHub Profile
@csvance
csvance / SKILL.md
Created May 12, 2026 04:28
Kaimon.jl Skill
name kaimon-julia
description Workflow guide for driving Julia projects through the Kaimon MCP server. Load this skill whenever working with Julia code in any capacity, including reading, writing, editing, or debugging .jl files, Project.toml/Manifest.toml, Julia REPL sessions, Pkg operations, Revise-based hot-reload workflows, or any Kaimon tool calls (start_session, ex, manage_repl, pkg_add, pkg_rm, check_eval, debug_exfiltrate, goto_definition, workspace_symbols). Kaimon is the preferred execution path for all Julia work in this repo.

Kaimon + Julia REPL Workflow

A reference for working a Julia project through the Kaimon MCP server. Covers session lifecycle, output management, Revise behavior, and the rough edges that cost the most round trips when you hit them blind.

1. Session lifecycle

from typing import *
import abc
class ArgsMatcher(abc.ABC):
@abc.abstractmethod
def __call__(self, *args, **kwargs):
raise NotImplementedError()
def strength(self):
import cv2
import numpy as np
import os
import imgaug as ia
from imgaug import augmenters as iaa
import tensorflow.keras as keras
from tensorflow.keras.losses import mean_absolute_error, mean_squared_error
from tensorflow.keras.models import Model
import copy
import numpy as np
import sys
import time
import plac
class FrozenGraph(object):
def __init__(self, model, shape):
import tensorflow.keras as keras
import keras
from keras.models import Model
from keras import backend as K
from keras.layers import Dense, Activation
import tensorflow as tf
from tensorflow.contrib import tensorrt as tftrt
import copy
import numpy as np
import sys
<launch>
<arg name="serial_no" default=""/>
<arg name="json_file_path" default=""/>
<arg name="camera" default="camera"/>
<arg name="tf_prefix" default="$(arg camera)"/>
<arg name="fisheye_width" default="640"/>
<arg name="fisheye_height" default="480"/>
<arg name="enable_fisheye" default="true"/>
clf
hold on
disp("Note: You must define the CX output as the general solution here after running one time for this code to work")
syms y(x) x d C2 C4
xrange = -5:0.1:5;
yrange = -10:0.1:10;
% Quiver
%ode = @(y, x) (x+2*y^2)/(2*y*x);
import cv2
cap = cv2.VideoCapture(0)
final_frame = None
initial_frame = None
while True:
# Capture frame-by-frame
ret, frame = cap.read()
syms t;
syms C;
syms y;
syms r;
syms y;
syms x;
syms Y;
syms X;
hw_problem = '2.1 #24';