メニュー
Skill for mechanism kinematics, dynamics, and motion analysis
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/a5c-ai/babysitter --skill mechanism-designコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Reference for querying the Atlas knowledge graph through its MCP tools — the SECONDARY enrichment/comparison layer that adds best-practice context to systems you have ALREADY scanned from your real sources (`az`, repos, dirs). Use when you need to look up nodes, edges, kinds, clusters, stats, or wiki pages in Atlas to compare against your real inventory. (atlas graph, query atlas, atlas mcp, search the graph, graph neighbors, atlas record, atlas kinds, enrichment layer)
Atlas turns your STATED NEED into a real systems atlas by SCANNING your actual sources (Azure via `az`, git repos, local dirs) and process/data mining them, THEN enriching against the Atlas knowledge graph. Use this skill when asked to inventory/map your real systems, scan your cloud + repos + directories, mine the real processes or data they contain, or collect their real constraints/gotchas. (atlas, scan my systems, inventory our azure account, map my repos, real systems atlas, process mining, data mining, collect nuances, system discovery)
This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable processes, babysitter plugins, and reusable procedural insights. Searches GitHub for SKILL.md files, classifies repos by archetype, and maintains structured research under docs/reference-repos/.
SKILL.md を表示中
SOC 職業分類に基づく
| name | mechanism-design |
| description | Skill for mechanism kinematics, dynamics, and motion analysis |
| allowed-tools | ["Read","Write","Glob","Grep","Bash"] |
| metadata | {"specialization":"mechanical-engineering","domain":"science","category":"mechanical-systems","priority":"medium","phase":8,"tools-libraries":["MSC ADAMS","RecurDyn","SolidWorks Motion","MATLAB"]} |
| graph | {"domains":["domain:mechanical-engineering"],"skillAreas":["skill-area:physics-simulation","skill-area:mathematical-reasoning","skill-area:motion-planning"],"roles":["role:systems-integration-engineer","role:research-engineer"]} |
The Mechanism Design skill provides capabilities for mechanism kinematics, dynamics, and motion analysis, enabling systematic design and optimization of mechanical motion systems.
Gruebler's Equation (planar):
DOF = 3(n-1) - 2j1 - j2
Where:
n = number of links (including ground)
j1 = number of full joints (pin, slider)
j2 = number of half joints (cam, gear)
DOF = 1: Constrained mechanism
DOF = 0: Structure
DOF < 0: Over-constrained
| Mechanism | Links | Joints | DOF | Application |
|---|---|---|---|---|
| Four-bar | 4 | 4 pins | 1 | Motion generation |
| Slider-crank | 4 | 3 pins + 1 slider | 1 | Reciprocating motion |
| Scotch yoke | 4 | 2 pins + 2 sliders | 1 | Exact sinusoidal |
| Quick return | 4 | 3 pins + 1 slider | 1 | Unequal stroke times |
| Geneva | 2 | Cam joint | Intermittent | Indexing |
Grashof criterion:
s + l <= p + q
Where:
s = shortest link
l = longest link
p, q = intermediate links
If satisfied: At least one link can rotate fully
Types:
- Crank-rocker: Shortest link is crank
- Double-crank: Shortest link is ground
- Double-rocker: No full rotation
Loop closure equation:
r2*e^(i*theta2) + r3*e^(i*theta3) - r4*e^(i*theta4) - r1 = 0
Solve for theta3, theta4 given theta2 (input)
Velocity:
omega3 = omega2 * r2 * sin(theta4-theta2) / (r3 * sin(theta4-theta3))
mu = angle between coupler and output link
Ideal: mu = 90 degrees
Acceptable: 40 < mu < 140 degrees
Poor: mu < 30 or mu > 150 degrees
| Type | Motion | Application |
|---|---|---|
| Plate cam | Translating or oscillating follower | High speed |
| Cylindrical cam | Oscillating follower | Indexing |
| Face cam | Translating follower | Compact |
| Globoidal cam | Oscillating follower | High accuracy |
Common profiles:
1. Parabolic (constant acceleration)
s = (1/2) * a * t^2 for first half
Good: Simple, smooth
Bad: Infinite jerk at transition
2. Simple harmonic
s = (h/2) * (1 - cos(pi*t/T))
Good: Zero velocity at ends
Bad: Finite acceleration at ends
3. Cycloidal
s = h * (t/T - sin(2*pi*t/T)/(2*pi))
Good: Zero acceleration at ends
Bad: Higher peak acceleration
4. Modified trapezoid
Combines constant acceleration with transitions
Good: Low peak acceleration
Bad: More complex
tan(alpha) = (dy/dtheta) / (rb + y)
Where:
alpha = pressure angle
dy/dtheta = slope of displacement curve
rb = base circle radius
y = follower displacement
Limit: alpha < 30 degrees (typically)
| Type | Application | Efficiency |
|---|---|---|
| Spur | Parallel shafts | 98-99% |
| Helical | Parallel shafts, quieter | 97-99% |
| Bevel | Intersecting shafts | 97-98% |
| Worm | High ratio, non-reversing | 50-90% |
| Planetary | Compact, high ratio | 97-98% |
Simple gear train:
i = N2/N1 = omega1/omega2
Compound gear train:
i_total = product of individual ratios
Planetary gear train:
i = 1 + Nring/Nsun (sun fixed)
i = 1/(1 + Nsun/Nring) (ring fixed)
Module: m = d/N
Pitch: p = pi * m
Addendum: a = m
Dedendum: b = 1.25 * m
Center distance: C = m * (N1 + N2) / 2
Contact ratio:
CR = (Arc of action) / (Circular pitch)
Minimum CR > 1.2 recommended
Newton-Euler method:
Sum F = m * a_g (for each link)
Sum M_g = I_g * alpha (about mass center)
D'Alembert approach:
Add inertia forces: -m*a, -I*alpha
Solve as static equilibrium
Shaking force = -Sum(m_i * a_i)
Shaking moment = -Sum(I_i * alpha_i + r_i x m_i * a_i)
Balancing strategies:
1. Add counterweights
2. Optimize mass distribution
3. Use multiple cylinders (phase)
{
"mechanism_type": "linkage|cam|gear|custom",
"motion_requirements": {
"input_motion": "rotation|translation",
"output_motion": "rotation|translation",
"motion_profile": "string or array",
"speed": "number (RPM or m/s)"
},
"constraints": {
"space_envelope": "object",
"force_requirements": "number",
"accuracy": "number"
},
"operating_conditions": {
"load": "number",
"speed_range": "array [min, max]",
"duty_cycle": "string"
}
}
{
"mechanism_design": {
"type": "string",
"configuration": "object",
"link_dimensions": "array"
},
"kinematic_results": {
"position_analysis": "array or function",
"velocity_analysis": "array or function",
"acceleration_analysis": "array or function",
"transmission_angle": "number"
},
"dynamic_results": {
"forces": "array",
"torques": "array",
"shaking_forces": "object"
},
"performance_metrics": {
"pressure_angle": "number (cams)",
"contact_ratio": "number (gears)",
"efficiency": "number"
},
"design_documentation": "reference"
}