agentleFS
BaratiLabBaratiLab/mechanical-engineering-skills/skills/machine-element-sizing/SKILL.md

machine-element-sizing

Skill16 starsChanged 16 days agoMITView on GitHub

Sizes and checks machine elements — bolted joints, shafts (fatigue), rolling bearings (L10 life), helical springs, fillet welds, and spur gears — with shown work and safety factors. Use when the user asks to size, select, or verify a bolt, shaft, bearing, spring, weld, or gear.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    All numbers come from scripts/me_sizing.py.

    line 8
  2. Distinctive:

    Never report a safety factor without stating the failure criterion it refers to.

    line 44

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Machine Element Sizing

All numbers come from scripts/me_sizing.py. Do not do sizing arithmetic in your head.

Workflow

  1. Identify the element and load case. Static vs fatigue; steady vs alternating components; operating speed.
  2. Collect inputs in SI (N, mm, MPa, N·mm, rpm). Convert user units first and state the conversion. If a required input is missing:
    • material strengths → look up in references/materials.md and state the source row;
    • stress concentration Kf/Kfs → use the first-iteration defaults in references/defaults.md, flag them as assumptions;
    • anything else → ask.
  3. Run the calculator (python scripts/me_sizing.py <cmd> --help for options):
    python scripts/me_sizing.py bolt    --size M10 --grade 8.8 --load 24000 --n-bolts 4 --fatigue
    python scripts/me_sizing.py shaft   --Ma 70000 --Tm 120000 --Kf 1.7 --Kfs 1.5 --Sut 690 --Sy 580
    python scripts/me_sizing.py bearing --type ball --Fr 2500 --rpm 1800 --hours 20000 --reliability 0.95
    python scripts/me_sizing.py spring  --d 2.5 --D 20 --Na 8 --F 120 --material music-wire
    python scripts/me_sizing.py weld    --F 30000 --h 6 --L 200 --electrode E70
    python scripts/me_sizing.py gear    --module 3 --N 20 --F 35 --T 150000 --rpm 1200 --Sy 400
  4. Iterate until every check is PASS: change size/grade/material, re-run. For shafts, round up to a standard diameter and re-run with updated Kf.
  5. Sanity check one result by a one-line hand estimate (e.g. τ ≈ 16T/πd³) and confirm it agrees within ~20%.
  6. Report in the format below.

Output format

## <Element> sizing — <one-line case>
Assumptions: ... (flag every defaulted value)
| Quantity | Value | Unit |       ← key intermediate values from the JSON
Checks:  ✅ n_L = 2.1 ≥ 1.5   ❌ n_f = 1.1 < 1.5
Recommendation: M12 grade 10.9, preload 75% proof, torque ≈ 0.2·Fi·d
Method: <method string from JSON>

Guardrails

  • Gear results are Lewis screening only; say that AGMA 2001 / ISO 6336 is required for final design.
  • Weld bending requires the weld-group unit properties; see references/weld_groups.md.
  • Never report a safety factor without stating the failure criterion it refers to.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.