agentleFS
Sign inStart free
adeerkhanadeerkhan/vitruvius/skills/mechanical/SKILL.md

mechanical

Skill10 starsChanged 4 days agoMITView on GitHub

Mechanical engineering research. Use when the user invokes /mechanical, asks about mechanical engineering topics — machine design, mechanisms, power transmission, thermal/fluids, materials selection, manufacturing, pressure vessels, piping, fasteners, bearings, gears — or asks to verify an engineering claim in that domain. Dispatches to the shared engineering-research method with the mechanical evidence landscape.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Units: every number carries a unit.

    line 40
  2. Distinctive:

    Code provisions: verify the standard exists, cite the section number, and read the actual provision before summarizing it.

    line 47
  3. Very specific:

    Follow the method's artifact contract (outputs/.plans/<slug>.md → draft → cited → final + .provenance.md).

    line 54
  4. Very specific:

    If research hits an evidence dead-end — no standard, paper, or dataset addresses the question after exhausting the discovery layers — …

    line 66

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
<!-- VITRUVIUS-COMPILED-SKILL:BEGIN v1 sha256=4b2a4fbbb76aaf1ca75464a01fb201b82555e114c2421b2d64ad449a007b180d -->

Mechanical Engineering Research

Activate the /skill:engineering-research method and run it with this domain payload. Do not restate the research loop here.

Evidence landscape

  • Standards/codes: ASME (BPVC, B31 piping), ASTM, ISO, SAE, AWS, AGMA, API. When a code governs the question, cite the exact section.
  • Handbooks: Machinery's Handbook, Marks', Shigley's, ASME/ASM handbooks — use only when a direct primary read is possible.
  • Primary sources: manufacturer datasheets, bearing/coupling catalogs, material property data from the issuing body, patent documents, peer- reviewed journals. For journal literature use the /skill:scholarly-research discovery layers (OpenAlex, Semantic Scholar, arXiv).
  • Prior art / practice: documented field failures, failure analyses, trade association guidance (e.g. ASME B31, AGMA, NFPA).

Verification criteria

  • Units: every number carries a unit; state the unit system (SI, US customary) and convert explicitly. Flag mixed-unit claims.
  • Sign conventions: tension/compression, torque direction, load sign.
  • Material properties: a property value must trace to a named grade + specification (e.g. A36 per ASTM A36), not to a vague "steel".
  • Design basis: design factor / factor of safety must be stated and traced to code or practice (e.g. ASME BPVC design factor), not assumed.
  • Code provisions: verify the standard exists, cite the section number, and read the actual provision before summarizing it.
  • Calculations: any derived number must show the formula, inputs, and units so it can be re-run.

Deliverable shape

Follow the method's artifact contract (outputs/.plans/<slug>.md → draft → cited → final + .provenance.md). In the final artifact, end with a Sources section citing standard + section, and mark every load, factor, and material property verified, inferred, or blocked.

Invocation Flags

Accept --deep and --quick flags and pass them through to the engineering-research method. See that skill for flag semantics.

Gap Detection

If research hits an evidence dead-end — no standard, paper, or dataset addresses the question after exhausting the discovery layers — suggest running /gap-analysis mechanical <sub-topic> to formally validate and document the gap. Do not invoke gap-analysis automatically; offer it as a next step and wait for the user to confirm.

Scope and Boundaries

  • This skill produces research — it does NOT produce final designs or construction documents.
  • Research-only, not for final engineering sign-off. Licensed engineers must review and approve any design based on this research.

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.

Check your setup, free