agentleFS
BaratiLabBaratiLab/mechanical-engineering-skills/skills/engineering-calc-report/SKILL.md

engineering-calc-report

Skill16 starsChanged 16 days agoMITView on GitHub

Turns engineering calculations, scripts, or notes into a formal, checkable calculation report — objective, inputs with sources, assumptions, method with equations, unit-checked results, margins, conclusions, and references — ready for review or sign-off. Use when the user asks for a calc report, calc package, design calculation document, or to write up an analysis formally.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Format: Use the Docs artifact type by default.

    line 23
  2. Distinctive:

    Self-check before delivery: every input has a source; every assumption is used somewhere.

    line 24

≈ “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

Engineering Calculation Report

Workflow

  1. Collect the calculations. Gather them from the conversation, attached scripts or spreadsheets, or outputs of other skills (machine-element-sizing, quick-fea, thermal-fluids-calc). Re-run every number in code. Never copy a figure without recomputing it.
  2. Unit-check everything with pint, using scripts/calc_template.py as the pattern. Each equation's result should carry units, and the script fails on any dimensional mismatch.
  3. Write the report in this structure (see references/report_structure.md):
    1. Header block: title, document number, revision, project, author, checker (blank), date
    2. Objective: one paragraph on what is being shown and against what criterion
    3. Summary of results: a table of each check with its value, allowable, margin, and PASS/FAIL. This is the first thing a reviewer reads.
    4. Inputs: a table with value, unit, and source (drawing number, datasheet, standard, assumption)
    5. Assumptions: numbered, each with a justification and a note on whether it's conservative
    6. Method and calculations: each step gives the equation in symbols (LaTeX), substituted values, result with units, and a reference (textbook eq. number or standard clause)
    7. Discussion: sensitivity to key assumptions, limitations
    8. Conclusions and recommendations
    9. References
    10. Appendix: the script or code used
  4. Margins. Report MS = allowable / (applied × FoS) − 1. A negative MS fails. State the factor of safety basis (code, customer, or company standard).
  5. Format. Use the Docs artifact type by default. If the user wants a file, produce docx (docx skill) or PDF/LaTeX (pdf skill). Equations go in LaTeX.
  6. Self-check before delivery: every input has a source; every assumption is used somewhere; the summary-table numbers match the body; units appear on every number.

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.