agentleFS
mementomori-comementomori-co/maker-mastery/.claude/skills/coupon/SKILL.md

coupon

Skill2 starsChanged 25 days agoMITView on GitHub

Use when a design number (clearance, bridge length, insert boss, wall, diffuser depth) is an assumption that a small print can measure. Runs test-coupon-designer in a fresh context and leaves coupon.py, coupon.stl and a blank measurement sheet under coupons\<slug>\ in the project folder.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    Write coupon.py (parameters at the top, labelled steps, one body, STL export that prints bbox, volume, bodies, watertight) and run it with …

    line 19
  2. Very specific:

    Write measurement-sheet.md with the constants header, the table | step | nominal | measured | pass/fail | note | and the filing path.

    line 21

≈ “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

Overview

Design a coupon for: $ARGUMENTS

Output on disk, inside the project folder the maker names (default work\coupons\<slug>\): coupon.py, coupon.stl, measurement-sheet.md. The filled sheet later goes through /verify and /file into a calibration-and-testing note in knowledge\. This skill does not print, slice or file.

When to use

Whenever cad-engineer, dfm-engineer, organic-modeler or electronics-engineer labels a value "assumed". Not for a value a TDS or wiki page states (use /research-one); not for flow or pressure-advance calibration (Bambu's own calibration pages on https://wiki.bambulab.com).

Steps

  1. Parse the hypothesis into variable, range and step, pass criterion, and constants (material, nozzle, process base 0.20mm Standard for your printer unless stated, plate, orientation). If a constant is missing, ask it as a NEEDS MAKER question before writing geometry.
  2. Glob the existing coupon folders for coupon.py; extend an existing coupon of the same variable instead of creating a second one.
  3. Write coupon.py (parameters at the top, labelled steps, one body, STL export that prints bbox, volume, bodies, watertight) and run it with .venv\Scripts\python.exe.
  4. Overhang check in the stated orientation against the threshold in knowledge\02-bambu-studio\support-settings.md; adjust geometry until self-supporting.
  5. Write measurement-sheet.md with the constants header, the table | step | nominal | measured | pass/fail | note | and the filing path.
  6. Return the three paths, the script's printed mesh stats and the hand-off line (dfm-engineer, then bambu-studio-expert, then /preprint-check). The maker prints it; no AI ever sends a print.

Common rationalizations

RationalizationReality
"Measure clearance and bridge on one part."Two variables, no filing. One coupon per variable.
"Skip /preprint-check for a 10-gram coupon."Every print goes through the gate (CLAUDE.md).
"Write the expected result into the note now."A number enters knowledge\ only from a filled sheet via /verify.

Red flags

  • A sheet missing a constant.
  • Steps without embossed labels.
  • An STL without coupon.py beside it.

Verification

  • coupon.py, coupon.stl, measurement-sheet.md exist in the coupon folder.
  • Script output quoted: bbox, volume, bodies 1, watertight.
  • Overhang check quoted against the profile threshold.
  • Filing path and hand-off line in the reply.

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.