FileMaker AI Grammar — Testing skill for Claude Code
171 engine-measured test vectors and 29 verified behaviour rules for FileMaker's calculation engine, round-trip tested against real FileMaker Pro rather than assumed or transcribed from docs.
How to install FileMaker AI Grammar
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open andykear/FileMaker-AI-Grammar and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What FileMaker AI Grammar does
171 engine-measured test vectors and 29 verified behaviour rules for FileMaker's calculation engine, round-trip tested against real FileMaker Pro rather than assumed or transcribed from docs. Includes a loadable Claude skill covering the traps AI models get confidently wrong. Companion to FileMaker AI Vocabulary.
Alternatives in Testing
- Claude Codepro — by Max Ritter - Professional development environment for Claude Code with spec-driven workflow, TDD enforcemen 1.6k ★
- TDD Skill — BitcoinAddressFinder — This skill documents test-driven development practices and refactoring patterns used in the BitcoinAddressFind 237 ★
- Cc10x — The Loop Engine for Claude Code — engineer the loop, not the prompt 163 ★
README
[](https://github.com/andykear/FileMaker-AI-Grammar) [](https://creativecommons.org/licenses/by/4.0/)
FileMaker AI Grammar
171 test vectors covering FileMaker's calculation engine, each one measured against real FileMaker Pro rather than assumed. 29 rules pulled out of that corpus and a Claude skill built from the seven that matter most.
Developed by Andrew Kear of Clockwork Creative Technology and shared openly with the FileMaker/Claris community.
The problem
FileMaker's calculation language has no published formal grammar. Claris maintains a full operator order of evaluation table, at `operators-in-formulas.html`, it just isn't cross linked from the four separate operator category pages that describe the individual operators.
So this repo tests instead of describing. Every vector here is a calculation expression, round trip tested against a real FileMaker Pro file, with the value it actually returned logged as the expected output.
The reason that matters: FileMaker's calculation engine has real, specific behavior that doesn't match general purpose language convention, or plain intuition. Unary minus binds tighter than exponentiation. `Trim` strips only spaces. `Substitute` is case sensitive while `Position` isn't. Some of this is stated in Claris's own help pages, it's just easy to miss, or to contradict with intuition carried over from another language. A model reasoning from general programming convention gets a predictable slice of this confidently wrong, with nothing to signal that anything is off.
Tested against ChatGPT
All eight predicted traps below were run against ChatGPT, logged honestly rather than cherry picked. Four produced a confirmed wrong answer. Four the model already had right.
| Prompt | Predicted wrong answer | Actual | Result |
|---|---|---|---|
"abc" = "ABC" |
False |
Related Skills
Writing Craft
A blind tested skill for better creative writing. Nine signals three AI judges named after scoring 50 samples
Pi Webgl Scroll Site
A verified AI-agent skill for building scroll-driven WebGL/three.js sites: working spine, measured gotchas, nu
Container Escape
Test container escape vectors on: $ARGUMENTS
Rtk Test Before Merge
Force the agent to write or extend a test for every behaviour change.
Ab Test Plan
Design an A/B test. Produces hypothesis, control/variant definition, sample size calculation, success metrics,
Zames Pro
Terminal coding agent that drives chat.deepseek.com through Playwright — no API key required. Reads/edits file
Related Agents
Conventions
Markers: [V] tool-verified; [I] inferred; [A] assumed; [U] unknown.
Targets
Targets pipeline reviewer. Use when verifying target dependencies are correct, dynamic branching is sound, for
Equivalent Mutant Judge
Use when mutants survived a test suite and each one must be classified as EQUIVALENT (no input can observe the