formula-validator
Skill10 starsChanged 6 days agoMITView on GitHub
Deterministic formula checker for physics and maths. You extract the equation and declare the units; the tool runs five CAS layers plus a pint unit cross-check and returns a strict pass / fail / unknown verdict. Fires on any formula whose correctness matters.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- JiamingShi-JsPhys/agent-skillstheir own version, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- JiamingShi-JsPhys/agent-skills★ 4same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/chelate-shell.mdcCursor rule
- 3d-modelerSkill
- ai-trace-removerSkill
- bibtex-normalizerSkill
- capstone-labmateSkill
- conflict-detectorSkill
- data-profilerSkill
- document-evolution-trackerSkill
- fulltext-extractorSkill
- latex-exporterSkill
- literature-retrieverSkill
- longitudinal-analysisSkill
- ml-auditorSkill
- multi-dim-managerSkill
- quantitative-validatorSkill
- reference-auditorSkill
- sci-visualizerSkill
- security-guardSkill
- task-organizerSkill
- video-trackerSkill
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
- Distinctive: line 27
Run this exact form — do not read the source tree:
- Very specific: line 83
Only validate/check run the pint layer.
≈ “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.
Files
formula-validator
Checks a formula with five independent layers (parse, dimension, limit, numeric, symbolic) plus a pint unit cross-check, and returns one strict verdict. You extract and interpret; the tool computes.
- Stage:
gates· Sandbox: no · Dependencies:sympy,numpy,pint
Quick Execution
Run this exact form — do not read the source tree:
python run.py --root <WS> --action validate -- --expr "F = m*a" --units F=N --units m=kg --units a=m/s**2- Everything after
--goes to the legacy CLI unchanged. --units sym=unitmay be repeated; leave a symbol undeclared rather than guessing its unit.- The verdict is written to
<WS>/process/gates/formula-validator_<ts>.jsonand a Markdown report to<WS>/process/reports/.
When to use
- A formula, identity or derived result appears and its correctness matters.
- A multi-step derivation must be checked, or a wrong result localised.
- A matrix must be confirmed Hermitian, unitary or otherwise structured.
- A dimensional or limiting-case check is requested.
When NOT to use
- Purely numeric evaluation with no symbolic claim.
- Prose or literature work with no formula.
- Curve fitting or statistics on measured data.
- A formula the user only wants typeset.
Actions
--action | Does | Extra arguments |
validate | D1–D5 layers + pint cross-check | --expr "..." [--units s=u ...] |
check | Alias of validate | same as validate |
derive | Check a multi-step derivation | --expr "..." |
matrix | Matrix property check | --expr "..." |
units | pint unit check only | --expr "..." --units s=u |
Hard constraints
- Never compute the algebra yourself.
- Never report a verdict the tool did not produce.
unknownis a valid outcome and must never be reinterpreted as a pass. - Never guess a unit silently — an undeclared symbol is a legitimate state.
Outputs
<WS>/process/gates/formula-validator_<ts>.json— the merged gate result.<WS>/process/reports/— the Markdown report with the failing layer named.
Failure handling
- Exit
3(parse error) — retry in SymPy syntax, then quote the message. - Exit
2(unknown) — report it as unknown and name what was not checked. - Exit
4— report the message verbatim; never fall back to guessing. - D2 disagrees while D4 agrees → verdict
conflict; almost always a unit error.
Limitations
- Only
validate/checkrun the pint layer;derive/matrixare D1–D5 only. - Pint cannot unit-check a decision; the report is a deterministic verdict.
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
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.