numerical-check

numerical-check is a Physics, mathematics & simulation skill for AI agents, published by flonat in the flonat-research repository on GitHub. Skillspace rates numerical-check D (68/100) and it passed the safety scan; the rating is based on static analysis only.

Use when you need to numerically stress-test / falsify a SELF-AUTHORED mathematical claim — monotonicity, threshold, comparative-static, inequality, closed-form, or limit — by Monte-Carlo/sweep over its parameter space. Finds a counterexample (definitive falsification) or supports the claim with a large-N no-counterexample sweep, with artifact-avoidance discipline (dense sampling, interior grid, noise-aware tolerance, characterize violators). R1 of the verification spectrum; the empirical arm of mark-unverified for self-authored math. Triggers: numerical-check, 'stress-test my conjecture', 'find a counterexample to', 'is this monotone/threshold true'. NOT for algebra identities (use symbolic-check), machine-proving a lemma (use lean-check), or replicating an empirical result (use cross-language-check).

Grade
D
Quality
68 / 100
Safety
Passed
GitHub stars
118

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubflonat/flonat-research

Our review

Architecture
100 / 100
Maturity
Basic: a single SKILL.md
Security scan
No issues found
License
MIT
Adoption
Adopted by 0 other repositories, in 0 collections

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in Physics, mathematics & simulation

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.