moq-analyzers-research-methodology

moq-analyzers-research-methodology is an Agent behaviour & coding discipline skill for AI agents, published by rjmurillo in the moq.analyzers repository on GitHub. Skillspace rates moq-analyzers-research-methodology D (66/100) and it passed the safety scan; the rating is based on static analysis only.

The discipline that turns a hunch into an accepted result in moq.analyzers — the evidence bar (one mechanism must explain ALL observations including negatives), assigned adversarial refutation (the author is never the only tester), predict-numbers-before-running for perf and FP work, the idea lifecycle, and experiment hygiene. Load when proposing a new analyzer idea or fix hypothesis, designing an experiment or corpus study, judging whether a claimed root cause is real, deciding how to write up or retire an investigation, or when someone says "I found the cause", "let's try", "this should be faster", or "can we delete this rule". Do NOT load for executing an already-planned fix (moq-analyzers-rule-lifecycle for new rules, moq-analyzers-fp-convergence-campaign for the backlog), single-claim verification (moq-analyzers-proof-toolkit), picking which open problem to attack (moq-analyzers-research-frontier), or the incident chronicle (moq-analyzers-failure-archaeology).

Grade

D

Quality

66 / 100

Safety

Passed

GitHub stars

23

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.

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