ai-nondeterministic
Skill0 starsChanged 18 days agoNo licenceView on GitHub
LLM/生成モデルが関わるテストを2局面(テストを書く道具としてのAI活用、製品に組み込まれた非決定的出力そのものの検証)で扱う。 test-catalog の手法カタログの一部。AI/LLM 支援テスト生成(観点出し、偽陽性/偽陰性対策)、 非決定的出力システムのテスト(階層化品質設計、入口/中央/出口層、スキーマ強制、メタモルフィック、複数サンプリング合意) を検証したい、または割り当てたいときに使う。通常は test-catalog スキルの索引経由で 手法が選定された後にこのスキルを直接参照する。
In this repository63 other files it gives its agents.
- blackbox-cause-effectSkill
- blackbox-coveringSkill
- blackbox-partitionSkill
- blackbox-stateSkill
- commit-flowSkill
- diff-reviewSkill
- experience-checklistSkill
- experience-exploratorySkill
- experience-scenarioSkill
- flakiness-concurrencySkill
- flakiness-externalSkill
- flakiness-valueSkill
- formal-verificationSkill
- generative-fuzzingSkill
- generative-propertySkill
- gh-ci-investigateSkill
- good-test-principlesSkill
- ledger-flowSkill
- levels-operationalSkill
- levels-serviceSkill
- levelsSkill
- levels-systemSkill
- loopeng-extractSkill
- loopeng-formalizeSkill
- loopeng-gherkinSkill
- loop-engineeringSkill
- loopeng-modelcheckSkill
- loopeng-smtSkill
- loopeng-tracecheckSkill
- micro-commitSkill
- mutation-testingSkill
- nonfunctional-attributesSkill
- nonfunctional-perfSkill
- nonfunctional-resilienceSkill
- oracle-differentialSkill
- oracle-model-basedSkill
- oracle-past-outputSkill
- oracle-relationalSkill
- pr-createSkill
- process-staticSkill
- rebase-flowSkill
- reset-flowSkill
- review-feedbackSkill
- strategy-allocationSkill
- strategy-operationsSkill
- tdd-cycleSkill
- tdd-green-strategySkill
- test-catalogSkill
- test-design-qualitySkill
- test-designSkill
- test-doublesSkill
- test-extractSkill
- testing-principlesSkill
- test-structure-anatomySkill
- test-structure-lifecycleSkill
- test-target-designSkill
- test-targetedSkill
- test-verifySkill
- using-hymmeSkill
- verifiabilitySkill
- The first 60 shown.
The file
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.