trace-based-testing
Skill46 starsChanged 4 months agoLicence not identifiedView on GitHub
Use this to turn real production traces into a regression test suite, so bugs you saw once never come back. Trigger on "turn traces into tests", "capture this bug as a test", "build tests from production data", "my eval set is out of date", or after debugging a production incident. This is the loop that connects observability to evaluation.
In this repository25 other files it gives its agents.
- add-llm-evalsSkill
- add-llm-fallbacksSkill
- add-llm-guardrailsSkill
- annotate-traces-for-reviewSkill
- build-eval-datasetSkill
- check-answer-consistencySkill
- choose-observability-stackSkill
- collect-user-feedbackSkill
- compare-llm-modelsSkill
- debug-agent-from-tracesSkill
- detect-hallucinationsSkill
- estimate-llm-costSkill
- eval-driven-developmentSkill
- instrument-llm-observabilitySkill
- measure-agent-task-successSkill
- monitor-rag-qualitySkill
- optimize-promptsSkill
- redact-pii-for-tracingSkill
- red-team-llm-appSkill
- reduce-llm-costSkill
- scrub-pii-from-textSkill
- set-up-ab-testingSkill
- set-up-drift-alertsSkill
- trace-multi-agent-systemSkill
- validate-genai-spansSkill
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.