langsmith-prod-evals
Skill1 starsChanged 51 days agoNo licenceView on GitHub
Expert guide for LangSmith production-eval pipelines and prompt versioning, organized by the order you actually hit each problem: instrument → discover your online evals are empty under masking → emit a safe projection → judge → make the score page someone → close the loop into a dataset → gate it in CI → version the prompts. Use whenever the user asks about: LangSmith online evaluators, LLM-as-judge in production, code/composite evaluators, automation rules, alerts on feedback scores, sampling traces, promoting failing traces to datasets, backtesting against production traces, masking/anonymizer-safe evaluation under GDPR, online evals returning empty `{}` on masked traces, in-worker LLM judges, prompt hub, push/pull prompts, commit hashes, prompt tags, staging/production prompt environments, prompt webhooks, CI/CD with LangSmith, or baking versioned prompts at build time for serverless / edge (e.g. Cloudflare Workers) runtimes. Trigger even when the user only says "eval pipeline", "prod monitoring", "trace scoring", "prompt versioning", or "LangSmith workflow".
- Reads credentials
- Installs packages
In this repository8 other files it gives its agents.
- implementation-orchestrationSkill
- llm-pipeline-qualitySkill
- monorepo-navigationSkill
- monorepoSkill
- n8n-automation-builderSkill
- paywall-conversionSkill
- qwen-asr-realtimeSkill
- workers-ai-llm-pipelinesSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “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.
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.