langfuse-core-workflow-b
Set up automated LLM output evaluation and scoring using Langfuse datasets and benchmarks.
Install
mkdir -p .claude/skills/langfuse-core-workflow-b && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/7936" && unzip -o skill.zip -d .claude/skills/langfuse-core-workflow-b && rm skill.zipInstalls to .claude/skills/langfuse-core-workflow-b
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Execute Langfuse secondary workflow: Evaluation, scoring, and datasets.Key capabilities
- →Create numeric scores for LLM traces
- →Implement categorical scores for LLM outputs
- →Apply boolean scores for user feedback
- →Manage versioned prompts for LLM applications
- →Build datasets for LLM evaluation experiments
- →Run experiments with evaluators for LLM benchmarking
How it works
The skill uses the Langfuse SDK to create numeric, categorical, and boolean scores for LLM traces and outputs. It also manages versioned prompts, creates datasets for testing, and runs experiments with custom evaluators.
Inputs & outputs
When to use langfuse-core-workflow-b
- →Create numeric quality scores for traces
- →Implement categorical pass/fail feedback
- →Set up experiment datasets for benchmarking
- →Integrate automated LLM evaluation
About langfuse-core-workflow-b
Configures scoring systems for LLM traces using numeric, categorical, and boolean data. Enables experiment runners and LLM-as-a-Judge patterns within Langfuse.
Execute Langfuse secondary workflow: Evaluation and scoring. Use when implementing LLM evaluation, adding user feedback, or setting up automated quality scoring for AI outputs. Trigger with phrases like "langfuse evaluation", "langfuse scoring", "rate llm outputs", "langfuse feedback", "evaluate ai responses".
Prerequisites
Limitations
- →Score validation errors occur if the value type does not match the dataType
- →LLM judge inconsistency can result from high temperature settings
How it compares
This skill provides a structured framework for LLM evaluation, prompt management, and experiment execution within Langfuse, offering more specific control than manual testing.
Compared to similar skills
langfuse-core-workflow-b side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| langfuse-core-workflow-b (this skill) | 0 | 4mo | Review | Intermediate |
| dependency-upgrade | 26 | 8mo | Review | Intermediate |
| woocommerce-dev-cycle | 5 | 6mo | No flags | Intermediate |
| lint-and-validate | 6 | 10mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by jeremylongshore
View all by jeremylongshore →You might also like
dependency-upgrade
wshobson
Manage major dependency version upgrades with compatibility analysis, staged rollout, and comprehensive testing. Use when upgrading framework versions, updating major dependencies, or managing breaking changes in libraries.
woocommerce-dev-cycle
woocommerce
Run tests, linting, and quality checks for WooCommerce development. Use when running tests, fixing code style, or following the development workflow.
lint-and-validate
davila7
Automatic quality control, linting, and static analysis procedures. Use after every code modification to ensure syntax correctness and project standards. Triggers onKeywords: lint, format, check, validate, types, static analysis.
coverage
alirezarezvani
Analyze test coverage gaps. Use when user says "test coverage", "what's not tested", "coverage gaps", "missing tests", "coverage report", or "what needs testing".
sentry-hello-world
jeremylongshore
Execute capture your first error with Sentry and verify it appears in the dashboard. Use when testing Sentry integration or verifying error capture works. Trigger with phrases like "test sentry", "sentry hello world", "verify sentry", "first sentry error".
verify-translator
zotero
Steps that MUST be performed to verify a Zotero translator after every addition or modification, and before submitting a PR.