langfuse-core-workflow-b

Execute Langfuse secondary workflow: Evaluation, scoring, and datasets. Use when implementing LLM evaluation, adding user feedback, or setting up automated quality scoring and experiment datasets. Trigger with phrases like "langfuse evaluation", "langfuse scoring", "rate llm outputs", "langfuse feedback", "langfuse datasets", "langfuse experiments".

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Advisory

Suggest reviewing before use

Quality

Content

80%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a strong, executable reference with concise code and a clear step sequence, but it keeps everything inline without bundle files and omits inline validation checkpoints for the batch experiment workflow. Splitting the heavier patterns into reference files and adding an explicit verify step would lift the two middle dimensions.

Suggestions

Add an explicit validation checkpoint in Step 5 (e.g., check result.runs for failures and confirm runCount before declaring success) so the batch experiment flow has a verify-then-proceed loop.

Move the LLM-as-a-Judge and experiment-runner patterns into references/ files (e.g., EVALUATORS.md) and keep SKILL.md as a concise overview with one-level-deep links.

Confirm whether referenced sibling skills (langfuse-common-errors, langfuse-ci-integration) exist as bundle files; if so, link them as clearly signaled one-level references.

Dimension	Reasoning	Score
Conciseness	The body is code-forward with brief section intros and inline comments that earn their place; it avoids explaining concepts Claude already knows (no "what is Langfuse" or library primer padding). Not score 2 because there is no unnecessary explanatory prose to trim.	3 / 3
Actionability	Each step provides complete, copy-paste-ready TypeScript (score.create, prompt.get/compile, datasets, runExperiment, llmJudge) with real argument values. Not score 2 because the examples are executable rather than pseudocode and include the key details.	3 / 3
Workflow Clarity	Steps 1-6 are clearly numbered and an Error Handling table offers recovery guidance, but there are no inline validation checkpoints in the sequence — notably the batch experiment run (Step 5) has no verify step before relying on results. Not score 3 because validation is relegated to an after-the-fact table rather than explicit checkpoints; not score 1 because the sequence itself is clear.	2 / 3
Progressive Disclosure	Sections are well-organized and external docs plus sibling skills are clearly signaled, but the ~250-line skill is monolithic with all six code-heavy steps inline and no references/scripts/assets bundle to offload detail. Not score 3 because content that could be split (e.g., full LLM-as-a-Judge and experiment-runner patterns) is not progressively disclosed; not score 1 because it is not a disorganized wall of text.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-constructed description that states concrete capabilities in third person and supplies explicit trigger guidance with natural keyword variations. It cleanly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Names the Langfuse domain and lists multiple concrete actions — "implementing LLM evaluation", "adding user feedback", "setting up automated quality scoring and experiment datasets" — matching the anchor for multiple specific concrete actions. Not score 2 because the action list is comprehensive rather than partial.	3 / 3
Completeness	Explicitly answers both what ("Execute Langfuse secondary workflow: Evaluation, scoring, and datasets") and when ("Use when implementing..." plus "Trigger with phrases like..."). Not score 2 because the 'when' is explicit, not merely implied.	3 / 3
Trigger Term Quality	Provides natural trigger phrases users would say: "langfuse evaluation", "langfuse scoring", "rate llm outputs", "langfuse feedback", "langfuse datasets", "langfuse experiments". Not score 2 because coverage spans the common variations rather than a single keyword.	3 / 3
Distinctiveness Conflict Risk	Scoped to a distinct Langfuse niche (evaluation/scoring/datasets) with "secondary workflow" naming and Langfuse-prefixed triggers that are unlikely to fire for unrelated skills. Not score 2 because the niche and triggers are clearly differentiated from generic skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/saas-packs/langfuse-pack/skills/langfuse-core-workflow-b/SKILL.md
Commit: b2e8c53

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.