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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

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 content is highly actionable and token-efficient, with complete executable examples across the core workflow. Its weaknesses are the absence of explicit validation checkpoints for batch operations and a monolithic structure with no progressive disclosure into reference files.

Suggestions

Add explicit validation checkpoints to batch steps — e.g., confirm a score was created before proceeding, and verify the dataset name exists before adding items — to lift workflow clarity.

Move the longer worked examples (experiment runner, LLM-as-a-Judge) into a references file and link to it from a concise overview section to improve progressive disclosure.

Tighten a few redundant inline comments (e.g., '1 = true, 0 = false') where the code is already self-explanatory.

Dimension	Reasoning	Score
Conciseness	The body is dominated by lean, executable TypeScript with minimal prose and assumes Claude's competence; it avoids explaining concepts Claude already knows. A few inline comments are redundant but every section earns its place.	3 / 3
Actionability	Six complete, copy-paste-ready code blocks cover scores, user feedback, prompt management, datasets, the experiment runner, and LLM-as-a-Judge — fully executable rather than pseudocode.	3 / 3
Workflow Clarity	The six-step sequence is clearly ordered and an Error Handling table aids recovery, but batch operations (scoring traces, populating datasets) lack explicit proactive validation checkpoints; the error table is reactive, so per the validation guideline workflow clarity is capped at 2.	2 / 3
Progressive Disclosure	With no bundle files present there are no one-level-deep references to navigate, and the ~250-line body keeps all six API workflows inline rather than splitting detailed examples into separate files, matching the 'content that should be separate is inline' anchor.	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 strong, third-person description that states concrete capabilities, provides natural trigger phrases, and clearly signals both what the skill does and when to use it. It is clearly distinguishable from other skills.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'Evaluation, scoring, and datasets', 'implementing LLM evaluation, adding user feedback', 'automated quality scoring and experiment datasets' — matching the top anchor for naming several specific capabilities.	3 / 3
Completeness	It answers both 'what' (Evaluation, scoring, and datasets) and 'when' via an explicit 'Use when...' clause plus trigger phrases, satisfying the highest anchor.	3 / 3
Trigger Term Quality	It supplies explicit natural trigger phrases a user would actually say: 'langfuse evaluation', 'langfuse scoring', 'rate llm outputs', 'langfuse feedback', 'langfuse datasets', 'langfuse experiments', giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	It targets a clear niche (Langfuse secondary workflow) with 'langfuse'-prefixed triggers, making it unlikely to fire for unrelated 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
Commit: 3022dd3

Reviewed: 1 day 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.