langfuse-core-workflow-a

Execute Langfuse primary workflow: Tracing LLM calls and spans. Use when implementing LLM tracing, building traced AI features, or adding observability to existing LLM applications. Trigger with phrases like "langfuse tracing", "trace LLM calls", "add langfuse to openai", "langfuse spans", "track llm requests".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

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 with complete executable examples and clear step sequencing, but it is monolithic and somewhat redundant, with no progressive disclosure into reference files and no explicit validation checkpoints in the workflow.

Suggestions

Add an explicit verification checkpoint after tracing setup (e.g., 'Run the snippet, then confirm a trace with spans appears in the Langfuse dashboard before continuing').

Split the v3 legacy RAG example and the per-integration details into a reference file (e.g., references/rag-tracing.md) and keep SKILL.md as a concise overview pointing to it.

Trim obvious inline comments ('all calls are now traced automatically') and consolidate the v4+/v3 RAG variants to reduce token cost.

Dimension	Reasoning	Score
Conciseness	The body is code-heavy and avoids explaining concepts Claude already knows, but it carries six full code blocks including redundant parallel v4+ and v3 RAG implementations and several obvious inline comments, so it could be tightened rather than earning the lean score-3 anchor.	2 / 3
Actionability	Every step is backed by complete, copy-paste-ready executable code (TypeScript and Python) with real imports, parameters, and usage objects, matching the fully-executable score-3 anchor.	3 / 3
Workflow Clarity	Steps are clearly numbered (Step 1-6) with prerequisites and an error-handling table, but there are no explicit verification checkpoints (e.g., 'confirm the trace appears in Langfuse') and the recovery guidance is a static table rather than a validate-fix-retry loop.	2 / 3
Progressive Disclosure	The ~250-line SKILL.md is a single monolithic document with all six detailed code examples inline and no bundle/reference files to offload detail to; sections are well-organized but content that should be split out is inline, fitting the score-2 anchor.	2 / 3
	Total	9 / 12 Passed

Description

90%

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

The description is strong overall: it clearly states what the skill does, gives explicit 'Use when' guidance, and supplies natural langfuse-specific trigger phrases. Its only weakness is that the capability list leans on use-case phrasing rather than a fully distinct set of concrete actions.

Suggestions

Tighten the capability statement to enumerate distinct concrete actions (e.g., 'Trace LLM calls and spans, instrument RAG pipelines, capture streaming token usage, integrate LangChain') rather than use-case phrasing like 'building traced AI features'.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete actions ('Tracing LLM calls and spans'), but the remaining phrases ('building traced AI features', 'adding observability') read as use-cases rather than a comprehensive list of distinct concrete actions, falling short of the multi-action score-3 anchor.	2 / 3
Completeness	Explicitly answers both 'what' (Tracing LLM calls and spans) and 'when' via an explicit 'Use when...' clause plus concrete trigger phrases, satisfying the score-3 anchor.	3 / 3
Trigger Term Quality	Provides a strong set of natural trigger phrases users would actually say ('langfuse tracing', 'trace LLM calls', 'add langfuse to openai', 'langfuse spans', 'track llm requests'), matching the good coverage anchor.	3 / 3
Distinctiveness Conflict Risk	The langfuse-specific niche and langfuse-branded trigger phrases make it clearly distinguishable and unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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.