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

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./plugins/saas-packs/langfuse-pack/skills/langfuse-core-workflow-a/SKILL.md

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 body is highly actionable with complete executable code across six tracing patterns and a useful error table, but it is overlong for an overview: the legacy v3 RAG pipeline duplicates the v4 path and should be moved to a deprecated section, and no external reference files are used to offload the detailed examples.

Suggestions

Move the Step 3 v3 legacy RAG pipeline into a clearly labeled 'Deprecated / v3 legacy' section or a separate reference file, since the v4 path already covers the same use case.

Split the larger worked examples (RAG pipeline, streaming, LangChain) into reference files under references/ and keep SKILL.md as a concise overview with one-level-deep links.

Add a validation checkpoint after the OpenAI wrapper step (e.g., 'Confirm traces appear in the Langfuse dashboard') to make the workflow feedback-driven.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean code with little filler, but ~250 lines include a duplicated RAG pipeline (v4 in Step 2 and v3 legacy in Step 3); per the guidelines, version-specific legacy content should live in a clearly marked 'deprecated/old patterns' section rather than an inline parallel example.	2 / 3
Actionability	All six steps provide complete, executable TypeScript/Python with concrete imports, configs, and real API calls — copy-paste ready with no pseudocode.	3 / 3
Workflow Clarity	Steps are clearly labeled and an error-handling table exists, but there are no validation checkpoints (e.g., verifying traces appear in the Langfuse dashboard after wrapping) and sequencing across steps is implicit rather than checkpointed.	2 / 3
Progressive Disclosure	There are no bundle files (references/, scripts/, assets/) and the body contains no one-level-deep file references; ~250 lines of six inline code examples could be split into reference files, so structure is present but content that should be separate is inline.	2 / 3
	Total	9 / 12 Passed

Description

92%

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, well-formed description: it states concrete capabilities, gives explicit 'Use when' guidance and natural trigger phrases, and answers both what and when. Its only weakness is that it does not explicitly distinguish the primary-tracing workflow from the sibling evaluation/scoring skill.

Suggestions

Add a distinguishing clause noting this skill is for tracing/observability, distinct from the evaluation/scoring handled by langfuse-core-workflow-b, to reduce trigger overlap.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Tracing LLM calls and spans', 'building traced AI features', and 'adding observability to existing LLM applications' — matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Explicitly answers both 'what' (tracing LLM calls/spans, observability) and 'when' via an explicit 'Use when...' clause plus trigger phrases, matching the top anchor.	3 / 3
Trigger Term Quality	Provides natural trigger phrases users would say — 'langfuse tracing', 'trace LLM calls', 'add langfuse to openai', 'langfuse spans', 'track llm requests' — giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	The Langfuse LLM-tracing niche is fairly distinct with specific triggers, but the description does not distinguish itself from the sibling 'langfuse-core-workflow-b' skill (referenced in the body), so generic 'langfuse' requests could overlap.	2 / 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
Path: plugins/saas-packs/langfuse-pack/skills/langfuse-core-workflow-a/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.