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

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

68%Weight 40%Scale 1-5

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

A code-forward, actionable tracing guide with well-organized sections and executable examples across six integration patterns. It lacks explicit validation/verification checkpoints, and much of the content is inlined rather than split into reference files.

Suggestions

Add a verification checkpoint after tracing setup (e.g. 'Check the Langfuse dashboard to confirm traces and spans appear') to close the validation gap in workflow_clarity.

Split the v3 legacy RAG example and per-provider integration details into reference files, keeping SKILL.md a concise overview with one-level-deep links.

Define or stub the helper functions (embedText, searchVectorDB, generateAnswer) so the RAG examples are fully copy-paste runnable.

Dimension	Reasoning	Score
Conciseness	Code-forward content with brief, useful comments and no condescending concept explanations; minor redundancy from carrying both v3 and v4+ RAG pipeline examples.	4 / 5
Actionability	Mostly executable tracing code with real imports and method calls across six integrations; minor gaps where helper functions (embedText, searchVectorDB, generateAnswer) are undefined placeholders.	4 / 5
Workflow Clarity	Numbered steps sequence the integration patterns and an error-handling table is provided, but there are no validation checkpoints (e.g. verifying traces appear in Langfuse) or feedback loops.	3 / 5
Progressive Disclosure	Well-organized into clear sections with external resource links and a Next Steps pointer to the sibling skill; bulk inline per-provider code could be split into one-level-deep reference files.	4 / 5
	Total	15 / 20 Passed

Description

78%Weight 40%Scale 1-5

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 specific, well-triggered description that clearly answers both what and when with concrete natural-language triggers. The second-person 'Use when' phrasing costs a specificity point under the voice rule.

Dimension	Reasoning	Score
Specificity	Names several concrete actions ('Tracing LLM calls and spans', 'building traced AI features', 'adding observability'), but reduced by one for second-person voice ('Use when...') per the rubric's voice rule.	3 / 5
Completeness	Explicitly answers both what ('Tracing LLM calls and spans') and when ('Use when implementing LLM tracing...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good coverage of natural trigger phrases a user would say ('langfuse tracing', 'trace LLM calls', 'langfuse spans', 'track llm requests'); a few synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Langfuse-specific triggers carve a clear niche with minimal conflict risk; minor overlap risk against sibling langfuse workflows (e.g. workflow-b).	4 / 5
	Total	16 / 20 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: 8585d6d

Reviewed: 13 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.