langfuse-hello-world

Create a minimal working Langfuse trace example. Use when starting a new Langfuse integration, testing your setup, or learning basic Langfuse tracing patterns. Trigger with phrases like "langfuse hello world", "langfuse example", "langfuse quick start", "first langfuse trace", "simple langfuse code".

Quality

67%

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-hello-world/SKILL.md

Quality

Content

65%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.

Highly actionable, executable content with strong code examples and a useful error table. Its weaknesses are token inefficiency from inlining four complete SDK variants, missing explicit validation checkpoints in the workflow, and no progressive file split for the redundant variants.

Suggestions

Trim to the single canonical hello-world example inline and move the legacy v3 and Python variants into a referenced file (e.g., references/alternative-sdks.md) to reduce token cost and improve progressive disclosure.

Add an explicit validation step after each example (e.g., 'Confirm the trace appears in the Langfuse dashboard before proceeding') to raise workflow clarity above the missing-checkpoint anchor.

Remove or condense the Trace Hierarchy ASCII diagram since it restates data already visible in the Step 1 code, reclaiming tokens without losing information.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and code-forward, but it provides four full hello-world implementations (v4 modular, observe wrapper, legacy v3, Python) plus a redundant Trace Hierarchy diagram restating data already shown in the code, which is more breadth than a 'hello world' skill needs.	3 / 5
Actionability	Every step is fully executable, copy-paste-ready code with concrete imports, SDK calls, and a complete Error Handling table mapping failures to fixes, covering the common cases comprehensively.	5 / 5
Workflow Clarity	The four steps are clearly labeled and sequenced, but there are no validation checkpoints or verify-success steps (e.g., confirm the trace appears before moving on) — the body relies on a single console.log rather than explicit validation, which is the anchor-3 'checkpoints missing or implicit' case.	3 / 5
Progressive Disclosure	Structure is reasonable with section headers and a Resources list, but there are no bundle files and all four full code variants are inlined in SKILL.md rather than split into referenced files; content that could live one level deep is kept inline.	3 / 5
	Total	14 / 20 Passed

Description

70%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 solid, third-person description with explicit 'Use when' guidance and concrete Langfuse trigger phrases. It is concise and distinct, but the capability list is narrow (one action) and the 'when' scenarios could be more tightly tied to specific trigger phrases.

Suggestions

Broaden the 'what' to list the concrete tracing actions the skill performs (e.g., create traces, spans, generations, and wrap functions with observe) so capability coverage reads as comprehensive rather than a single example.

Tie the 'Use when' scenarios directly to the listed trigger phrases so the 'what' and 'when' reinforce each other at the top completeness anchor.

Dimension	Reasoning	Score
Specificity	The description names the domain ('minimal working Langfuse trace example') and gives one concrete action, but does not enumerate several specific operations, fitting the 'domain and 1-2 concrete actions' anchor.	3 / 5
Completeness	It states what the skill does ('Create a minimal working Langfuse trace example') and when to use it ('Use when starting a new Langfuse integration...'), but the 'when' enumerates scenarios more than concrete trigger phrases tied to the 'what', so it stops just short of the top anchor.	4 / 5
Trigger Term Quality	It lists natural phrases users would actually say ('langfuse hello world', 'langfuse quick start', 'first langfuse trace'), giving good keyword coverage, though it omits synonyms like 'langfuse demo' or extensionless variations.	4 / 5
Distinctiveness Conflict Risk	The Langfuse-specific trigger phrases carve a clear niche with minimal conflict risk against unrelated skills, though it could overlap slightly with adjacent Langfuse integration skills in the same family.	4 / 5
	Total	15 / 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-hello-world/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.