langfuse-install-auth
Install and configure Langfuse SDK authentication for LLM observability. Use when setting up a new Langfuse integration, configuring API keys, or initializing Langfuse tracing in your project. Trigger with phrases like "install langfuse", "setup langfuse", "langfuse auth", "configure langfuse API key", "langfuse tracing setup".
67
82%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is a strong skill description that clearly defines its scope (Langfuse SDK authentication and tracing setup), provides explicit 'Use when' guidance, and includes natural trigger phrases. It uses proper third-person voice and is concise without being vague. The narrow, product-specific focus makes it highly distinctive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Install and configure Langfuse SDK authentication', 'configuring API keys', 'initializing Langfuse tracing'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (install and configure Langfuse SDK authentication for LLM observability) and 'when' (setting up a new Langfuse integration, configuring API keys, initializing tracing) with explicit trigger phrases. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms explicitly listed: 'install langfuse', 'setup langfuse', 'langfuse auth', 'configure langfuse API key', 'langfuse tracing setup'. These are phrases users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — 'Langfuse' is a specific product name, and the description is narrowly scoped to SDK authentication and tracing setup. Very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with executable code examples covering multiple languages and SDK versions. Its main weaknesses are moderate verbosity (legacy SDK coverage, explanatory text Claude doesn't need) and lack of explicit validation/error-recovery steps integrated into the workflow. The content would benefit from trimming explanatory prose and adding verification checkpoints with failure handling.
Suggestions
Integrate validation checkpoints into the workflow — e.g., after Step 4/5/6, add explicit 'If you see X error, do Y' guidance rather than relegating it to a separate table.
Trim explanatory text Claude already knows (e.g., what public/secret keys do, dashboard navigation steps) and consider moving the v3 legacy section and SDK comparison table to a separate reference file.
Add a concrete check after environment variable setup (e.g., `echo $LANGFUSE_PUBLIC_KEY` to verify vars are loaded) as a validation checkpoint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary detail for Claude — e.g., explaining what public/secret keys are ('identifies your project', 'grants write access'), step-by-step dashboard navigation instructions, and the full v3 legacy SDK section which adds significant length. The version comparison table and error handling table are useful but the overall content could be tightened. | 2 / 3 |
Actionability | Provides fully executable, copy-paste-ready code for all three environments (TS v4+, TS v3, Python), concrete install commands, environment variable setup, and verification scripts. The error handling table maps specific errors to specific solutions. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced (install → get keys → configure env → initialize → verify), but there are no explicit validation checkpoints or feedback loops. Step 4's verify() function doesn't check for errors or tell you what to do if verification fails — it just says 'check dashboard for trace.' The error handling table partially compensates but isn't integrated into the workflow. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and a logical flow, and it links to external resources. However, with no bundle files, the entire skill is a single monolithic document (~150 lines). The v3 legacy content, SDK comparison table, and error handling could reasonably be split into separate reference files to keep the main skill leaner. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Commit
a04d1a2
- Reviewed
Table of Contents
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.